diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml index 02e4fce..0af9318 100644 --- a/.github/workflows/ci.yaml +++ b/.github/workflows/ci.yaml @@ -12,6 +12,64 @@ on: - cron: '0 0 * * *' # runs at 00:00 UTC every day jobs: + Benchmarks: + runs-on: ${{ matrix.os }} + strategy: + fail-fast: false + matrix: + os: [ubuntu-latest] + python-version: ['3.10'] # requires python<=3.9 + model: [yolov8n] + steps: + - uses: actions/checkout@v3 + - uses: actions/setup-python@v4 + with: + python-version: ${{ matrix.python-version }} + #- name: Cache pip + # uses: actions/cache@v3 + # with: + # path: ~/.cache/pip + # key: ${{ runner.os }}-Benchmarks-${{ hashFiles('requirements.txt') }} + # restore-keys: ${{ runner.os }}-Benchmarks- + - name: Install requirements + run: | + python -m pip install --upgrade pip wheel + pip install -e '.[export]' --extra-index-url https://download.pytorch.org/whl/cpu + - name: Check environment + run: | + echo "RUNNER_OS is ${{ runner.os }}" + echo "GITHUB_EVENT_NAME is ${{ github.event_name }}" + echo "GITHUB_WORKFLOW is ${{ github.workflow }}" + echo "GITHUB_ACTOR is ${{ github.actor }}" + echo "GITHUB_REPOSITORY is ${{ github.repository }}" + echo "GITHUB_REPOSITORY_OWNER is ${{ github.repository_owner }}" + python --version + pip --version + pip list + - name: TF Lite export + run: | + yolo export model=${{ matrix.model }}.pt format=tflite + yolo task=detect mode=predict model=yolov8n_saved_model/yolov8n_float16.tflite imgsz=640 + - name: TF *.pb export + run: | + yolo export model=${{ matrix.model }}.pt format=pb + yolo task=detect mode=predict model=yolov8n.pb imgsz=640 + - name: TF Lite Edge TPU export + run: | + yolo export model=${{ matrix.model }}.pt format=edgetpu + - name: TF.js export + run: | + yolo export model=${{ matrix.model }}.pt format=tfjs + - name: Benchmark DetectionModel + run: | + # yolo benchmark model=${{ matrix.model }}.pt imgsz=320 min_metric=0.29 + - name: Benchmark SegmentationModel + run: | + # yolo benchmark model=${{ matrix.model }}-seg.pt imgsz=320 min_metric=0.29 + - name: Benchmark ClassificationModel + run: | + # yolo benchmark model=${{ matrix.model }}-cls.pt imgsz=224 min_metric=0.29 + Tests: timeout-minutes: 60 runs-on: ${{ matrix.os }} @@ -49,15 +107,13 @@ jobs: run: | python -m pip install --upgrade pip wheel if [ "${{ matrix.torch }}" == "1.8.0" ]; then - pip install -e . torch==1.8.0 torchvision==0.9.0 onnx openvino-dev>=2022.3 pytest --extra-index-url https://download.pytorch.org/whl/cpu + pip install -e '.[export]' torch==1.8.0 torchvision==0.9.0 pytest --extra-index-url https://download.pytorch.org/whl/cpu else - pip install -e . onnx openvino-dev>=2022.3 pytest --extra-index-url https://download.pytorch.org/whl/cpu + pip install -e '.[export]' pytest --extra-index-url https://download.pytorch.org/whl/cpu fi - # pip install ultralytics (production) shell: bash # for Windows compatibility - name: Check environment run: | - # python -c "import utils; utils.notebook_init()" echo "RUNNER_OS is ${{ runner.os }}" echo "GITHUB_EVENT_NAME is ${{ github.event_name }}" echo "GITHUB_WORKFLOW is ${{ github.workflow }}" diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 01f13c4..2ab431d 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -31,11 +31,11 @@ repos: name: Upgrade code args: [--py37-plus] - # - repo: https://github.com/PyCQA/isort - # rev: 5.11.4 - # hooks: - # - id: isort - # name: Sort imports + - repo: https://github.com/PyCQA/isort + rev: 5.12.0 + hooks: + - id: isort + name: Sort imports - repo: https://github.com/google/yapf rev: v0.32.0 diff --git a/README.md b/README.md index 23a4d4e..3cddc03 100644 --- a/README.md +++ b/README.md @@ -108,6 +108,12 @@ success = model.export(format="onnx") # export the model to ONNX format Ultralytics [release](https://github.com/ultralytics/assets/releases). See YOLOv8 [Python Docs](https://docs.ultralytics.com/python) for more examples. +#### Model Architectures + +⭐ **NEW** YOLOv5u anchor free models are now available. + +All supported model architectures can be found in the [Models](./ultralytics/models/) section. + #### Known Issues / TODOs We are still working on several parts of YOLOv8! We aim to have these completed soon to bring the YOLOv8 feature set up @@ -152,13 +158,13 @@ See [Detection Docs](https://docs.ultralytics.com/tasks/detection/) for usage ex See [Segmentation Docs](https://docs.ultralytics.com/tasks/segmentation/) for usage examples with these models. -| Model | size
(pixels) | mAPbox
50-95 | mAPmask
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | -| ---------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | -| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | -| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | -| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | -| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | -| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | +| Model | size
(pixels) | mAPbox
50-95 | mAPmask
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | +| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | +| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | +| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | +| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | +| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | +| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | - **mAPval** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset.
Reproduce by `yolo val segment data=coco.yaml device=0` @@ -172,13 +178,13 @@ See [Segmentation Docs](https://docs.ultralytics.com/tasks/segmentation/) for us See [Classification Docs](https://docs.ultralytics.com/tasks/classification/) for usage examples with these models. -| Model | size
(pixels) | acc
top1 | acc
top5 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) at 640 | -| ---------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | -| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | -| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | -| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | -| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | -| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | +| Model | size
(pixels) | acc
top1 | acc
top5 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) at 640 | +| -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | +| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | +| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | +| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | +| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | +| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | - **acc** values are model accuracies on the [ImageNet](https://www.image-net.org/) dataset validation set.
Reproduce by `yolo val classify data=path/to/ImageNet device=0` diff --git a/README.zh-CN.md b/README.zh-CN.md index 805fb39..e9ec585 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -132,13 +132,13 @@ success = model.export(format="onnx") # 将模型导出为 ONNX 格式
实例分割 -| 模型 | 尺寸
（像素） | mAPbox
50-95 | mAPmask
50-95 | 推理速度
CPU ONNX
(ms) | 推理速度
A100 TensorRT
(ms) | 参数量
(M) | FLOPs
(B) | -| ---------------------------------------------------------------------------------------- | --------------- | -------------------- | --------------------- | ----------------------------- | ---------------------------------- | --------------- | ----------------- | -| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | -| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | -| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | -| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | -| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | +| 模型 | 尺寸
（像素） | mAPbox
50-95 | mAPmask
50-95 | 推理速度
CPU ONNX
(ms) | 推理速度
A100 TensorRT
(ms) | 参数量
(M) | FLOPs
(B) | +| -------------------------------------------------------------------------------------------- | --------------- | -------------------- | --------------------- | ----------------------------- | ---------------------------------- | --------------- | ----------------- | +| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | +| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | +| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | +| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | +| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | - **mAPval** 结果都在 [COCO val2017](http://cocodataset.org) 数据集上，使用单模型单尺度测试得到。
复现命令 `yolo val segment data=coco.yaml device=0` @@ -149,13 +149,13 @@ success = model.export(format="onnx") # 将模型导出为 ONNX 格式
分类 -| 模型 | 尺寸
（像素） | acc
top1 | acc
top5 | 推理速度
CPU ONNX
(ms) | 推理速度
A100 TensorRT
(ms) | 参数量
(M) | FLOPs
(B) at 640 | -| ---------------------------------------------------------------------------------------- | --------------- | ---------------- | ---------------- | ----------------------------- | ---------------------------------- | --------------- | ------------------------ | -| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | -| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | -| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | -| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | -| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | +| 模型 | 尺寸
（像素） | acc
top1 | acc
top5 | 推理速度
CPU ONNX
(ms) | 推理速度
A100 TensorRT
(ms) | 参数量
(M) | FLOPs
(B) at 640 | +| -------------------------------------------------------------------------------------------- | --------------- | ---------------- | ---------------- | ----------------------------- | ---------------------------------- | --------------- | ------------------------ | +| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | +| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | +| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | +| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | +| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | - **acc** 都在 [ImageNet](https://www.image-net.org/) 数据集上，使用单模型单尺度测试得到。
复现命令 `yolo val classify data=path/to/ImageNet device=0` diff --git a/docker/Dockerfile b/docker/Dockerfile index 61f43ab..fceb9c7 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -31,8 +31,7 @@ RUN git clone https://github.com/ultralytics/ultralytics /usr/src/ultralytics # Install pip packages COPY requirements.txt . RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache ultralytics albumentations comet gsutil notebook \ - coremltools onnx onnx-simplifier onnxruntime openvino-dev>=2022.3 +RUN pip install --no-cache ultralytics[export] albumentations comet gsutil notebook \ # tensorflow tensorflowjs \ # Set environment variables diff --git a/docker/Dockerfile-arm64 b/docker/Dockerfile-arm64 index 3108c5f..ce33da1 100644 --- a/docker/Dockerfile-arm64 +++ b/docker/Dockerfile-arm64 @@ -26,8 +26,8 @@ RUN git clone https://github.com/ultralytics/ultralytics /usr/src/ultralytics # Install pip packages COPY requirements.txt . RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache ultralytics albumentations gsutil notebook \ - coremltools onnx onnxruntime +RUN pip install --no-cache ultralytics albumentations gsutil notebook + # coremltools onnx onnxruntime \ # tensorflow-aarch64 tensorflowjs \ # Cleanup diff --git a/docker/Dockerfile-cpu b/docker/Dockerfile-cpu index bf515e5..90e5007 100644 --- a/docker/Dockerfile-cpu +++ b/docker/Dockerfile-cpu @@ -26,8 +26,7 @@ RUN git clone https://github.com/ultralytics/ultralytics /usr/src/ultralytics # Install pip packages COPY requirements.txt . RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache ultralytics albumentations gsutil notebook \ - coremltools onnx onnx-simplifier onnxruntime openvino-dev>=2022.3 \ +RUN pip install --no-cache ultralytics[export] albumentations gsutil notebook \ # tensorflow-cpu tensorflowjs \ --extra-index-url https://download.pytorch.org/whl/cpu diff --git a/docs/callbacks.md b/docs/callbacks.md new file mode 100644 index 0000000..5dce9b0 --- /dev/null +++ b/docs/callbacks.md @@ -0,0 +1,75 @@ +## Callbacks +Ultralytics framework supports callbacks as entry points in strategic stages of train, val, export, and predict modes. Each callback accepts a `Trainer`, `Validator`, or `Predictor` object depending on the operation type. All properties of these objects can be found in Reference section of the docs. + +## Examples + +### Returning additional information with Prediction +In this example, we want to return the original frame with each result object. Here's how we can do that +```python +def on_predict_batch_end(predictor): + # results -> List[batch_size] + _, _, im0s, _, _ = predictor.batch + im0s = im0s if isinstance(im0s, list) else [im0s] + predictor.results = zip(predictor.results, im0s) + +model = YOLO(f"yolov8n.pt") +model.add_callback("on_predict_batch_end", on_predict_batch_end) +for (result, frame) in model.track/predict(): + pass +``` + +## All callbacks +Here are all supported callbacks. +### Trainer +`on_pretrain_routine_start` + +`on_pretrain_routine_end` + +`on_train_start` + +`on_train_epoch_start` + +`on_train_batch_start` + +`optimizer_step` + +`on_before_zero_grad` + +`on_train_batch_end` + +`on_train_epoch_end` + +`on_fit_epoch_end` + +`on_model_save` + +`on_train_end` + +`on_params_update` + +`teardown` + +### Validator +`on_val_start` + +`on_val_batch_start` + +`on_val_batch_end` + +`on_val_end` + +### Predictor +`on_predict_start` + +`on_predict_batch_start` + +`on_predict_postprocess_end` + +`on_predict_batch_end` + +`on_predict_end` + +### Exporter +`on_export_start` + +`on_export_end` diff --git a/docs/predict.md b/docs/predict.md index 67606d7..57c41f0 100644 --- a/docs/predict.md +++ b/docs/predict.md @@ -34,7 +34,8 @@ Results object consists of these component objects: - `Results.boxes` : `Boxes` object with properties and methods for manipulating bboxes - `Results.masks` : `Masks` object used to index masks or to get segment coordinates. -- `Results.prob` : `torch.Tensor` containing the class probabilities/logits. +- `Results.probs` : `torch.Tensor` containing the class probabilities/logits. +- `Results.orig_shape` : `tuple` containing the original image size as (height, width). Each result is composed of torch.Tensor by default, in which you can easily use following functionality: @@ -92,3 +93,19 @@ results[0].probs # cls prob, (num_class, ) ``` Class reference documentation for `Results` module and its components can be found [here](reference/results.md) + +## Visualizing results + +You can use `visualize()` function of `Result` object to get a visualization. It plots all componenets(boxes, masks, classification logits, etc) found in the results object +```python + res = model(img) + res_plotted = res[0].visualize() + cv2.imshow("result", res_plotted) +``` +!!! example "`visualize()` arguments" + + `show_conf (bool)`: Show confidence + + `line_width (Float)`: The line width of boxes. Automatically scaled to img size if not provided + + `font_size (Float)`: The font size of . Automatically scaled to img size if not provided diff --git a/docs/tasks/classification.md b/docs/tasks/classification.md index 0f1ac3d..6b60df1 100644 --- a/docs/tasks/classification.md +++ b/docs/tasks/classification.md @@ -90,6 +90,7 @@ Use a trained YOLOv8n-cls model to run predictions on images. yolo classify predict model=yolov8n-cls.pt source="https://ultralytics.com/images/bus.jpg" # predict with official model yolo classify predict model=path/to/best.pt source="https://ultralytics.com/images/bus.jpg" # predict with custom model ``` + Read more details of `predict` in our [Predict](https://docs.ultralytics.com/predict/) page. ## Export @@ -117,20 +118,20 @@ Export a YOLOv8n-cls model to a different format like ONNX, CoreML, etc. yolo export model=path/to/best.pt format=onnx # export custom trained model ``` - Available YOLOv8-cls export formats include: +Available YOLOv8-cls export formats include: + +| Format | `format=` | Model | Metadata | +|--------------------------------------------------------------------|---------------|-------------------------------|----------| +| [PyTorch](https://pytorch.org/) | - | `yolov8n-cls.pt` | ✅ | +| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n-cls.torchscript` | ✅ | +| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n-cls.onnx` | ✅ | +| [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov8n-cls_openvino_model/` | ✅ | +| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n-cls.engine` | ✅ | +| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n-cls.mlmodel` | ✅ | +| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n-cls_saved_model/` | ✅ | +| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n-cls.pb` | ❌ | +| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n-cls.tflite` | ✅ | +| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-cls_edgetpu.tflite` | ✅ | +| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-cls_web_model/` | ✅ | +| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-cls_paddle_model/` | ✅ | - | Format | `format=` | Model | - |----------------------------------------------------------------------------|---------------|-------------------------------| - | [PyTorch](https://pytorch.org/) | - | `yolov8n-cls.pt` | - | [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n-cls.torchscript` | - | [ONNX](https://onnx.ai/) | `onnx` | `yolov8n-cls.onnx` | - | [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov8n-cls_openvino_model/` | - | [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n-cls.engine` | - | [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n-cls.mlmodel` | - | [TensorFlow SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n-cls_saved_model/` | - | [TensorFlow GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n-cls.pb` | - | [TensorFlow Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n-cls.tflite` | - | [TensorFlow Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-cls_edgetpu.tflite` | - | [TensorFlow.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-cls_web_model/` | - | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-cls_paddle_model/` | - diff --git a/docs/tasks/detection.md b/docs/tasks/detection.md index 4374de2..d2f7c4f 100644 --- a/docs/tasks/detection.md +++ b/docs/tasks/detection.md @@ -92,6 +92,7 @@ Use a trained YOLOv8n model to run predictions on images. yolo detect predict model=yolov8n.pt source="https://ultralytics.com/images/bus.jpg" # predict with official model yolo detect predict model=path/to/best.pt source="https://ultralytics.com/images/bus.jpg" # predict with custom model ``` + Read more details of `predict` in our [Predict](https://docs.ultralytics.com/predict/) page. ## Export @@ -119,19 +120,19 @@ Export a YOLOv8n model to a different format like ONNX, CoreML, etc. yolo export model=path/to/best.pt format=onnx # export custom trained model ``` - Available YOLOv8 export formats include: - - | Format | `format=` | Model | - |----------------------------------------------------------------------------|--------------------|---------------------------| - | [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` | - | [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` | - | [ONNX](https://onnx.ai/) | `onnx` | `yolov8n.onnx` | - | [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov8n_openvino_model/` | - | [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` | - | [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlmodel` | - | [TensorFlow SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` | - | [TensorFlow GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` | - | [TensorFlow Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` | - | [TensorFlow Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | - | [TensorFlow.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | - | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | +Available YOLOv8 export formats include: + +| Format | `format=` | Model | Metadata | +|--------------------------------------------------------------------|---------------|---------------------------|----------| +| [PyTorch](https://pytorch.org/) | - | `yolov8n.pt` | ✅ | +| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n.torchscript` | ✅ | +| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n.onnx` | ✅ | +| [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov8n_openvino_model/` | ✅ | +| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n.engine` | ✅ | +| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n.mlmodel` | ✅ | +| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n_saved_model/` | ✅ | +| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n.pb` | ❌ | +| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n.tflite` | ✅ | +| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | +| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | +| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | diff --git a/docs/tasks/segmentation.md b/docs/tasks/segmentation.md index 0dcdc54..5155115 100644 --- a/docs/tasks/segmentation.md +++ b/docs/tasks/segmentation.md @@ -96,6 +96,7 @@ Use a trained YOLOv8n-seg model to run predictions on images. yolo segment predict model=yolov8n-seg.pt source="https://ultralytics.com/images/bus.jpg" # predict with official model yolo segment predict model=path/to/best.pt source="https://ultralytics.com/images/bus.jpg" # predict with custom model ``` + Read more details of `predict` in our [Predict](https://docs.ultralytics.com/predict/) page. ## Export @@ -123,22 +124,21 @@ Export a YOLOv8n-seg model to a different format like ONNX, CoreML, etc. yolo export model=path/to/best.pt format=onnx # export custom trained model ``` - Available YOLOv8-seg export formats include: - - | Format | `format=` | Model | - |----------------------------------------------------------------------------|---------------|-------------------------------| - | [PyTorch](https://pytorch.org/) | - | `yolov8n-seg.pt` | - | [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n-seg.torchscript` | - | [ONNX](https://onnx.ai/) | `onnx` | `yolov8n-seg.onnx` | - | [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov8n-seg_openvino_model/` | - | [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n-seg.engine` | - | [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n-seg.mlmodel` | - | [TensorFlow SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n-seg_saved_model/` | - | [TensorFlow GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n-seg.pb` | - | [TensorFlow Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n-seg.tflite` | - | [TensorFlow Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-seg_edgetpu.tflite` | - | [TensorFlow.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-seg_web_model/` | - | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-seg_paddle_model/` | +Available YOLOv8-seg export formats include: +| Format | `format=` | Model | Metadata | +|--------------------------------------------------------------------|---------------|-------------------------------|----------| +| [PyTorch](https://pytorch.org/) | - | `yolov8n-seg.pt` | ✅ | +| [TorchScript](https://pytorch.org/docs/stable/jit.html) | `torchscript` | `yolov8n-seg.torchscript` | ✅ | +| [ONNX](https://onnx.ai/) | `onnx` | `yolov8n-seg.onnx` | ✅ | +| [OpenVINO](https://docs.openvino.ai/latest/index.html) | `openvino` | `yolov8n-seg_openvino_model/` | ✅ | +| [TensorRT](https://developer.nvidia.com/tensorrt) | `engine` | `yolov8n-seg.engine` | ✅ | +| [CoreML](https://github.com/apple/coremltools) | `coreml` | `yolov8n-seg.mlmodel` | ✅ | +| [TF SavedModel](https://www.tensorflow.org/guide/saved_model) | `saved_model` | `yolov8n-seg_saved_model/` | ✅ | +| [TF GraphDef](https://www.tensorflow.org/api_docs/python/tf/Graph) | `pb` | `yolov8n-seg.pb` | ❌ | +| [TF Lite](https://www.tensorflow.org/lite) | `tflite` | `yolov8n-seg.tflite` | ✅ | +| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-seg_edgetpu.tflite` | ✅ | +| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-seg_web_model/` | ✅ | +| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-seg_paddle_model/` | ✅ | diff --git a/mkdocs.yml b/mkdocs.yml index 95957f2..eef6271 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -1,3 +1,5 @@ +# Ultralytics YOLO 🚀, GPL-3.0 license + site_name: YOLOv8 Docs repo_url: https://github.com/ultralytics/ultralytics edit_uri: https://github.com/ultralytics/ultralytics/tree/main/docs @@ -109,7 +111,8 @@ nav: - Python: python.md - Predict: predict.md - Configuration: cfg.md - - Customization Guide: engine.md + - Customization using callbacks: callbacks.md + - Advanced customization: engine.md - Ultralytics HUB: hub.md - iOS and Android App: app.md - Reference: diff --git a/requirements.txt b/requirements.txt index 3e869ba..8fdd8bd 100644 --- a/requirements.txt +++ b/requirements.txt @@ -25,7 +25,7 @@ seaborn>=0.11.0 # Export -------------------------------------- # coremltools>=6.0 # CoreML export # onnx>=1.12.0 # ONNX export -# onnx-simplifier>=0.4.1 # ONNX simplifier +# onnxsim>=0.4.1 # ONNX simplifier # nvidia-pyindex # TensorRT export # nvidia-tensorrt # TensorRT export # scikit-learn==0.19.2 # CoreML quantization diff --git a/setup.py b/setup.py index 35d85d9..dde8f54 100644 --- a/setup.py +++ b/setup.py @@ -9,7 +9,7 @@ from setuptools import find_packages, setup # Settings FILE = Path(__file__).resolve() PARENT = FILE.parent # root directory -README = (PARENT / "README.md").read_text(encoding="utf-8") +README = (PARENT / 'README.md').read_text(encoding='utf-8') REQUIREMENTS = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements((PARENT / 'requirements.txt').read_text())] PKG_REQUIREMENTS = ['sentry_sdk'] # pip-only requirements @@ -20,45 +20,46 @@ def get_version(): setup( - name="ultralytics", # name of pypi package + name='ultralytics', # name of pypi package version=get_version(), # version of pypi package - python_requires=">=3.7", + python_requires='>=3.7', license='GPL-3.0', description='Ultralytics YOLOv8', long_description=README, - long_description_content_type="text/markdown", - url="https://github.com/ultralytics/ultralytics", + long_description_content_type='text/markdown', + url='https://github.com/ultralytics/ultralytics', project_urls={ 'Bug Reports': 'https://github.com/ultralytics/ultralytics/issues', 'Funding': 'https://ultralytics.com', 'Source': 'https://github.com/ultralytics/ultralytics'}, - author="Ultralytics", + author='Ultralytics', author_email='hello@ultralytics.com', packages=find_packages(), # required include_package_data=True, install_requires=REQUIREMENTS + PKG_REQUIREMENTS, extras_require={ - 'dev': - ['check-manifest', 'pytest', 'pytest-cov', 'coverage', 'mkdocs', 'mkdocstrings[python]', 'mkdocs-material']}, + 'dev': ['check-manifest', 'pytest', 'pytest-cov', 'coverage', 'mkdocs-material', 'mkdocstrings[python]'], + 'export': ['coremltools>=6.0', 'onnx', 'onnxsim', 'onnxruntime', 'openvino-dev>=2022.3'], + 'tf': ['onnx2tf', 'sng4onnx', 'tflite_support', 'tensorflow']}, classifiers=[ - "Development Status :: 4 - Beta", - "Intended Audience :: Developers", - "Intended Audience :: Education", - "Intended Audience :: Science/Research", - "License :: OSI Approved :: GNU General Public License v3 (GPLv3)", - "Programming Language :: Python :: 3", - "Programming Language :: Python :: 3.7", - "Programming Language :: Python :: 3.8", - "Programming Language :: Python :: 3.9", - "Programming Language :: Python :: 3.10", - "Programming Language :: Python :: 3.11", - "Topic :: Software Development", - "Topic :: Scientific/Engineering", - "Topic :: Scientific/Engineering :: Artificial Intelligence", - "Topic :: Scientific/Engineering :: Image Recognition", - "Operating System :: POSIX :: Linux", - "Operating System :: MacOS", - "Operating System :: Microsoft :: Windows",], - keywords="machine-learning, deep-learning, vision, ML, DL, AI, YOLO, YOLOv3, YOLOv5, YOLOv8, HUB, Ultralytics", + 'Development Status :: 4 - Beta', + 'Intended Audience :: Developers', + 'Intended Audience :: Education', + 'Intended Audience :: Science/Research', + 'License :: OSI Approved :: GNU General Public License v3 (GPLv3)', + 'Programming Language :: Python :: 3', + 'Programming Language :: Python :: 3.7', + 'Programming Language :: Python :: 3.8', + 'Programming Language :: Python :: 3.9', + 'Programming Language :: Python :: 3.10', + 'Programming Language :: Python :: 3.11', + 'Topic :: Software Development', + 'Topic :: Scientific/Engineering', + 'Topic :: Scientific/Engineering :: Artificial Intelligence', + 'Topic :: Scientific/Engineering :: Image Recognition', + 'Operating System :: POSIX :: Linux', + 'Operating System :: MacOS', + 'Operating System :: Microsoft :: Windows',], + keywords='machine-learning, deep-learning, vision, ML, DL, AI, YOLO, YOLOv3, YOLOv5, YOLOv8, HUB, Ultralytics', entry_points={ 'console_scripts': ['yolo = ultralytics.yolo.cfg:entrypoint', 'ultralytics = ultralytics.yolo.cfg:entrypoint']}) diff --git a/tests/test_cli.py b/tests/test_cli.py index f594181..21d57e8 100644 --- a/tests/test_cli.py +++ b/tests/test_cli.py @@ -3,7 +3,7 @@ import subprocess from pathlib import Path -from ultralytics.yolo.utils import ROOT, SETTINGS +from ultralytics.yolo.utils import LINUX, ROOT, SETTINGS MODEL = Path(SETTINGS['weights_dir']) / 'yolov8n' CFG = 'yolov8n' @@ -73,3 +73,8 @@ def test_export_segment_torchscript(): def test_export_classify_torchscript(): run(f'yolo export model={MODEL}-cls.pt format=torchscript') + + +def test_export_detect_edgetpu(enabled=False): + if enabled and LINUX: + run(f'yolo export model={MODEL}.pt format=edgetpu') diff --git a/tests/test_python.py b/tests/test_python.py index 351ea1a..0219b8c 100644 --- a/tests/test_python.py +++ b/tests/test_python.py @@ -1,6 +1,5 @@ # Ultralytics YOLO 🚀, GPL-3.0 license -import platform from pathlib import Path import cv2 @@ -10,12 +9,11 @@ from PIL import Image from ultralytics import YOLO from ultralytics.yolo.data.build import load_inference_source -from ultralytics.yolo.utils import ROOT, SETTINGS +from ultralytics.yolo.utils import LINUX, ROOT, SETTINGS MODEL = Path(SETTINGS['weights_dir']) / 'yolov8n.pt' CFG = 'yolov8n.yaml' SOURCE = ROOT / 'assets/bus.jpg' -MACOS = platform.system() == 'Darwin' # macOS environment def test_model_forward(): @@ -87,24 +85,6 @@ def test_train_pretrained(): def test_export_torchscript(): - """ - Format Argument Suffix CPU GPU - 0 PyTorch - .pt True True - 1 TorchScript torchscript .torchscript True True - 2 ONNX onnx .onnx True True - 3 OpenVINO openvino _openvino_model True False - 4 TensorRT engine .engine False True - 5 CoreML coreml .mlmodel True False - 6 TensorFlow SavedModel saved_model _saved_model True True - 7 TensorFlow GraphDef pb .pb True True - 8 TensorFlow Lite tflite .tflite True False - 9 TensorFlow Edge TPU edgetpu _edgetpu.tflite False False - 10 TensorFlow.js tfjs _web_model False False - 11 PaddlePaddle paddle _paddle_model True True - """ - from ultralytics.yolo.engine.exporter import export_formats - print(export_formats()) - model = YOLO(MODEL) f = model.export(format='torchscript') YOLO(f)(SOURCE) # exported model inference @@ -124,9 +104,25 @@ def test_export_openvino(): def test_export_coreml(): # sourcery skip: move-assign model = YOLO(MODEL) - f = model.export(format='coreml') - if MACOS: - YOLO(f)(SOURCE) # model prediction only supported on macOS + model.export(format='coreml') + # if MACOS: + # YOLO(f)(SOURCE) # model prediction only supported on macOS + + +def test_export_tflite(enabled=False): + # TF suffers from install conflicts on Windows and macOS + if enabled and LINUX: + model = YOLO(MODEL) + f = model.export(format='tflite') + YOLO(f)(SOURCE) + + +def test_export_pb(enabled=False): + # TF suffers from install conflicts on Windows and macOS + if enabled and LINUX: + model = YOLO(MODEL) + f = model.export(format='pb') + YOLO(f)(SOURCE) def test_export_paddle(enabled=False): @@ -145,9 +141,8 @@ def test_workflow(): model = YOLO(MODEL) model.train(data="coco8.yaml", epochs=1, imgsz=32) model.val() - print(model.metrics) model.predict(SOURCE) - model.export(format="onnx", opset=12) # export a model to ONNX format + model.export(format="onnx") # export a model to ONNX format def test_predict_callback_and_setup(): @@ -170,3 +165,13 @@ def test_predict_callback_and_setup(): print('test_callback', bs) boxes = result.boxes # Boxes object for bbox outputs print(boxes) + + +def test_result(): + model = YOLO("yolov8n-seg.pt") + img = str(ROOT / "assets/bus.jpg") + res = model([img, img]) + res[0].numpy() + res[0].cpu().numpy() + resimg = res[0].visualize(show_conf=False) + print(resimg) diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py index ab8c107..50ac7f5 100644 --- a/ultralytics/__init__.py +++ b/ultralytics/__init__.py @@ -1,6 +1,6 @@ # Ultralytics YOLO 🚀, GPL-3.0 license -__version__ = "8.0.39" +__version__ = "8.0.40" from ultralytics.yolo.engine.model import YOLO from ultralytics.yolo.utils.checks import check_yolo as checks diff --git a/ultralytics/models/README.md b/ultralytics/models/README.md index e56b6e7..074c418 100644 --- a/ultralytics/models/README.md +++ b/ultralytics/models/README.md @@ -29,8 +29,81 @@ They may also be used directly in a Python environment, and accepts the same ```python from ultralytics import YOLO -model = YOLO("yolov8n.yaml") # build a YOLOv8n model from scratch - +model = YOLO("model.yaml") # build a YOLOv8n model from scratch +# YOLO("model.pt") use pre-trained model if available model.info() # display model information model.train(data="coco128.yaml", epochs=100) # train the model ``` + +## Pre-trained Model Architectures + +Ultralytics supports many model architectures. Visit [models](#) page to view detailed information and usage. +Any of these models can be used by loading their configs or pretrained checkpoints if available. + +What to add your model architecture? [Here's](#) how you can contribute + +### 1. YOLOv8 + +**About** - Cutting edge Detection, Segmentation and Classification models developed by Ultralytics.
+**Citation** - +Available Models: + +- Detection - `yolov8n`, `yolov8s`, `yolov8m`, `yolov8l`, `yolov8x` +- Instance Segmentation - `yolov8n-seg`, `yolov8s-seg`, `yolov8m-seg`, `yolov8l-seg`, `yolov8x-seg` +- Classification - `yolov8n-cls`, `yolov8s-cls`, `yolov8m-cls`, `yolov8l-cls`, `yolov8x-cls` + +
Performance + +### Detection + +| Model | size
(pixels) | mAPval
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | +| ------------------------------------------------------------------------------------ | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | +| [YOLOv8n](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt) | 640 | 37.3 | 80.4 | 0.99 | 3.2 | 8.7 | +| [YOLOv8s](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt) | 640 | 44.9 | 128.4 | 1.20 | 11.2 | 28.6 | +| [YOLOv8m](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt) | 640 | 50.2 | 234.7 | 1.83 | 25.9 | 78.9 | +| [YOLOv8l](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt) | 640 | 52.9 | 375.2 | 2.39 | 43.7 | 165.2 | +| [YOLOv8x](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x.pt) | 640 | 53.9 | 479.1 | 3.53 | 68.2 | 257.8 | + +### Segmentation + +| Model | size
(pixels) | mAPbox
50-95 | mAPmask
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | +| -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | +| [YOLOv8n-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-seg.pt) | 640 | 36.7 | 30.5 | 96.1 | 1.21 | 3.4 | 12.6 | +| [YOLOv8s-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-seg.pt) | 640 | 44.6 | 36.8 | 155.7 | 1.47 | 11.8 | 42.6 | +| [YOLOv8m-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-seg.pt) | 640 | 49.9 | 40.8 | 317.0 | 2.18 | 27.3 | 110.2 | +| [YOLOv8l-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-seg.pt) | 640 | 52.3 | 42.6 | 572.4 | 2.79 | 46.0 | 220.5 | +| [YOLOv8x-seg](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-seg.pt) | 640 | 53.4 | 43.4 | 712.1 | 4.02 | 71.8 | 344.1 | + +### Classification + +| Model | size
(pixels) | acc
top1 | acc
top5 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) at 640 | +| -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ | +| [YOLOv8n-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-cls.pt) | 224 | 66.6 | 87.0 | 12.9 | 0.31 | 2.7 | 4.3 | +| [YOLOv8s-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-cls.pt) | 224 | 72.3 | 91.1 | 23.4 | 0.35 | 6.4 | 13.5 | +| [YOLOv8m-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-cls.pt) | 224 | 76.4 | 93.2 | 85.4 | 0.62 | 17.0 | 42.7 | +| [YOLOv8l-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-cls.pt) | 224 | 78.0 | 94.1 | 163.0 | 0.87 | 37.5 | 99.7 | +| [YOLOv8x-cls](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-cls.pt) | 224 | 78.4 | 94.3 | 232.0 | 1.01 | 57.4 | 154.8 | + +
+ +### 2. YOLOv5u + +**About** - Anchor-free YOLOv5 models with new detection head and better speed-accuracy tradeoff
+**Citation** - +Available Models: + +- Detection - `yolov5nu`, `yolov5su`, `yolov5mu`, `yolov5lu`, `yolov5xu` + +
Performance + +### Detection + +| Model | size
(pixels) | mAPval
50-95 | Speed
CPU ONNX
(ms) | Speed
A100 TensorRT
(ms) | params
(M) | FLOPs
(B) | +| -------------------------------------------------------------------------------------- | --------------------- | -------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- | +| [YOLOv5nu](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5nu.pt) | 640 | 34.3 | 73.6 | 1.06 | 2.6 | 7.7 | +| [YOLOv5su](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5su.pt) | 640 | 43.0 | 120.7 | 1.27 | 9.1 | 24.0 | +| [YOLOv5mu](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5mu.pt) | 640 | 49.0 | 233.9 | 1.86 | 25.1 | 64.2 | +| [YOLOv5lu](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5lu.pt) | 640 | 52.2 | 408.4 | 2.50 | 53.2 | 135.0 | +| [YOLOv5xu](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5xu.pt) | 640 | 53.2 | 763.2 | 3.81 | 97.2 | 246.4 | + +
diff --git a/ultralytics/nn/autobackend.py b/ultralytics/nn/autobackend.py index 9878600..1b93a7b 100644 --- a/ultralytics/nn/autobackend.py +++ b/ultralytics/nn/autobackend.py @@ -24,9 +24,12 @@ def check_class_names(names): # Check class names. Map imagenet class codes to human-readable names if required. Convert lists to dicts. if isinstance(names, list): # names is a list names = dict(enumerate(names)) # convert to dict - if isinstance(names[0], str) and names[0].startswith('n0'): # imagenet class codes, i.e. 'n01440764' - map = yaml_load(ROOT / 'yolo/data/datasets/ImageNet.yaml')['map'] # human-readable names - names = {k: map[v] for k, v in names.items()} + if isinstance(names, dict): + if not all(isinstance(k, int) for k in names.keys()): # convert string keys to int, i.e. '0' to 0 + names = {int(k): v for k, v in names.items()} + if isinstance(names[0], str) and names[0].startswith('n0'): # imagenet class codes, i.e. 'n01440764' + map = yaml_load(ROOT / 'yolo/data/datasets/ImageNet.yaml')['map'] # human-readable names + names = {k: map[v] for k, v in names.items()} return names @@ -129,7 +132,6 @@ class AutoBackend(nn.Module): if batch_dim.is_static: batch_size = batch_dim.get_length() executable_network = ie.compile_model(network, device_name="CPU") # device_name="MYRIAD" for Intel NCS2 - stride, names = self._load_metadata(Path(w).with_suffix('.yaml')) # load metadata elif engine: # TensorRT LOGGER.info(f'Loading {w} for TensorRT inference...') import tensorrt as trt # https://developer.nvidia.com/nvidia-tensorrt-download @@ -138,7 +140,14 @@ class AutoBackend(nn.Module): device = torch.device('cuda:0') Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr')) logger = trt.Logger(trt.Logger.INFO) + # Read file with open(w, 'rb') as f, trt.Runtime(logger) as runtime: + # Read metadata length + meta_len = int.from_bytes(f.read(4), byteorder='little') + # Read metadata + meta = json.loads(f.read(meta_len).decode('utf-8')) + stride, names = int(meta['stride']), meta['names'] + # Read engine model = runtime.deserialize_cuda_engine(f.read()) context = model.create_execution_context() bindings = OrderedDict() @@ -216,7 +225,7 @@ class AutoBackend(nn.Module): meta = ast.literal_eval(model.read(meta_file).decode("utf-8")) stride, names = int(meta['stride']), meta['names'] elif tfjs: # TF.js - raise NotImplementedError('ERROR: YOLOv8 TF.js inference is not supported') + raise NotImplementedError('YOLOv8 TF.js inference is not supported') elif paddle: # PaddlePaddle LOGGER.info(f'Loading {w} for PaddlePaddle inference...') check_requirements('paddlepaddle-gpu' if cuda else 'paddlepaddle') @@ -245,7 +254,16 @@ class AutoBackend(nn.Module): "See https://docs.ultralytics.com/tasks/detection/#export for help." f"\n\n{EXPORT_FORMATS_TABLE}") - # class names + # Load external metadata YAML + if xml or saved_model or paddle: + metadata = Path(w).parent / 'metadata.yaml' + if metadata.exists(): + metadata = yaml_load(metadata) + stride, names = int(metadata['stride']), metadata['names'] # load metadata + else: + LOGGER.warning(f"WARNING ⚠️ Metadata not found at '{metadata}'") + + # Check names if 'names' not in locals(): # names missing names = yaml_load(check_yaml(data))['names'] if data else {i: f'class{i}' for i in range(999)} # assign names = check_class_names(names) @@ -340,7 +358,7 @@ class AutoBackend(nn.Module): if len(self.output_details) == 2: # segment y = [y[1], np.transpose(y[0], (0, 3, 1, 2))] y = [x if isinstance(x, np.ndarray) else x.numpy() for x in y] - y[0][..., :4] *= [w, h, w, h] # xywh normalized to pixels + # y[0][..., :4] *= [w, h, w, h] # xywh normalized to pixels if isinstance(y, (list, tuple)): return self.from_numpy(y[0]) if len(y) == 1 else [self.from_numpy(x) for x in y] @@ -394,18 +412,3 @@ class AutoBackend(nn.Module): types[8] &= not types[9] # tflite &= not edgetpu triton = not any(types) and all([any(s in url.scheme for s in ["http", "grpc"]), url.netloc]) return types + [triton] - - @staticmethod - def _load_metadata(f=Path('path/to/meta.yaml')): - """ - Loads the metadata from a yaml file - - Args: - f: The path to the metadata file. - """ - - # Load metadata from meta.yaml if it exists - if f.exists(): - d = yaml_load(f) - return d['stride'], d['names'] # assign stride, names - return None, None diff --git a/ultralytics/nn/tasks.py b/ultralytics/nn/tasks.py index f44c17d..1529126 100644 --- a/ultralytics/nn/tasks.py +++ b/ultralytics/nn/tasks.py @@ -248,6 +248,9 @@ class SegmentationModel(DetectionModel): def __init__(self, cfg='yolov8n-seg.yaml', ch=3, nc=None, verbose=True): super().__init__(cfg, ch, nc, verbose) + def _forward_augment(self, x): + raise NotImplementedError("WARNING ⚠️ SegmentationModel has not supported augment inference yet!") + class ClassificationModel(BaseModel): # YOLOv8 classification model diff --git a/ultralytics/tracker/__init__.py b/ultralytics/tracker/__init__.py index 9a1ac3d..2eb9f41 100644 --- a/ultralytics/tracker/__init__.py +++ b/ultralytics/tracker/__init__.py @@ -1 +1 @@ -from .trackers import BYTETracker, BOTSORT +from .trackers import BOTSORT, BYTETracker diff --git a/ultralytics/tracker/track.py b/ultralytics/tracker/track.py index 843b116..0da0d6f 100644 --- a/ultralytics/tracker/track.py +++ b/ultralytics/tracker/track.py @@ -1,8 +1,9 @@ -from ultralytics.tracker import BYTETracker, BOTSORT -from ultralytics.yolo.utils.checks import check_requirements, check_yaml -from ultralytics.yolo.utils import IterableSimpleNamespace, yaml_load import torch +from ultralytics.tracker import BOTSORT, BYTETracker +from ultralytics.yolo.utils import IterableSimpleNamespace, yaml_load +from ultralytics.yolo.utils.checks import check_requirements, check_yaml + TRACKER_MAP = {"bytetrack": BYTETracker, "botsort": BOTSORT} check_requirements('lap') # for linear_assignment diff --git a/ultralytics/tracker/trackers/__init__.py b/ultralytics/tracker/trackers/__init__.py index b519a0a..225217c 100644 --- a/ultralytics/tracker/trackers/__init__.py +++ b/ultralytics/tracker/trackers/__init__.py @@ -1,2 +1,2 @@ -from .byte_tracker import BYTETracker from .bot_sort import BOTSORT +from .byte_tracker import BYTETracker diff --git a/ultralytics/tracker/trackers/basetrack.py b/ultralytics/tracker/trackers/basetrack.py index db61567..c19464a 100644 --- a/ultralytics/tracker/trackers/basetrack.py +++ b/ultralytics/tracker/trackers/basetrack.py @@ -1,6 +1,7 @@ -import numpy as np from collections import OrderedDict +import numpy as np + class TrackState: New = 0 diff --git a/ultralytics/tracker/trackers/bot_sort.py b/ultralytics/tracker/trackers/bot_sort.py index c9f3371..fab20a6 100644 --- a/ultralytics/tracker/trackers/bot_sort.py +++ b/ultralytics/tracker/trackers/bot_sort.py @@ -1,10 +1,12 @@ from collections import deque + import numpy as np + from ..utils import matching from ..utils.gmc import GMC from ..utils.kalman_filter import KalmanFilterXYWH -from .byte_tracker import STrack, BYTETracker from .basetrack import TrackState +from .byte_tracker import BYTETracker, STrack class BOTrack(STrack): diff --git a/ultralytics/tracker/trackers/byte_tracker.py b/ultralytics/tracker/trackers/byte_tracker.py index 65c6768..5da2d29 100644 --- a/ultralytics/tracker/trackers/byte_tracker.py +++ b/ultralytics/tracker/trackers/byte_tracker.py @@ -1,8 +1,8 @@ import numpy as np -from .basetrack import BaseTrack, TrackState from ..utils import matching from ..utils.kalman_filter import KalmanFilterXYAH +from .basetrack import BaseTrack, TrackState class STrack(BaseTrack): diff --git a/ultralytics/yolo/cfg/default.yaml b/ultralytics/yolo/cfg/default.yaml index 85a9439..fd7ad9b 100644 --- a/ultralytics/yolo/cfg/default.yaml +++ b/ultralytics/yolo/cfg/default.yaml @@ -112,5 +112,4 @@ cfg: # for overriding defaults.yaml v5loader: False # use legacy YOLOv5 dataloader # Tracker settings ------------------------------------------------------------------------------------------------------ -tracker: botsort # tracker type, ['botsort', 'bytetrack'] -tracker_cfg: null # path to tracker config file +tracker: botsort.yaml # tracker type, ['botsort.yaml', 'bytetrack.yaml'] diff --git a/ultralytics/yolo/data/augment.py b/ultralytics/yolo/data/augment.py index 3c42e61..1809bb0 100644 --- a/ultralytics/yolo/data/augment.py +++ b/ultralytics/yolo/data/augment.py @@ -585,6 +585,7 @@ class Albumentations: new = self.transform(image=im, bboxes=bboxes, class_labels=cls) # transformed labels["img"] = new["image"] labels["cls"] = np.array(new["class_labels"]) + bboxes = np.array(new["bboxes"]) labels["instances"].update(bboxes=bboxes) return labels diff --git a/ultralytics/yolo/engine/exporter.py b/ultralytics/yolo/engine/exporter.py index 1692be8..237b241 100644 --- a/ultralytics/yolo/engine/exporter.py +++ b/ultralytics/yolo/engine/exporter.py @@ -18,8 +18,8 @@ TensorFlow.js | `tfjs` | yolov8n_web_model/ PaddlePaddle | `paddle` | yolov8n_paddle_model/ Requirements: - $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu # CPU - $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow # GPU + $ pip install -r requirements.txt coremltools onnx onnxsim onnxruntime openvino-dev tensorflow-cpu # CPU + $ pip install -r requirements.txt coremltools onnx onnxsim onnxruntime-gpu openvino-dev tensorflow # GPU Python: from ultralytics import YOLO @@ -69,13 +69,14 @@ from ultralytics.nn.tasks import DetectionModel, SegmentationModel from ultralytics.yolo.cfg import get_cfg from ultralytics.yolo.data.dataloaders.stream_loaders import LoadImages from ultralytics.yolo.data.utils import IMAGENET_MEAN, IMAGENET_STD, check_det_dataset -from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, __version__, callbacks, colorstr, get_default_args, yaml_save +from ultralytics.yolo.utils import (DEFAULT_CFG, LINUX, LOGGER, MACOS, WINDOWS, __version__, callbacks, colorstr, + get_default_args, yaml_save) from ultralytics.yolo.utils.checks import check_imgsz, check_requirements, check_version, check_yaml from ultralytics.yolo.utils.files import file_size from ultralytics.yolo.utils.ops import Profile from ultralytics.yolo.utils.torch_utils import get_latest_opset, select_device, smart_inference_mode -MACOS = platform.system() == 'Darwin' # macOS environment +CUDA = torch.cuda.is_available() def export_formats(): @@ -229,27 +230,24 @@ class Exporter: if coreml: # CoreML f[4], _ = self._export_coreml() if any((saved_model, pb, tflite, edgetpu, tfjs)): # TensorFlow formats - LOGGER.warning('WARNING ⚠️ YOLOv8 TensorFlow export support is still under development. ' + LOGGER.warning('WARNING ⚠️ YOLOv8 TensorFlow export is still under development. ' 'Please consider contributing to the effort if you have TF expertise. Thank you!') nms = False f[5], s_model = self._export_saved_model(nms=nms or self.args.agnostic_nms or tfjs, agnostic_nms=self.args.agnostic_nms or tfjs) - - debug = False - if debug: - if pb or tfjs: # pb prerequisite to tfjs - f[6], _ = self._export_pb(s_model) - if tflite or edgetpu: - f[7], _ = self._export_tflite(s_model, - int8=self.args.int8 or edgetpu, - data=self.args.data, - nms=nms, - agnostic_nms=self.args.agnostic_nms) - if edgetpu: - f[8], _ = self._export_edgetpu() - self._add_tflite_metadata(f[8] or f[7]) - if tfjs: - f[9], _ = self._export_tfjs() + if pb or tfjs: # pb prerequisite to tfjs + f[6], _ = self._export_pb(s_model) + if tflite or edgetpu: + f[7] = str(Path(f[5]) / (self.file.stem + '_float16.tflite')) + # f[7], _ = self._export_tflite(s_model, + # int8=self.args.int8 or edgetpu, + # data=self.args.data, + # nms=nms, + # agnostic_nms=self.args.agnostic_nms) + if edgetpu: + f[8], _ = self._export_edgetpu(tflite_model=f[7]) + if tfjs: + f[9], _ = self._export_tfjs() if paddle: # PaddlePaddle f[10], _ = self._export_paddle() @@ -258,13 +256,14 @@ class Exporter: if any(f): f = str(Path(f[-1])) square = self.imgsz[0] == self.imgsz[1] - s = f"WARNING ⚠️ non-PyTorch val requires square images, 'imgsz={self.imgsz}' will not work. Use " \ - f"export 'imgsz={max(self.imgsz)}' if val is required." if not square else '' + s = '' if square else f"WARNING ⚠️ non-PyTorch val requires square images, 'imgsz={self.imgsz}' will not " \ + f"work. Use export 'imgsz={max(self.imgsz)}' if val is required." imgsz = self.imgsz[0] if square else str(self.imgsz)[1:-1].replace(' ', '') + data = f"data={self.args.data}" if model.task == 'segment' and format == 'pb' else '' LOGGER.info( f'\nExport complete ({time.time() - t:.1f}s)' f"\nResults saved to {colorstr('bold', file.parent.resolve())}" - f"\nPredict: yolo task={model.task} mode=predict model={f} imgsz={imgsz}" + f"\nPredict: yolo task={model.task} mode=predict model={f} imgsz={imgsz} {data}" f"\nValidate: yolo task={model.task} mode=val model={f} imgsz={imgsz} data={self.args.data} {s}" f"\nVisualize: https://netron.app") @@ -335,7 +334,7 @@ class Exporter: check_requirements('onnxsim') import onnxsim - LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...') + LOGGER.info(f'{prefix} simplifying with onnxsim {onnxsim.__version__}...') subprocess.run(f'onnxsim {f} {f}', shell=True) except Exception as e: LOGGER.info(f'{prefix} simplifier failure: {e}') @@ -358,7 +357,7 @@ class Exporter: framework="onnx", compress_to_fp16=self.args.half) # export ov.serialize(ov_model, f_ov) # save - yaml_save(Path(f) / self.file.with_suffix('.yaml').name, self.metadata) # add metadata.yaml + yaml_save(Path(f) / 'metadata.yaml', self.metadata) # add metadata.yaml return f, None @try_export @@ -372,7 +371,7 @@ class Exporter: f = str(self.file).replace(self.file.suffix, f'_paddle_model{os.sep}') pytorch2paddle(module=self.model, save_dir=f, jit_type='trace', input_examples=[self.im]) # export - yaml_save(Path(f) / self.file.with_suffix('.yaml').name, self.metadata) # add metadata.yaml + yaml_save(Path(f) / 'metadata.yaml', self.metadata) # add metadata.yaml return f, None @try_export @@ -436,7 +435,7 @@ class Exporter: try: import tensorrt as trt # noqa except ImportError: - if platform.system() == 'Linux': + if LINUX: check_requirements('nvidia-tensorrt', cmds='-U --index-url https://pypi.ngc.nvidia.com') import tensorrt as trt # noqa @@ -482,8 +481,16 @@ class Exporter: f'{prefix} building FP{16 if builder.platform_has_fast_fp16 and self.args.half else 32} engine as {f}') if builder.platform_has_fast_fp16 and self.args.half: config.set_flag(trt.BuilderFlag.FP16) + + # Write file with builder.build_engine(network, config) as engine, open(f, 'wb') as t: + # Metadata + meta = json.dumps(self.metadata) + t.write(len(meta).to_bytes(4, byteorder='little', signed=True)) + t.write(meta.encode()) + # Model t.write(engine.serialize()) + return f, None @try_export @@ -500,10 +507,10 @@ class Exporter: try: import tensorflow as tf # noqa except ImportError: - check_requirements(f"tensorflow{'' if torch.cuda.is_available() else '-macos' if MACOS else '-cpu'}") + check_requirements(f"tensorflow{'' if CUDA else '-macos' if MACOS else '-cpu' if LINUX else ''}") import tensorflow as tf # noqa check_requirements(("onnx", "onnx2tf", "sng4onnx", "onnxsim", "onnx_graphsurgeon", "tflite_support"), - cmds="--extra-index-url https://pypi.ngc.nvidia.com ") + cmds="--extra-index-url https://pypi.ngc.nvidia.com") LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...') f = str(self.file).replace(self.file.suffix, '_saved_model') @@ -514,10 +521,11 @@ class Exporter: # Export to TF SavedModel subprocess.run(f'onnx2tf -i {onnx} -o {f} --non_verbose', shell=True) + yaml_save(Path(f) / 'metadata.yaml', self.metadata) # add metadata.yaml # Add TFLite metadata - for tflite_file in Path(f).rglob('*.tflite'): - self._add_tflite_metadata(tflite_file) + for file in Path(f).rglob('*.tflite'): + self._add_tflite_metadata(file) # Load saved_model keras_model = tf.saved_model.load(f, tags=None, options=None) @@ -537,7 +545,7 @@ class Exporter: try: import tensorflow as tf # noqa except ImportError: - check_requirements(f"tensorflow{'' if torch.cuda.is_available() else '-macos' if MACOS else '-cpu'}") + check_requirements(f"tensorflow{'' if CUDA else '-macos' if MACOS else '-cpu' if LINUX else ''}") import tensorflow as tf # noqa # from models.tf import TFModel from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2 # noqa @@ -628,11 +636,11 @@ class Exporter: return f, None @try_export - def _export_edgetpu(self, prefix=colorstr('Edge TPU:')): + def _export_edgetpu(self, tflite_model='', prefix=colorstr('Edge TPU:')): # YOLOv8 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/ cmd = 'edgetpu_compiler --version' help_url = 'https://coral.ai/docs/edgetpu/compiler/' - assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}' + assert LINUX, f'export only supported on Linux. See {help_url}' if subprocess.run(f'{cmd} >/dev/null', shell=True).returncode != 0: LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}') sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0 # sudo installed on system @@ -646,11 +654,11 @@ class Exporter: ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1] LOGGER.info(f'\n{prefix} starting export with Edge TPU compiler {ver}...') - f = str(self.file).replace(self.file.suffix, '-int8_edgetpu.tflite') # Edge TPU model - f_tfl = str(self.file).replace(self.file.suffix, '-int8.tflite') # TFLite model + f = str(tflite_model).replace('.tflite', '_edgetpu.tflite') # Edge TPU model - cmd = f"edgetpu_compiler -s -d -k 10 --out_dir {self.file.parent} {f_tfl}" + cmd = f"edgetpu_compiler -s -d -k 10 --out_dir {self.file.parent} {tflite_model}" subprocess.run(cmd.split(), check=True) + self._add_tflite_metadata(f) return f, None @try_export @@ -681,6 +689,7 @@ class Exporter: f_json.read_text(), ) j.write(subst) + yaml_save(Path(f) / 'metadata.yaml', self.metadata) # add metadata.yaml return f, None def _add_tflite_metadata(self, file): @@ -736,14 +745,6 @@ class Exporter: populator.populate() tmp_file.unlink() - # TODO Rename this here and in `_add_tflite_metadata` - def _extracted_from__add_tflite_metadata_15(self, _metadata_fb, arg1, arg2): - # Creates input info. - result = _metadata_fb.TensorMetadataT() - result.name = arg1 - result.description = arg2 - return result - def _pipeline_coreml(self, model, prefix=colorstr('CoreML Pipeline:')): # YOLOv8 CoreML pipeline import coremltools as ct # noqa diff --git a/ultralytics/yolo/engine/model.py b/ultralytics/yolo/engine/model.py index 72c32a6..a7fc7b0 100644 --- a/ultralytics/yolo/engine/model.py +++ b/ultralytics/yolo/engine/model.py @@ -42,6 +42,7 @@ class YOLO: model (str, Path): model to load or create type (str): Type/version of models to use. Defaults to "v8". """ + self._reset_callbacks() self.type = type self.ModelClass = None # model class self.TrainerClass = None # trainer class @@ -307,3 +308,8 @@ class YOLO: for arg in 'augment', 'verbose', 'project', 'name', 'exist_ok', 'resume', 'batch', 'epochs', 'cache', \ 'save_json', 'half', 'v5loader', 'device', 'cfg', 'save', 'rect', 'plots', 'opset': args.pop(arg, None) + + @staticmethod + def _reset_callbacks(): + for event in callbacks.default_callbacks.keys(): + callbacks.default_callbacks[event] = [callbacks.default_callbacks[event][0]] diff --git a/ultralytics/yolo/engine/predictor.py b/ultralytics/yolo/engine/predictor.py index 4678238..d7d8b10 100644 --- a/ultralytics/yolo/engine/predictor.py +++ b/ultralytics/yolo/engine/predictor.py @@ -85,7 +85,6 @@ class BasePredictor: self.data = self.args.data # data_dict self.imgsz = None self.device = None - self.classes = self.args.classes self.dataset = None self.vid_path, self.vid_writer = None, None self.annotator = None @@ -103,7 +102,7 @@ class BasePredictor: def write_results(self, results, batch, print_string): raise NotImplementedError("print_results function needs to be implemented") - def postprocess(self, preds, img, orig_img, classes=None): + def postprocess(self, preds, img, orig_img): return preds @smart_inference_mode() @@ -170,13 +169,13 @@ class BasePredictor: # postprocess with self.dt[2]: - self.results = self.postprocess(preds, im, im0s, self.classes) + self.results = self.postprocess(preds, im, im0s) self.run_callbacks("on_predict_postprocess_end") # visualize, save, write results for i in range(len(im)): - p, im0 = (path[i], im0s[i].copy()) if self.source_type.webcam or self.source_type.from_img else (path, - im0s) + p, im0 = (path[i], im0s[i].copy()) if self.source_type.webcam or self.source_type.from_img \ + else (path, im0s.copy()) p = Path(p) if self.args.verbose or self.args.save or self.args.save_txt or self.args.show: diff --git a/ultralytics/yolo/engine/results.py b/ultralytics/yolo/engine/results.py index 9b67656..404e6fd 100644 --- a/ultralytics/yolo/engine/results.py +++ b/ultralytics/yolo/engine/results.py @@ -1,9 +1,13 @@ +from copy import deepcopy from functools import lru_cache import numpy as np import torch +import torchvision.transforms.functional as F +from PIL import Image from ultralytics.yolo.utils import LOGGER, ops +from ultralytics.yolo.utils.plotting import Annotator, colors class Results: @@ -14,22 +18,24 @@ class Results: boxes (Boxes, optional): A Boxes object containing the detection bounding boxes. masks (Masks, optional): A Masks object containing the detection masks. probs (torch.Tensor, optional): A tensor containing the detection class probabilities. - orig_shape (tuple, optional): Original image size. + orig_img (tuple, optional): Original image size. Attributes: boxes (Boxes, optional): A Boxes object containing the detection bounding boxes. masks (Masks, optional): A Masks object containing the detection masks. probs (torch.Tensor, optional): A tensor containing the detection class probabilities. - orig_shape (tuple, optional): Original image size. + orig_img (tuple, optional): Original image size. data (torch.Tensor): The raw masks tensor """ - def __init__(self, boxes=None, masks=None, probs=None, orig_shape=None) -> None: - self.boxes = Boxes(boxes, orig_shape) if boxes is not None else None # native size boxes - self.masks = Masks(masks, orig_shape) if masks is not None else None # native size or imgsz masks + def __init__(self, boxes=None, masks=None, probs=None, orig_img=None, names=None) -> None: + self.orig_img = orig_img + self.orig_shape = orig_img.shape[:2] + self.boxes = Boxes(boxes, self.orig_shape) if boxes is not None else None # native size boxes + self.masks = Masks(masks, self.orig_shape) if masks is not None else None # native size or imgsz masks self.probs = probs if probs is not None else None - self.orig_shape = orig_shape + self.names = names self.comp = ["boxes", "masks", "probs"] def pandas(self): @@ -37,7 +43,7 @@ class Results: # TODO masks.pandas + boxes.pandas + cls.pandas def __getitem__(self, idx): - r = Results(orig_shape=self.orig_shape) + r = Results(orig_img=self.orig_img) for item in self.comp: if getattr(self, item) is None: continue @@ -53,7 +59,7 @@ class Results: self.probs = probs def cpu(self): - r = Results(orig_shape=self.orig_shape) + r = Results(orig_img=self.orig_img) for item in self.comp: if getattr(self, item) is None: continue @@ -61,7 +67,7 @@ class Results: return r def numpy(self): - r = Results(orig_shape=self.orig_shape) + r = Results(orig_img=self.orig_img) for item in self.comp: if getattr(self, item) is None: continue @@ -69,7 +75,7 @@ class Results: return r def cuda(self): - r = Results(orig_shape=self.orig_shape) + r = Results(orig_img=self.orig_img) for item in self.comp: if getattr(self, item) is None: continue @@ -77,7 +83,7 @@ class Results: return r def to(self, *args, **kwargs): - r = Results(orig_shape=self.orig_shape) + r = Results(orig_img=self.orig_img) for item in self.comp: if getattr(self, item) is None: continue @@ -118,6 +124,40 @@ class Results: orig_shape (tuple, optional): Original image size. """) + def visualize(self, show_conf=True, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'): + """ + Plots the given result on an input RGB image. Accepts cv2(numpy) or PIL Image + + Args: + show_conf (bool): Show confidence + line_width (Float): The line width of boxes. Automatically scaled to img size if not provided + font_size (Float): The font size of . Automatically scaled to img size if not provided + """ + img = deepcopy(self.orig_img) + annotator = Annotator(img, line_width, font_size, font, pil, example) + boxes = self.boxes + masks = self.masks.data + logits = self.probs + names = self.names + if boxes is not None: + for d in reversed(boxes): + cls, conf = d.cls.squeeze(), d.conf.squeeze() + c = int(cls) + label = (f'{names[c]}' if names else f'{c}') + (f'{conf:.2f}' if show_conf else '') + annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True)) + + if masks is not None: + im_gpu = torch.as_tensor(img, dtype=torch.float16).permute(2, 0, 1).flip(0).contiguous() + im_gpu = F.resize(im_gpu, masks.data.shape[1:]) / 255 + annotator.masks(masks.data, colors=[colors(x, True) for x in boxes.cls], im_gpu=im_gpu) + + if logits is not None: + top5i = logits.argsort(0, descending=True)[:5].tolist() # top 5 indices + text = f"{', '.join(f'{names[j] if names else j} {logits[j]:.2f}' for j in top5i)}, " + annotator.text((32, 32), text, txt_color=(255, 255, 255)) # TODO: allow setting colors + + return img + class Boxes: """ diff --git a/ultralytics/yolo/utils/__init__.py b/ultralytics/yolo/utils/__init__.py index bbc6379..c67d28a 100644 --- a/ultralytics/yolo/utils/__init__.py +++ b/ultralytics/yolo/utils/__init__.py @@ -34,6 +34,7 @@ AUTOINSTALL = str(os.getenv('YOLO_AUTOINSTALL', True)).lower() == 'true' # glob VERBOSE = str(os.getenv('YOLO_VERBOSE', True)).lower() == 'true' # global verbose mode TQDM_BAR_FORMAT = '{l_bar}{bar:10}{r_bar}' # tqdm bar format LOGGING_NAME = 'ultralytics' +MACOS, LINUX, WINDOWS = (platform.system() == x for x in ['Darwin', 'Linux', 'Windows']) # environment booleans HELP_MSG = \ """ Usage examples for running YOLOv8: @@ -393,18 +394,15 @@ def get_user_config_dir(sub_dir='Ultralytics'): Returns: Path: The path to the user config directory. """ - # Get the operating system name - os_name = platform.system() - # Return the appropriate config directory for each operating system - if os_name == 'Windows': + if WINDOWS: path = Path.home() / 'AppData' / 'Roaming' / sub_dir - elif os_name == 'Darwin': # macOS + elif MACOS: # macOS path = Path.home() / 'Library' / 'Application Support' / sub_dir - elif os_name == 'Linux': + elif LINUX: path = Path.home() / '.config' / sub_dir else: - raise ValueError(f'Unsupported operating system: {os_name}') + raise ValueError(f'Unsupported operating system: {platform.system()}') # GCP and AWS lambda fix, only /tmp is writeable if not is_dir_writeable(str(path.parent)): @@ -421,7 +419,7 @@ USER_CONFIG_DIR = get_user_config_dir() # Ultralytics settings dir def emojis(string=''): # Return platform-dependent emoji-safe version of string - return string.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else string + return string.encode().decode('ascii', 'ignore') if WINDOWS else string def colorstr(*input): @@ -617,7 +615,7 @@ def set_settings(kwargs, file=USER_CONFIG_DIR / 'settings.yaml'): # Set logger set_logging(LOGGING_NAME) # run before defining LOGGER LOGGER = logging.getLogger(LOGGING_NAME) # define globally (used in train.py, val.py, detect.py, etc.) -if platform.system() == 'Windows': +if WINDOWS: for fn in LOGGER.info, LOGGER.warning: setattr(LOGGER, fn.__name__, lambda x: fn(emojis(x))) # emoji safe logging diff --git a/ultralytics/yolo/utils/ops.py b/ultralytics/yolo/utils/ops.py index 5c95684..2004e3e 100644 --- a/ultralytics/yolo/utils/ops.py +++ b/ultralytics/yolo/utils/ops.py @@ -139,6 +139,9 @@ def non_max_suppression( labels=(), max_det=300, nc=0, # number of classes (optional) + max_time_img=0.05, + max_nms=30000, + max_wh=7680, ): """ Perform non-maximum suppression (NMS) on a set of boxes, with support for masks and multiple labels per box. @@ -160,6 +163,9 @@ def non_max_suppression( output by a dataloader, with each label being a tuple of (class_index, x1, y1, x2, y2). max_det (int): The maximum number of boxes to keep after NMS. nc (int): (optional) The number of classes output by the model. Any indices after this will be considered masks. + max_time_img (float): The maximum time (seconds) for processing one image. + max_nms (int): The maximum number of boxes into torchvision.ops.nms(). + max_wh (int): The maximum box width and height in pixels Returns: (List[torch.Tensor]): A list of length batch_size, where each element is a tensor of @@ -185,9 +191,7 @@ def non_max_suppression( # Settings # min_wh = 2 # (pixels) minimum box width and height - max_wh = 7680 # (pixels) maximum box width and height - max_nms = 30000 # maximum number of boxes into torchvision.ops.nms() - time_limit = 0.5 + 0.05 * bs # seconds to quit after + time_limit = 0.5 + max_time_img * bs # seconds to quit after redundant = True # require redundant detections multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img) merge = False # use merge-NMS diff --git a/ultralytics/yolo/utils/plotting.py b/ultralytics/yolo/utils/plotting.py index 43d547e..4e3af60 100644 --- a/ultralytics/yolo/utils/plotting.py +++ b/ultralytics/yolo/utils/plotting.py @@ -136,7 +136,11 @@ class Annotator: if anchor == 'bottom': # start y from font bottom w, h = self.font.getsize(text) # text width, height xy[1] += 1 - h - self.draw.text(xy, text, fill=txt_color, font=self.font) + if self.pil: + self.draw.text(xy, text, fill=txt_color, font=self.font) + else: + tf = max(self.lw - 1, 1) # font thickness + cv2.putText(self.im, text, xy, 0, self.lw / 3, txt_color, thickness=tf, lineType=cv2.LINE_AA) def fromarray(self, im): # Update self.im from a numpy array diff --git a/ultralytics/yolo/v8/classify/predict.py b/ultralytics/yolo/v8/classify/predict.py index efd311c..f80c834 100644 --- a/ultralytics/yolo/v8/classify/predict.py +++ b/ultralytics/yolo/v8/classify/predict.py @@ -18,11 +18,12 @@ class ClassificationPredictor(BasePredictor): img = img.half() if self.model.fp16 else img.float() # uint8 to fp16/32 return img - def postprocess(self, preds, img, orig_img, classes=None): + def postprocess(self, preds, img, orig_img): results = [] for i, pred in enumerate(preds): - shape = orig_img[i].shape if isinstance(orig_img, list) else orig_img.shape - results.append(Results(probs=pred, orig_shape=shape[:2])) + orig_img = orig_img[i] if isinstance(orig_img, list) else orig_img + results.append(Results(probs=pred.softmax(0), orig_img=orig_img, names=self.model.names)) + return results def write_results(self, idx, results, batch): diff --git a/ultralytics/yolo/v8/detect/predict.py b/ultralytics/yolo/v8/detect/predict.py index 69ae86f..cdc0251 100644 --- a/ultralytics/yolo/v8/detect/predict.py +++ b/ultralytics/yolo/v8/detect/predict.py @@ -19,7 +19,7 @@ class DetectionPredictor(BasePredictor): img /= 255 # 0 - 255 to 0.0 - 1.0 return img - def postprocess(self, preds, img, orig_img, classes=None): + def postprocess(self, preds, img, orig_img): preds = ops.non_max_suppression(preds, self.args.conf, self.args.iou, @@ -29,9 +29,10 @@ class DetectionPredictor(BasePredictor): results = [] for i, pred in enumerate(preds): - shape = orig_img[i].shape if isinstance(orig_img, list) else orig_img.shape + orig_img = orig_img[i] if isinstance(orig_img, list) else orig_img + shape = orig_img.shape pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], shape).round() - results.append(Results(boxes=pred, orig_shape=shape[:2])) + results.append(Results(boxes=pred, orig_img=orig_img, names=self.model.names)) return results def write_results(self, idx, results, batch): diff --git a/ultralytics/yolo/v8/segment/predict.py b/ultralytics/yolo/v8/segment/predict.py index 9606b6e..6942a4b 100644 --- a/ultralytics/yolo/v8/segment/predict.py +++ b/ultralytics/yolo/v8/segment/predict.py @@ -10,7 +10,7 @@ from ultralytics.yolo.v8.detect.predict import DetectionPredictor class SegmentationPredictor(DetectionPredictor): - def postprocess(self, preds, img, orig_img, classes=None): + def postprocess(self, preds, img, orig_img): # TODO: filter by classes p = ops.non_max_suppression(preds[0], self.args.conf, @@ -22,9 +22,11 @@ class SegmentationPredictor(DetectionPredictor): results = [] proto = preds[1][-1] if len(preds[1]) == 3 else preds[1] # second output is len 3 if pt, but only 1 if exported for i, pred in enumerate(p): - shape = orig_img[i].shape if isinstance(orig_img, list) else orig_img.shape + orig_img = orig_img[i] if isinstance(orig_img, list) else orig_img + shape = orig_img.shape if not len(pred): - results.append(Results(boxes=pred[:, :6], orig_shape=shape[:2])) # save empty boxes + results.append(Results(boxes=pred[:, :6], orig_img=orig_img, + names=self.model.names)) # save empty boxes continue if self.args.retina_masks: pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], shape).round() @@ -32,7 +34,7 @@ class SegmentationPredictor(DetectionPredictor): else: masks = ops.process_mask(proto[i], pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True) # HWC pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], shape).round() - results.append(Results(boxes=pred[:, :6], masks=masks, orig_shape=shape[:2])) + results.append(Results(boxes=pred[:, :6], masks=masks, orig_img=orig_img, names=self.model.names)) return results def write_results(self, idx, results, batch): diff --git a/ultralytics/yolo/v8/segment/val.py b/ultralytics/yolo/v8/segment/val.py index 556ac1f..40bc687 100644 --- a/ultralytics/yolo/v8/segment/val.py +++ b/ultralytics/yolo/v8/segment/val.py @@ -28,19 +28,8 @@ class SegmentationValidator(DetectionValidator): return batch def init_metrics(self, model): - val = self.data.get(self.args.split, '') # validation path - self.is_coco = isinstance(val, str) and val.endswith(f'coco{os.sep}val2017.txt') # is COCO dataset - self.class_map = ops.coco80_to_coco91_class() if self.is_coco else list(range(1000)) - self.args.save_json |= self.is_coco and not self.training # run on final val if training COCO - self.names = model.names - self.nc = len(model.names) - self.metrics.names = self.names - self.metrics.plot = self.args.plots - self.confusion_matrix = ConfusionMatrix(nc=self.nc) + super().init_metrics(model) self.plot_masks = [] - self.seen = 0 - self.jdict = [] - self.stats = [] if self.args.save_json: check_requirements('pycocotools>=2.0.6') self.process = ops.process_mask_upsample # more accurate