ultralytics 8.0.90 actions and docs improvements (#2326)
Co-authored-by: calmisential <xinyu_std@163.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: triple Mu <gpu@163.com> Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com> Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com> Co-authored-by: Laughing-q <1185102784@qq.com> Co-authored-by: ran xiao <ben.xiao@me.com> Co-authored-by: rxiao <ran.xiao@silverpond.com.au>
This commit is contained in:
Glenn Jocher
GitHub
@ -1,6 +1,6 @@
|
||||
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
||||
|
||||
__version__ = '8.0.89'
|
||||
__version__ = '8.0.90'
|
||||
|
||||
from ultralytics.hub import start
|
||||
from ultralytics.vit.sam import SAM
|
||||
|
||||
@ -12,7 +12,7 @@ directory provides a great starting point for your custom model development need
|
||||
|
||||
To get started, simply browse through the models in this directory and find one that best suits your needs. Once you've
|
||||
selected a model, you can use the provided `*.yaml` file to train and deploy your custom YOLO model with ease. See full
|
||||
details at the Ultralytics [Docs](https://docs.ultralytics.com), and if you need help or have any questions, feel free
|
||||
details at the Ultralytics [Docs](https://docs.ultralytics.com/models), and if you need help or have any questions, feel free
|
||||
to reach out to the Ultralytics team for support. So, don't wait, start creating your custom YOLO model now!
|
||||
|
||||
### Usage
|
||||
@ -37,92 +37,9 @@ 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.
|
||||
Ultralytics supports many model architectures. Visit https://docs.ultralytics.com/models to view detailed information
|
||||
and usage. Any of these models can be used by loading their configs or pretrained checkpoints if available.
|
||||
|
||||
<b>What to add your model architecture?</b> [Here's](#) how you can contribute
|
||||
## Contributing New Models
|
||||
|
||||
### 1. YOLOv8
|
||||
|
||||
**About** - Cutting edge Detection, Segmentation, Classification and Pose models developed by Ultralytics. </br>
|
||||
|
||||
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`
|
||||
- Pose - `yolov8n-pose`, `yolov8s-pose`, `yolov8m-pose`, `yolov8l-pose`, `yolov8x-pose`, `yolov8x-pose-p6`
|
||||
|
||||
<details><summary>Performance</summary>
|
||||
|
||||
### Detection
|
||||
|
||||
| Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(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<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(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<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(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 |
|
||||
|
||||
### Pose
|
||||
|
||||
| Model | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
|
||||
| ---------------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
|
||||
| [YOLOv8n-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n-pose.pt) | 640 | 50.4 | 80.1 | 131.8 | 1.18 | 3.3 | 9.2 |
|
||||
| [YOLOv8s-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s-pose.pt) | 640 | 60.0 | 86.2 | 233.2 | 1.42 | 11.6 | 30.2 |
|
||||
| [YOLOv8m-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m-pose.pt) | 640 | 65.0 | 88.8 | 456.3 | 2.00 | 26.4 | 81.0 |
|
||||
| [YOLOv8l-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l-pose.pt) | 640 | 67.6 | 90.0 | 784.5 | 2.59 | 44.4 | 168.6 |
|
||||
| [YOLOv8x-pose](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose.pt) | 640 | 69.2 | 90.2 | 1607.1 | 3.73 | 69.4 | 263.2 |
|
||||
| [YOLOv8x-pose-p6](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8x-pose-p6.pt) | 1280 | 71.6 | 91.2 | 4088.7 | 10.04 | 99.1 | 1066.4 |
|
||||
|
||||
</details>
|
||||
|
||||
### 2. YOLOv5u
|
||||
|
||||
**About** - Anchor-free YOLOv5 models with new detection head and better speed-accuracy tradeoff </br>
|
||||
|
||||
Available Models:
|
||||
|
||||
- Detection P5/32 - `yolov5nu`, `yolov5su`, `yolov5mu`, `yolov5lu`, `yolov5xu`
|
||||
- Detection P6/64 - `yolov5n6u`, `yolov5s6u`, `yolov5m6u`, `yolov5l6u`, `yolov5x6u`
|
||||
|
||||
<details><summary>Performance</summary>
|
||||
|
||||
### Detection
|
||||
|
||||
| Model | size<br><sup>(pixels) | mAP<sup>val<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>A100 TensorRT<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(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 |
|
||||
| | | | | | | |
|
||||
| [YOLOv5n6u](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5n6u.pt) | 1280 | 42.1 | - | - | 4.3 | 7.8 |
|
||||
| [YOLOv5s6u](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5s6u.pt) | 1280 | 48.6 | - | - | 15.3 | 24.6 |
|
||||
| [YOLOv5m6u](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5m6u.pt) | 1280 | 53.6 | - | - | 41.2 | 65.7 |
|
||||
| [YOLOv5l6u](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5l6u.pt) | 1280 | 55.7 | - | - | 86.1 | 137.4 |
|
||||
| [YOLOv5x6u](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov5x6u.pt) | 1280 | 56.8 | - | - | 155.4 | 250.7 |
|
||||
|
||||
</details>
|
||||
If you've developed a new model architecture or have improvements for existing models that you'd like to contribute to the Ultralytics community, please submit your contribution in a new Pull Request. For more details, visit our [Contributing Guide](https://docs.ultralytics.com/help/contributing).
|
||||
|
||||
@ -13,6 +13,7 @@ from ultralytics.nn.modules import (C1, C2, C3, C3TR, SPP, SPPF, Bottleneck, Bot
|
||||
GhostBottleneck, GhostConv, Pose, Segment)
|
||||
from ultralytics.yolo.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, colorstr, emojis, yaml_load
|
||||
from ultralytics.yolo.utils.checks import check_requirements, check_suffix, check_yaml
|
||||
from ultralytics.yolo.utils.plotting import feature_visualization
|
||||
from ultralytics.yolo.utils.torch_utils import (fuse_conv_and_bn, fuse_deconv_and_bn, initialize_weights,
|
||||
intersect_dicts, make_divisible, model_info, scale_img, time_sync)
|
||||
|
||||
@ -58,8 +59,7 @@ class BaseModel(nn.Module):
|
||||
x = m(x) # run
|
||||
y.append(x if m.i in self.save else None) # save output
|
||||
if visualize:
|
||||
LOGGER.info('visualize feature not yet supported')
|
||||
# TODO: feature_visualization(x, m.type, m.i, save_dir=visualize)
|
||||
feature_visualization(x, m.type, m.i, save_dir=visualize)
|
||||
return x
|
||||
|
||||
def _profile_one_layer(self, m, x, dt):
|
||||
|
||||
@ -217,7 +217,7 @@ class BYTETracker:
|
||||
strack_pool = self.joint_stracks(tracked_stracks, self.lost_stracks)
|
||||
# Predict the current location with KF
|
||||
self.multi_predict(strack_pool)
|
||||
if hasattr(self, 'gmc'):
|
||||
if hasattr(self, 'gmc') and img is not None:
|
||||
warp = self.gmc.apply(img, dets)
|
||||
STrack.multi_gmc(strack_pool, warp)
|
||||
STrack.multi_gmc(unconfirmed, warp)
|
||||
|
||||
@ -233,10 +233,10 @@ class PromptEncoder(nn.Module):
|
||||
embeddings.
|
||||
|
||||
Arguments:
|
||||
points (tuple(torch.Tensor, torch.Tensor) or none): point coordinates
|
||||
points (tuple(torch.Tensor, torch.Tensor), None): point coordinates
|
||||
and labels to embed.
|
||||
boxes (torch.Tensor or none): boxes to embed
|
||||
masks (torch.Tensor or none): masks to embed
|
||||
boxes (torch.Tensor, None): boxes to embed
|
||||
masks (torch.Tensor, None): masks to embed
|
||||
|
||||
Returns:
|
||||
torch.Tensor: sparse embeddings for the points and boxes, with shape
|
||||
@ -337,7 +337,7 @@ class Block(nn.Module):
|
||||
rel_pos_zero_init (bool): If True, zero initialize relative positional parameters.
|
||||
window_size (int): Window size for window attention blocks. If it equals 0, then
|
||||
use global attention.
|
||||
input_size (tuple(int, int) or None): Input resolution for calculating the relative
|
||||
input_size (tuple(int, int), None): Input resolution for calculating the relative
|
||||
positional parameter size.
|
||||
"""
|
||||
super().__init__()
|
||||
@ -392,9 +392,8 @@ class Attention(nn.Module):
|
||||
dim (int): Number of input channels.
|
||||
num_heads (int): Number of attention heads.
|
||||
qkv_bias (bool): If True, add a learnable bias to query, key, value.
|
||||
rel_pos (bool): If True, add relative positional embeddings to the attention map.
|
||||
rel_pos_zero_init (bool): If True, zero initialize relative positional parameters.
|
||||
input_size (tuple(int, int) or None): Input resolution for calculating the relative
|
||||
input_size (tuple(int, int), None): Input resolution for calculating the relative
|
||||
positional parameter size.
|
||||
"""
|
||||
super().__init__()
|
||||
|
||||
@ -45,7 +45,7 @@ class SamAutomaticMaskGenerator:
|
||||
|
||||
Arguments:
|
||||
model (Sam): The SAM model to use for mask prediction.
|
||||
points_per_side (int or None): The number of points to be sampled
|
||||
points_per_side (int, None): The number of points to be sampled
|
||||
along one side of the image. The total number of points is
|
||||
points_per_side**2. If None, 'point_grids' must provide explicit
|
||||
point sampling.
|
||||
@ -70,7 +70,7 @@ class SamAutomaticMaskGenerator:
|
||||
the image length. Later layers with more crops scale down this overlap.
|
||||
crop_n_points_downscale_factor (int): The number of points-per-side
|
||||
sampled in layer n is scaled down by crop_n_points_downscale_factor**n.
|
||||
point_grids (list(np.ndarray) or None): A list over explicit grids
|
||||
point_grids (list(np.ndarray), None): A list over explicit grids
|
||||
of points used for sampling, normalized to [0,1]. The nth grid in the
|
||||
list is used in the nth crop layer. Exclusive with points_per_side.
|
||||
min_mask_region_area (int): If >0, postprocessing will be applied
|
||||
@ -128,9 +128,8 @@ class SamAutomaticMaskGenerator:
|
||||
image (np.ndarray): The image to generate masks for, in HWC uint8 format.
|
||||
|
||||
Returns:
|
||||
list(dict(str, any)): A list over records for masks. Each record is
|
||||
a dict containing the following keys:
|
||||
segmentation (dict(str, any) or np.ndarray): The mask. If
|
||||
list(dict(str, any)): A list over records for masks. Each record is a dict containing the following keys:
|
||||
segmentation (dict(str, any), np.ndarray): The mask. If
|
||||
output_mode='binary_mask', is an array of shape HW. Otherwise,
|
||||
is a dictionary containing the RLE.
|
||||
bbox (list(float)): The box around the mask, in XYWH format.
|
||||
|
||||
@ -81,12 +81,12 @@ class PromptPredictor:
|
||||
Predict masks for the given input prompts, using the currently set image.
|
||||
|
||||
Arguments:
|
||||
point_coords (np.ndarray or None): A Nx2 array of point prompts to the
|
||||
point_coords (np.ndarray, None): A Nx2 array of point prompts to the
|
||||
model. Each point is in (X,Y) in pixels.
|
||||
point_labels (np.ndarray or None): A length N array of labels for the
|
||||
point_labels (np.ndarray, None): A length N array of labels for the
|
||||
point prompts. 1 indicates a foreground point and 0 indicates a
|
||||
background point.
|
||||
box (np.ndarray or None): A length 4 array given a box prompt to the
|
||||
box (np.ndarray, None): A length 4 array given a box prompt to the
|
||||
model, in XYXY format.
|
||||
mask_input (np.ndarray): A low resolution mask input to the model, typically
|
||||
coming from a previous prediction iteration. Has form 1xHxW, where
|
||||
@ -158,12 +158,12 @@ class PromptPredictor:
|
||||
transformed to the input frame using ResizeLongestSide.
|
||||
|
||||
Arguments:
|
||||
point_coords (torch.Tensor or None): A BxNx2 array of point prompts to the
|
||||
point_coords (torch.Tensor, None): A BxNx2 array of point prompts to the
|
||||
model. Each point is in (X,Y) in pixels.
|
||||
point_labels (torch.Tensor or None): A BxN array of labels for the
|
||||
point_labels (torch.Tensor, None): A BxN array of labels for the
|
||||
point prompts. 1 indicates a foreground point and 0 indicates a
|
||||
background point.
|
||||
boxes (np.ndarray or None): A Bx4 array given a box prompt to the
|
||||
boxes (np.ndarray, None): A Bx4 array given a box prompt to the
|
||||
model, in XYXY format.
|
||||
mask_input (np.ndarray): A low resolution mask input to the model, typically
|
||||
coming from a previous prediction iteration. Has form Bx1xHxW, where
|
||||
|
||||
@ -6,6 +6,18 @@ from ultralytics.yolo.utils.torch_utils import select_device
|
||||
|
||||
|
||||
def auto_annotate(data, det_model='yolov8x.pt', sam_model='sam_b.pt', device='', output_dir=None):
|
||||
"""
|
||||
Automatically annotates images using a YOLO object detection model and a SAM segmentation model.
|
||||
|
||||
Args:
|
||||
data (str): Path to a folder containing images to be annotated.
|
||||
det_model (str, optional): Pre-trained YOLO detection model. Defaults to 'yolov8x.pt'.
|
||||
sam_model (str, optional): Pre-trained SAM segmentation model. Defaults to 'sam_b.pt'.
|
||||
device (str, optional): Device to run the models on. Defaults to an empty string (CPU or GPU, if available).
|
||||
output_dir (str, None, optional): Directory to save the annotated results.
|
||||
Defaults to a 'labels' folder in the same directory as 'data'.
|
||||
|
||||
"""
|
||||
device = select_device(device)
|
||||
det_model = YOLO(det_model)
|
||||
sam_model = build_sam(sam_model)
|
||||
@ -33,7 +45,7 @@ def auto_annotate(data, det_model='yolov8x.pt', sam_model='sam_b.pt', device='',
|
||||
result.update(masks=masks.squeeze(1))
|
||||
segments = result.masks.xyn # noqa
|
||||
|
||||
with open(str(Path(output_dir) / Path(result.path).stem) + '.txt', 'w') as f:
|
||||
with open(f'{str(Path(output_dir) / Path(result.path).stem)}.txt', 'w') as f:
|
||||
for i in range(len(segments)):
|
||||
s = segments[i]
|
||||
if len(s) == 0:
|
||||
|
||||
@ -141,11 +141,8 @@ def load_inference_source(source=None, imgsz=640, vid_stride=1):
|
||||
|
||||
Args:
|
||||
source (str, Path, Tensor, PIL.Image, np.ndarray): The input source for inference.
|
||||
transforms (callable, optional): Custom transformations to be applied to the input source.
|
||||
imgsz (int, optional): The size of the image for inference. Default is 640.
|
||||
vid_stride (int, optional): The frame interval for video sources. Default is 1.
|
||||
stride (int, optional): The model stride. Default is 32.
|
||||
auto (bool, optional): Automatically apply pre-processing. Default is True.
|
||||
|
||||
Returns:
|
||||
dataset (Dataset): A dataset object for the specified input source.
|
||||
|
||||
@ -72,9 +72,6 @@ class LoadStreams:
|
||||
# Check for common shapes
|
||||
self.bs = self.__len__()
|
||||
|
||||
if not self.rect:
|
||||
LOGGER.warning('WARNING ⚠️ Stream shapes differ. For optimal performance supply similarly-shaped streams.')
|
||||
|
||||
def update(self, i, cap, stream):
|
||||
"""Read stream `i` frames in daemon thread."""
|
||||
n, f = 0, self.frames[i] # frame number, frame array
|
||||
|
||||
@ -116,6 +116,9 @@ class BasePredictor:
|
||||
"""
|
||||
if not isinstance(im, torch.Tensor):
|
||||
auto = all(x.shape == im[0].shape for x in im) and self.model.pt
|
||||
if not auto:
|
||||
LOGGER.warning(
|
||||
'WARNING ⚠️ Source shapes differ. For optimal performance supply similarly-shaped sources.')
|
||||
im = np.stack([LetterBox(self.imgsz, auto=auto, stride=self.model.stride)(image=x) for x in im])
|
||||
im = im[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW, (n, 3, h, w)
|
||||
im = np.ascontiguousarray(im) # contiguous
|
||||
@ -217,7 +220,8 @@ class BasePredictor:
|
||||
self.run_callbacks('on_predict_batch_start')
|
||||
self.batch = batch
|
||||
path, im0s, vid_cap, s = batch
|
||||
visualize = increment_path(self.save_dir / Path(path).stem, mkdir=True) if self.args.visualize else False
|
||||
visualize = increment_path(self.save_dir / Path(path[0]).stem,
|
||||
mkdir=True) if self.args.visualize and (not self.source_type.tensor) else False
|
||||
|
||||
# Preprocess
|
||||
with self.dt[0]:
|
||||
@ -298,7 +302,7 @@ class BasePredictor:
|
||||
cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux)
|
||||
cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
|
||||
cv2.imshow(str(p), im0)
|
||||
cv2.waitKey(500 if self.batch[4].startswith('image') else 1) # 1 millisecond
|
||||
cv2.waitKey(500 if self.batch[3].startswith('image') else 1) # 1 millisecond
|
||||
|
||||
def save_preds(self, vid_cap, idx, save_path):
|
||||
"""Save video predictions as mp4 at specified path."""
|
||||
|
||||
@ -205,7 +205,7 @@ class FocalLoss(nn.Module):
|
||||
return loss.mean()
|
||||
elif self.reduction == 'sum':
|
||||
return loss.sum()
|
||||
else: # 'none'
|
||||
else: # 'None'
|
||||
return loss
|
||||
|
||||
|
||||
|
||||
@ -148,7 +148,7 @@ def non_max_suppression(
|
||||
Perform non-maximum suppression (NMS) on a set of boxes, with support for masks and multiple labels per box.
|
||||
|
||||
Arguments:
|
||||
prediction (torch.Tensor): A tensor of shape (batch_size, num_boxes, num_classes + 4 + num_masks)
|
||||
prediction (torch.Tensor): A tensor of shape (batch_size, num_classes + 4 + num_masks, num_boxes)
|
||||
containing the predicted boxes, classes, and masks. The tensor should be in the format
|
||||
output by a model, such as YOLO.
|
||||
conf_thres (float): The confidence threshold below which boxes will be filtered out.
|
||||
|
||||
@ -469,3 +469,39 @@ def output_to_target(output, max_det=300):
|
||||
targets.append(torch.cat((j, cls, xyxy2xywh(box), conf), 1))
|
||||
targets = torch.cat(targets, 0).numpy()
|
||||
return targets[:, 0], targets[:, 1], targets[:, 2:]
|
||||
|
||||
|
||||
def feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp')):
|
||||
"""
|
||||
Visualize feature maps of a given model module during inference.
|
||||
|
||||
Args:
|
||||
x (torch.Tensor): Features to be visualized.
|
||||
module_type (str): Module type.
|
||||
stage (int): Module stage within the model.
|
||||
n (int, optional): Maximum number of feature maps to plot. Defaults to 32.
|
||||
save_dir (Path, optional): Directory to save results. Defaults to Path('runs/detect/exp').
|
||||
|
||||
Returns:
|
||||
None: This function does not return any value; it saves the visualization to the specified directory.
|
||||
"""
|
||||
for m in ['Detect', 'Pose', 'Segment']:
|
||||
if m in module_type:
|
||||
return
|
||||
batch, channels, height, width = x.shape # batch, channels, height, width
|
||||
if height > 1 and width > 1:
|
||||
f = save_dir / f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename
|
||||
|
||||
blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels
|
||||
n = min(n, channels) # number of plots
|
||||
fig, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols
|
||||
ax = ax.ravel()
|
||||
plt.subplots_adjust(wspace=0.05, hspace=0.05)
|
||||
for i in range(n):
|
||||
ax[i].imshow(blocks[i].squeeze()) # cmap='gray'
|
||||
ax[i].axis('off')
|
||||
|
||||
LOGGER.info(f'Saving {f}... ({n}/{channels})')
|
||||
plt.savefig(f, dpi=300, bbox_inches='tight')
|
||||
plt.close()
|
||||
np.save(str(f.with_suffix('.npy')), x[0].cpu().numpy()) # npy save
|
||||
|
||||
@ -27,7 +27,7 @@ class DetectionTrainer(BaseTrainer):
|
||||
Args:
|
||||
img_path (str): Path to the folder containing images.
|
||||
mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode.
|
||||
batch_size (int, optional): Size of batches, this is for `rect`. Defaults to None.
|
||||
batch (int, optional): Size of batches, this is for `rect`. Defaults to None.
|
||||
"""
|
||||
gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
|
||||
return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=mode == 'val', stride=gs)
|
||||
|
||||
@ -177,7 +177,7 @@ class DetectionValidator(BaseValidator):
|
||||
Args:
|
||||
img_path (str): Path to the folder containing images.
|
||||
mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode.
|
||||
batch_size (int, optional): Size of batches, this is for `rect`. Defaults to None.
|
||||
batch (int, optional): Size of batches, this is for `rect`. Defaults to None.
|
||||
"""
|
||||
gs = max(int(de_parallel(self.model).stride if self.model else 0), 32)
|
||||
return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, stride=gs)
|
||||
|
||||
Reference in New Issue
Block a user