xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.71 updates and fixes (#1907)

Browse Source 
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: Pavel Bugneac <50273042+pavelbugneac@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
2023-04-08 21:10:36 +02:00
committed by GitHub
parent c38b17a0d8
commit 4e997013bc
19 changed files with 103 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/modes/benchmark.md
View File

@ -23,7 +23,7 @@ full list of export arguments.
```python
from ultralytics.yolo.utils.benchmarks import benchmark
# Benchmark
# Benchmark on GPU
benchmark(model='yolov8n.pt', imgsz=640, half=False, device=0)
```
=== "CLI"
@ -63,3 +63,5 @@ Benchmarks will attempt to run automatically on all possible export formats belo
| [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/` | ✅ |
See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.

1
docs/modes/train.md
View File

@ -90,7 +90,6 @@ task.
| `dfl` | `1.5` | dfl loss gain |
| `pose` | `12.0` | pose loss gain (pose-only) |
| `kobj` | `2.0` | keypoint obj loss gain (pose-only) |
| `fl_gamma` | `0.0` | focal loss gamma (efficientDet default gamma=1.5) |
| `label_smoothing` | `0.0` | label smoothing (fraction) |
| `nbs` | `64` | nominal batch size |
| `overlap_mask` | `True` | masks should overlap during training (segment train only) |

1
docs/usage/cfg.md
View File

@ -112,7 +112,6 @@ The training settings for YOLO models encompass various hyperparameters and conf
| `dfl` | `1.5` | dfl loss gain |
| `pose` | `12.0` | pose loss gain (pose-only) |
| `kobj` | `2.0` | keypoint obj loss gain (pose-only) |
| `fl_gamma` | `0.0` | focal loss gamma (efficientDet default gamma=1.5) |
| `label_smoothing` | `0.0` | label smoothing (fraction) |
| `nbs` | `64` | nominal batch size |
| `overlap_mask` | `True` | masks should overlap during training (segment train only) |