HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Add multi_scale training argument to docs (#18531)

Browse source 
Signed-off-by: Mohammed Yasin <32206511+Y-T-G@users.noreply.github.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Mohammed Yasin 2025-01-05 23:34:59 +08:00 • committed by GitHub
parent e336d87a68
commit bf4874ce40
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
docs/en/macros/train-args.md
View file

@ -22,6 +22,7 @@
| `single_cls` | `bool` | `False` | Treats all classes in multi-class datasets as a single class during training. Useful for binary classification tasks or when focusing on object presence rather than classification. | | `single_cls` | `bool` | `False` | Treats all classes in multi-class datasets as a single class during training. Useful for binary classification tasks or when focusing on object presence rather than classification. |
| `classes` | `list[int]` | `None` | Specifies a list of class IDs to train on. Useful for filtering out and focusing only on certain classes during training. | | `classes` | `list[int]` | `None` | Specifies a list of class IDs to train on. Useful for filtering out and focusing only on certain classes during training. |
| `rect` | `bool` | `False` | Enables rectangular training, optimizing batch composition for minimal padding. Can improve efficiency and speed but may affect model accuracy. | | `rect` | `bool` | `False` | Enables rectangular training, optimizing batch composition for minimal padding. Can improve efficiency and speed but may affect model accuracy. |
| `multi_scale` | `bool` | `False` | Enables multi-scale training by increasing/decreasing `imgsz` by upto a factor of `0.5` during training. Trains the model to be more accurate with multiple `imgsz` during inference. |
| `cos_lr` | `bool` | `False` | Utilizes a cosine [learning rate](https://www.ultralytics.com/glossary/learning-rate) scheduler, adjusting the learning rate following a cosine curve over epochs. Helps in managing learning rate for better convergence. | | `cos_lr` | `bool` | `False` | Utilizes a cosine [learning rate](https://www.ultralytics.com/glossary/learning-rate) scheduler, adjusting the learning rate following a cosine curve over epochs. Helps in managing learning rate for better convergence. |
| `close_mosaic` | `int` | `10` | Disables mosaic [data augmentation](https://www.ultralytics.com/glossary/data-augmentation) in the last N epochs to stabilize training before completion. Setting to 0 disables this feature. | | `close_mosaic` | `int` | `10` | Disables mosaic [data augmentation](https://www.ultralytics.com/glossary/data-augmentation) in the last N epochs to stabilize training before completion. Setting to 0 disables this feature. |
| `resume` | `bool` | `False` | Resumes training from the last saved checkpoint. Automatically loads model weights, optimizer state, and epoch count, continuing training seamlessly. | | `resume` | `bool` | `False` | Resumes training from the last saved checkpoint. Automatically loads model weights, optimizer state, and epoch count, continuing training seamlessly. |
@ -42,7 +43,7 @@
| `pose` | `float` | `12.0` | Weight of the pose loss in models trained for pose estimation, influencing the emphasis on accurately predicting pose keypoints. | | `pose` | `float` | `12.0` | Weight of the pose loss in models trained for pose estimation, influencing the emphasis on accurately predicting pose keypoints. |
| `kobj` | `float` | `2.0` | Weight of the keypoint objectness loss in pose estimation models, balancing detection confidence with pose accuracy. | | `kobj` | `float` | `2.0` | Weight of the keypoint objectness loss in pose estimation models, balancing detection confidence with pose accuracy. |
| `nbs` | `int` | `64` | Nominal batch size for normalization of loss. | | `nbs` | `int` | `64` | Nominal batch size for normalization of loss. |
| `overlap_mask` | `bool` | `True` | Determines whether object masks should be merged into a single mask for training, or kept separate for each object. In case of overlap, the smaller mask is overlayed on top of the larger mask during merge. | | `overlap_mask` | `bool` | `True` | Determines whether object masks should be merged into a single mask for training, or kept separate for each object. In case of overlap, the smaller mask is overlaid on top of the larger mask during merge. |
| `mask_ratio` | `int` | `4` | Downsample ratio for segmentation masks, affecting the resolution of masks used during training. | | `mask_ratio` | `int` | `4` | Downsample ratio for segmentation masks, affecting the resolution of masks used during training. |
| `dropout` | `float` | `0.0` | Dropout rate for regularization in classification tasks, preventing overfitting by randomly omitting units during training. | | `dropout` | `float` | `0.0` | Dropout rate for regularization in classification tasks, preventing overfitting by randomly omitting units during training. |
| `val` | `bool` | `True` | Enables validation during training, allowing for periodic evaluation of model performance on a separate dataset. | | `val` | `bool` | `True` | Enables validation during training, allowing for periodic evaluation of model performance on a separate dataset. |