YOLOv5 v5.0 Release (ultralytics#2762)

(cherry picked from commit f5b8f7d)
Lechtr · Apr 12, 2021 · 7edf5bf · 7edf5bf
1 parent 00c6948
commit 7edf5bf
Show file tree

Hide file tree

Showing 3 changed files with 66 additions and 75 deletions.
diff --git a/README.md b/README.md
@@ -6,36 +6,43 @@
 
 This repository represents Ultralytics open-source research into future object detection methods, and incorporates lessons learned and best practices evolved over thousands of hours of training and evolution on anonymized client datasets. **All code and models are under active development, and are subject to modification or deletion without notice.** Use at your own risk.
 
-<p align="center"><img width="800" src="https://user-images.githubusercontent.com/26833433/103594689-455e0e00-4eae-11eb-9cdf-7d753e2ceeeb.png"></p>
+<p align="center"><img width="800" src="https://user-images.githubusercontent.com/26833433/114313216-f0a5e100-9af5-11eb-8445-c682b60da2e3.png"></p>
+<details>
+  <summary>YOLOv5-P5 640 Figure (click to expand)</summary>
+
+<p align="center"><img width="800" src="https://user-images.githubusercontent.com/26833433/114313219-f1d70e00-9af5-11eb-9973-52b1f98d321a.png"></p>
+</details>
 <details>
   <summary>Figure Notes (click to expand)</summary>
 
   * GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS. 
   * EfficientDet data from [google/automl](https://github.com/google/automl) at batch size 8.
+  * **Reproduce** by `python test.py --task study --data coco.yaml --iou 0.7 --weights yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`
 </details>
 
+- **April 11, 2021**: [v5.0 release](https://github.com/ultralytics/yolov5/releases/tag/v5.0): YOLOv5-P6 1280 models, [AWS](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart), [Supervise.ly](https://github.com/ultralytics/yolov5/issues/2518) and [YouTube](https://github.com/ultralytics/yolov5/pull/2752) integrations.
 - **January 5, 2021**: [v4.0 release](https://github.com/ultralytics/yolov5/releases/tag/v4.0): nn.SiLU() activations, [Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_readme) logging, [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/) integration.
 - **August 13, 2020**: [v3.0 release](https://github.com/ultralytics/yolov5/releases/tag/v3.0): nn.Hardswish() activations, data autodownload, native AMP.
 - **July 23, 2020**: [v2.0 release](https://github.com/ultralytics/yolov5/releases/tag/v2.0): improved model definition, training and mAP.
-- **June 22, 2020**: [PANet](https://arxiv.org/abs/1803.01534) updates: new heads, reduced parameters, improved speed and mAP [364fcfd](https://github.com/ultralytics/yolov5/commit/364fcfd7dba53f46edd4f04c037a039c0a287972).
-- **June 19, 2020**: [FP16](https://pytorch.org/docs/stable/nn.html#torch.nn.Module.half) as new default for smaller checkpoints and faster inference [d4c6674](https://github.com/ultralytics/yolov5/commit/d4c6674c98e19df4c40e33a777610a18d1961145).
 
 
 ## Pretrained Checkpoints
 
-| Model | size | AP<sup>val</sup> | AP<sup>test</sup> | AP<sub>50</sub> | Speed<sub>V100</sub> | FPS<sub>V100</sub> || params | GFLOPS |
-|---------- |------ |------ |------ |------ | -------- | ------| ------ |------  |  :------: |
-| [YOLOv5s](https://github.com/ultralytics/yolov5/releases)    |640 |36.8     |36.8     |55.6     |**2.2ms** |**455** ||7.3M   |17.0
-| [YOLOv5m](https://github.com/ultralytics/yolov5/releases)    |640 |44.5     |44.5     |63.1     |2.9ms     |345     ||21.4M  |51.3
-| [YOLOv5l](https://github.com/ultralytics/yolov5/releases)    |640 |48.1     |48.1     |66.4     |3.8ms     |264     ||47.0M  |115.4
-| [YOLOv5x](https://github.com/ultralytics/yolov5/releases)    |640 |**50.1** |**50.1** |**68.7** |6.0ms     |167     ||87.7M  |218.8
-| | | | | | | || |
-| [YOLOv5x](https://github.com/ultralytics/yolov5/releases) + TTA |832 |**51.9** |**51.9** |**69.6** |24.9ms |40      ||87.7M  |1005.3
-
-<!--- 
-| [YOLOv5l6](https://github.com/ultralytics/yolov5/releases)   |640 |49.0     |49.0     |67.4     |4.1ms     |244     ||77.2M  |117.7
-| [YOLOv5l6](https://github.com/ultralytics/yolov5/releases)   |1280 |53.0     |53.0     |70.8     |12.3ms     |81     ||77.2M  |117.7
---->
+[assets]: https://github.com/ultralytics/yolov5/releases
+
+Model |size<br><sup>(pixels) |mAP<sup>val<br>0.5:0.95 |mAP<sup>test<br>0.5:0.95 |mAP<sup>val<br>0.5 |Speed<br><sup>V100 (ms) | |params<br><sup>(M) |FLOPS<br><sup>640 (B)
+---   |---  |---        |---         |---             |---                |---|---              |---
+[YOLOv5s][assets]    |640  |36.7     |36.7     |55.4     |**2.0** | |7.3   |17.0
+[YOLOv5m][assets]    |640  |44.5     |44.5     |63.3     |2.7     | |21.4  |51.3
+[YOLOv5l][assets]    |640  |48.2     |48.2     |66.9     |3.8     | |47.0  |115.4
+[YOLOv5x][assets]    |640  |**50.4** |**50.4** |**68.8** |6.1     | |87.7  |218.8
+| | | | | | || |
+[YOLOv5s6][assets]   |1280 |43.3     |43.3     |61.9     |**4.3** | |12.7  |17.4
+[YOLOv5m6][assets]   |1280 |50.5     |50.5     |68.7     |8.4     | |35.9  |52.4
+[YOLOv5l6][assets]   |1280 |53.4     |53.4     |71.1     |12.3    | |77.2  |117.7
+[YOLOv5x6][assets]   |1280 |**54.4** |**54.4** |**72.0** |22.4    | |141.8 |222.9
+| | | | | | || |
+[YOLOv5x6][assets] TTA |1280 |**55.0** |**55.0** |**72.0** |70.8 | |-  |-
 
 <details>
   <summary>Table Notes (click to expand)</summary>
@@ -44,7 +51,7 @@ This repository represents Ultralytics open-source research into future object d
   * AP values are for single-model single-scale unless otherwise noted. **Reproduce mAP** by `python test.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65`  
   * Speed<sub>GPU</sub> averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) V100 instance, and includes FP16 inference, postprocessing and NMS. **Reproduce speed** by `python test.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45`  
   * All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation). 
-  * Test Time Augmentation ([TTA](https://github.com/ultralytics/yolov5/issues/303)) includes reflection and scale augmentation. **Reproduce TTA** by `python test.py --data coco.yaml --img 832 --iou 0.65 --augment`
+  * Test Time Augmentation ([TTA](https://github.com/ultralytics/yolov5/issues/303)) includes reflection and scale augmentation. **Reproduce TTA** by `python test.py --data coco.yaml --img 1536 --iou 0.7 --augment`
 </details>
 
 
@@ -85,7 +92,7 @@ YOLOv5 may be run in any of the following up-to-date verified environments (with
 
 ## Inference
 
-detect.py runs inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases) and saving results to `runs/detect`.
+`detect.py` runs inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases) and saving results to `runs/detect`.
 ```bash
 $ python detect.py --source 0  # webcam
                             file.jpg  # image 

diff --git a/hubconf.py b/hubconf.py
@@ -55,84 +55,68 @@ def create(name, pretrained, channels, classes, autoshape):
         raise Exception(s) from e
 
 
-def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True):
-    """YOLOv5-small model from https://github.com/ultralytics/yolov5
+def custom(path_or_model='path/to/model.pt', autoshape=True):
+    """YOLOv5-custom model https://github.com/ultralytics/yolov5
 
-    Arguments:
-        pretrained (bool): load pretrained weights into the model, default=False
-        channels (int): number of input channels, default=3
-        classes (int): number of model classes, default=80
+    Arguments (3 options):
+        path_or_model (str): 'path/to/model.pt'
+        path_or_model (dict): torch.load('path/to/model.pt')
+        path_or_model (nn.Module): torch.load('path/to/model.pt')['model']
 
     Returns:
         pytorch model
     """
-    return create('yolov5s', pretrained, channels, classes, autoshape)
+    model = torch.load(path_or_model) if isinstance(path_or_model, str) else path_or_model  # load checkpoint
+    if isinstance(model, dict):
+        model = model['ema' if model.get('ema') else 'model']  # load model
 
+    hub_model = Model(model.yaml).to(next(model.parameters()).device)  # create
+    hub_model.load_state_dict(model.float().state_dict())  # load state_dict
+    hub_model.names = model.names  # class names
+    if autoshape:
+        hub_model = hub_model.autoshape()  # for file/URI/PIL/cv2/np inputs and NMS
+    device = select_device('0' if torch.cuda.is_available() else 'cpu')  # default to GPU if available
+    return hub_model.to(device)
 
-def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True):
-    """YOLOv5-medium model from https://github.com/ultralytics/yolov5
 
-    Arguments:
-        pretrained (bool): load pretrained weights into the model, default=False
-        channels (int): number of input channels, default=3
-        classes (int): number of model classes, default=80
+def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-small model https://github.com/ultralytics/yolov5
+    return create('yolov5s', pretrained, channels, classes, autoshape)
 
-    Returns:
-        pytorch model
-    """
+
+def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-medium model https://github.com/ultralytics/yolov5
     return create('yolov5m', pretrained, channels, classes, autoshape)
 
 
 def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True):
-    """YOLOv5-large model from https://github.com/ultralytics/yolov5
-
-    Arguments:
-        pretrained (bool): load pretrained weights into the model, default=False
-        channels (int): number of input channels, default=3
-        classes (int): number of model classes, default=80
-
-    Returns:
-        pytorch model
-    """
+    # YOLOv5-large model https://github.com/ultralytics/yolov5
     return create('yolov5l', pretrained, channels, classes, autoshape)
 
 
 def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True):
-    """YOLOv5-xlarge model from https://github.com/ultralytics/yolov5
+    # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
+    return create('yolov5x', pretrained, channels, classes, autoshape)
 
-    Arguments:
-        pretrained (bool): load pretrained weights into the model, default=False
-        channels (int): number of input channels, default=3
-        classes (int): number of model classes, default=80
 
-    Returns:
-        pytorch model
-    """
-    return create('yolov5x', pretrained, channels, classes, autoshape)
+def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-small model https://github.com/ultralytics/yolov5
+    return create('yolov5s6', pretrained, channels, classes, autoshape)
 
 
-def custom(path_or_model='path/to/model.pt', autoshape=True):
-    """YOLOv5-custom model from https://github.com/ultralytics/yolov5
+def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-medium model https://github.com/ultralytics/yolov5
+    return create('yolov5m6', pretrained, channels, classes, autoshape)
 
-    Arguments (3 options):
-        path_or_model (str): 'path/to/model.pt'
-        path_or_model (dict): torch.load('path/to/model.pt')
-        path_or_model (nn.Module): torch.load('path/to/model.pt')['model']
 
-    Returns:
-        pytorch model
-    """
-    model = torch.load(path_or_model) if isinstance(path_or_model, str) else path_or_model  # load checkpoint
-    if isinstance(model, dict):
-        model = model['ema' if model.get('ema') else 'model']  # load model
+def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-large model https://github.com/ultralytics/yolov5
+    return create('yolov5l6', pretrained, channels, classes, autoshape)
 
-    hub_model = Model(model.yaml).to(next(model.parameters()).device)  # create
-    hub_model.load_state_dict(model.float().state_dict())  # load state_dict
-    hub_model.names = model.names  # class names
-    if autoshape:
-        hub_model = hub_model.autoshape()  # for file/URI/PIL/cv2/np inputs and NMS
-    device = select_device('0' if torch.cuda.is_available() else 'cpu')  # default to GPU if available
-    return hub_model.to(device)
+
+def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
+    return create('yolov5x6', pretrained, channels, classes, autoshape)
 
 
 if __name__ == '__main__':

diff --git a/utils/plots.py b/utils/plots.py
@@ -243,7 +243,7 @@ def plot_study_txt(path='', x=None):  # from utils.plots import *; plot_study_tx
     # ax = ax.ravel()
 
     fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True)
-    # for f in [Path(path) / f'study_coco_{x}.txt' for x in ['yolov5s', 'yolov5m', 'yolov5l', 'yolov5x']]:
+    # for f in [Path(path) / f'study_coco_{x}.txt' for x in ['yolov5s6', 'yolov5m6', 'yolov5l6', 'yolov5x6']]:
     for f in sorted(Path(path).glob('study*.txt')):
         y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T
         x = np.arange(y.shape[1]) if x is None else np.array(x)
@@ -253,15 +253,15 @@ def plot_study_txt(path='', x=None):  # from utils.plots import *; plot_study_tx
         #     ax[i].set_title(s[i])
 
         j = y[3].argmax() + 1
-        ax2.plot(y[6, :j], y[3, :j] * 1E2, '.-', linewidth=2, markersize=8,
+        ax2.plot(y[6, 1:j], y[3, 1:j] * 1E2, '.-', linewidth=2, markersize=8,
                  label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO'))
 
     ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5],
              'k.-', linewidth=2, markersize=8, alpha=.25, label='EfficientDet')
 
     ax2.grid(alpha=0.2)
     ax2.set_yticks(np.arange(20, 60, 5))
-    ax2.set_xlim(0, 30)
+    ax2.set_xlim(0, 57)
     ax2.set_ylim(30, 55)
     ax2.set_xlabel('GPU Speed (ms/img)')
     ax2.set_ylabel('COCO AP val')