feat: update code

configs/yolov6_tiny.py

@@ -0,0 +1,53 @@
+# YOLOv6t model
+model = dict(
+    type='YOLOv6t',
+    pretrained=None,
+    depth_multiple=0.25,  
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPAN',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='YOLOv6tHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='ciou'
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1       
+)
+
+data_aug = dict(
+    hsv_h=0.015,  
+    hsv_s=0.7, 
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)

configs/yolov6_tiny_finetune.py

@@ -0,0 +1,53 @@
+# YOLOv6t model
+model = dict(
+    type='YOLOv6t',
+    pretrained='./weights/yolov6t.pt',
+    depth_multiple=0.25,  
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPAN',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='ciou'
+    )
+)   
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05 
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)

configs/yolov6n.py

@@ -0,0 +1,53 @@
+# YOLOv6n model
+model = dict(
+    type='YOLOv6n',
+    pretrained=None,
+    depth_multiple=0.33,  
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPAN',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='ciou'
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1       
+)
+
+data_aug = dict(
+    hsv_h=0.015,  
+    hsv_s=0.7, 
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)

configs/yolov6n_finetune.py

@@ -0,0 +1,53 @@
+# YOLOv6n model
+model = dict(
+    type='YOLOv6n',
+    pretrained='./weights/yolov6n.pt',
+    depth_multiple=0.33,
+    width_multiple=0.25,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPAN',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='ciou'
+    )
+)   
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05 
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243
+)

configs/yolov6s.py

@@ -0,0 +1,53 @@
+# YOLOv6s model
+model = dict(
+    type='YOLOv6s',
+    pretrained=None,
+    depth_multiple=0.33,
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPAN',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='EffiDeHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='siou'
+    )
+)
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.01,
+    lrf=0.01,
+    momentum=0.937,
+    weight_decay=0.0005,
+    warmup_epochs=3.0,
+    warmup_momentum=0.8,
+    warmup_bias_lr=0.1       
+)
+
+data_aug = dict(
+    hsv_h=0.015,  
+    hsv_s=0.7, 
+    hsv_v=0.4,
+    degrees=0.0,
+    translate=0.1,
+    scale=0.5,
+    shear=0.0,
+    flipud=0.0,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.0,
+)

configs/yolov6s_finetune.py

@@ -0,0 +1,53 @@
+# YOLOv6s model
+model = dict(
+    type='YOLOv6s',
+    pretrained='./weights/yolov6s.pt',
+    depth_multiple=0.33,  
+    width_multiple=0.50,
+    backbone=dict(
+        type='EfficientRep',
+        num_repeats=[1, 6, 12, 18, 6],
+        out_channels=[64, 128, 256, 512, 1024],
+        ),
+    neck=dict(
+        type='RepPAN',
+        num_repeats=[12, 12, 12, 12],
+        out_channels=[256, 128, 128, 256, 256, 512],
+        ),
+    head=dict(
+        type='YOLOv6sHead',
+        in_channels=[128, 256, 512],
+        num_layers=3,
+        begin_indices=24,
+        anchors=1,
+        out_indices=[17, 20, 23],
+        strides=[8, 16, 32],
+        iou_type='siou'
+    )
+)   
+
+solver = dict(
+    optim='SGD',
+    lr_scheduler='Cosine',
+    lr0=0.0032,
+    lrf=0.12,
+    momentum=0.843,
+    weight_decay=0.00036,
+    warmup_epochs=2.0,
+    warmup_momentum=0.5,
+    warmup_bias_lr=0.05 
+)
+
+data_aug = dict(
+    hsv_h=0.0138,
+    hsv_s=0.664,
+    hsv_v=0.464,
+    degrees=0.373,
+    translate=0.245,
+    scale=0.898,
+    shear=0.602,
+    flipud=0.00856,
+    fliplr=0.5,
+    mosaic=1.0,
+    mixup=0.243,
+)

data/coco.yaml

@@ -0,0 +1,19 @@
+# COCO 2017 dataset http://cocodataset.org
+train: ../coco/images/train2017 # 118287 images
+val: ../coco/images/val2017  # 5000 images
+test: ../coco/images/test2017
+anno_path: ../coco/annotations/instances_val2017.json
+# number of classes
+nc: 80
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]
+

docs/Test_speed.md

@@ -0,0 +1,42 @@
+# Test speed
+
+This guidence explains how to reproduce speed results of YOLOv6. For fair comparision, the speed results do not contain the time cost of data pre-processing and NMS post-processing.
+
+## 0. Prepare model and 
+
+Download the models you want to test in model zoo.
+
+## 1. Prepare testing environment
+
+Refer to README, install packages corresponding to CUDA, CUDNN and TensorRT version. 
+
+Here, we use Torch1.8.0 inference on V100 and TensorRT 7.2 on T4.
+
+## 2. Reproduce speed
+
+#### 2.1 Torch Inference on V100
+
+To get inference speed without TensorRT on V100,  you can run the following command:
+
+```shell
+python tools/eval.py --data data/coco.yaml  --batch 32 --weights yolov6n.pt --task speed [--half]
+```
+
+- Speed results with batchsize = 1 are unstable in multiple runs, thus we do not provide the bs1 speed results.
+
+#### 2.2 TensorRT Inference on T4
+
+To  get inference speed with TensorRT in FP16 mode on T4, you can follow the steps below:
+
+First, export pytorch model as onnx format using the  following command:
+
+```shell
+python tools/export_onnx.py --weights yolov6n.pt --device 0 --batch [1 or 32] 
+```
+
+Second,  generate an inference  trt engine and test speed using `trtexec`:
+
+```
+trtexec --onnx=yolov6n.onnx --workspace=1024 --avgRuns=1000 --inputIOFormats=fp16:chw --outputIOFormats=fp16:chw
+```
+