2.打开voc_label.py，并修改代码 classes=[""]填入自己的类名，比如你的是训练猫和狗，那么就是classes=["dog","cat"]，然后运行该程序。此时会在labels文件下生成对应每个图像的txt文件，形式如下：【最前面的0是类对应的索引，我这里只有一个类，后面的四个数为box的参数，均归一化以后的，分别表示box的左上和右下坐标，等训练的时候会处理成center_x，center_y，w, h】

0 0.4723557692307693 0.5408653846153847 0.34375 0.8990384615384616
0 0.8834134615384616 0.5793269230769231 0.21875 0.8221153846153847

3.在data文件夹下新建一个mydata.yaml文件。内容如下【你也可以把coco.yaml复制过来】。

你只需要修改nc以及names即可，nc是类的数量，names是类的名字。

train: ./dataset/train.txt
val: ./dataset/val.txt
test: ./dataset/test.txt

# number of classes
nc: 1

# class names
names: ['target']

4.终端输入参数，开始训练。

以yolov5s为例：

python train.py --weights yolov5s.pt --cfg models/yolov5s.yaml --data data/mydata.yaml

from n params module arguments
0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2]
2 -1 1 18816 models.common.C3 [64, 64, 1]
3 -1 1 73984 models.common.Conv [64, 128, 3, 2]
4 -1 2 115712 models.common.C3 [128, 128, 2]
5 -1 1 295424 models.common.Conv [128, 256, 3, 2]
6 -1 3 625152 models.common.C3 [256, 256, 3]
7 -1 1 1180672 models.common.Conv [256, 512, 3, 2]
8 -1 1 1182720 models.common.C3 [512, 512, 1]
9 -1 1 656896 models.common.SPPF [512, 512, 5]
10 -1 1 131584 models.common.Conv [512, 256, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 models.common.Concat [1]
13 -1 1 361984 models.common.C3 [512, 256, 1, False]
20 -1 1 296448 models.common.C3 [256, 256, 1, False]
21 -1 1 590336 models.common.Conv [256, 256, 3, 2]
22 [-1, 10] 1 0 models.common.Concat [1]
23 -1 1 1182720 models.common.C3 [512, 512, 1, False]
24 [17, 20, 23] 1 16182 models.yolo.Detect [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Model Summary: 270 layers, 7022326 parameters, 7022326 gradients, 15.8 GFLOPs

Starting training for 300 epochs...

Epoch gpu_mem box obj cls labels img_size
0/299 0.589G 0.0779 0.03841 0 4 640: 6%|████▋ | 23/359 [00:23<04:15, 1.31it/s]

看到以上信息就开始训练了。

2.对任意卷积层进行剪枝

在利用剪枝功能前，需要安装一下剪枝的库。需要安装0.2.7版本，0.2.8有粉丝说有问题。剪枝时的一些log信息会自动保存在logs文件夹下，每个log的大小我设置的为1MB，如果有其他需要大家可以更改。

pip install torch_pruning==0.2.7

YOLOv5与我之前写过的剪枝不同，v5在训练保存后的权重本身就保存了完整的model，即用的是torch.save(model,...)，而不是torch.save(model.state_dict(),...)，因此不需要单独在对网络结构保存一次。

模型剪枝代码在tools/prunmodel.py。你只需要找到这部分代码进行修改：我这里是以剪枝整个backbone的卷积层为例，如果你要剪枝的是其他层按需修改.included_layers内就是你要剪枝的层。

    """
    这里写要剪枝的层
    """
    included_layers = []
    for layer in model.model[:10]:
        if type(layer) is Conv:
            included_layers.append(layer.conv)
        elif type(layer) is C3:
            included_layers.append(layer.cv1.conv)
            included_layers.append(layer.cv2.conv)
            included_layers.append(layer.cv3.conv)
        elif type(layer) is SPPF:
            included_layers.append(layer.cv1.conv)
            included_layers.append(layer.cv2.conv)

接下来在找到下面这行代码，amount为剪枝率，同样也是按需修改。【这里需要明白的一点，这里的剪枝率仅是对你要剪枝的所有层剪枝这么多，并不是把网络从头到尾全部剪，有些粉丝说我选了一层，剪枝率50%，怎么模型还那么大，没啥变化，这个就是他搞混了，他以为是对整个网络剪枝50%】。

pruning_plan = DG.get_pruning_plan(m, tp.prune_conv, idxs=strategy(m.weight, amount=0.8))

接下来调用剪枝函数，传入参数为自己的训练好的权重文件路径。

layer_pruning('../runs/train/exp/weights/best.pt')

见到如下形式，就说明剪枝成功了，剪枝以后的权重会保存在model_data下，名字为layer_pruning.pt。

这里需要说明一下，保存的权重文件中不仅包含了网络结构和权值内容，还有优化器的权值，如果仅仅保存网络结构和权值也是可以的，这样pt会更小一点，我这里默认都保存是为了和官方pt格式一致。

-------------
[ <DEP: prune_conv => prune_conv on model.9.cv2.conv (Conv2d(208, 512, kernel_size=(1, 1), stride=(1, 1), bias=False))>, Index=[0, 1, 2, 3, 7, 8, 10, 11, 12, 13, 16, 17, 18, 19, 21, 22, 23, 25, 27, 28, 29, 30, 31, 32, 33, 34, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 56, 57, 58, 59, 60, 61, 62, 63, 65, 67, 69, 70, 71, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 92, 95, 96, 97, 99, 100, 102, 103, 104, 105, 106, 107, 109, 110, 111, 113, 114, 115, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 132, 133, 135, 137, 139, 142, 143, 144, 146, 148, 150, 152, 153, 154, 155, 156, 157, 158, 159, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 173, 174, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 215, 216, 217, 219, 220, 221, 222, 223, 224, 225, 226, 228, 229, 230, 232, 233, 234, 235, 236, 237, 239, 240, 241, 242, 243, 246, 247, 248, 249, 251, 252, 253, 254, 257, 258, 259, 260, 263, 264, 265, 266, 267, 268, 270, 271, 272, 273, 274, 275, 276, 277, 278, 280, 281, 282, 283, 284, 285, 286, 287, 288, 292, 293, 294, 295, 296, 297, 299, 301, 302, 303, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 317, 318, 321, 322, 323, 324, 325, 326, 327, 329, 330, 331, 332, 334, 335, 338, 339, 341, 342, 343, 344, 346, 347, 349, 351, 353, 354, 355, 356, 357, 358, 359, 361, 362, 363, 364, 365, 366, 368, 369, 370, 372, 373, 374, 375, 378, 379, 381, 382, 383, 385, 386, 387, 388, 389, 390, 391, 392, 393, 395, 396, 397, 398, 399, 401, 402, 403, 404, 405, 407, 408, 411, 413, 414, 415, 416, 418, 419, 420, 421, 422, 423, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 440, 441, 442, 443, 444, 445, 446, 448, 449, 451, 452, 453, 454, 455, 456, 457, 458, 459, 461, 463, 465, 466, 468, 470, 472, 473, 474, 475, 476, 477, 478, 479, 480, 482, 483, 484, 485, 486, 487, 488, 490, 491, 492, 493, 494, 495, 496, 497, 498, 499, 500, 502, 503, 505, 506, 507, 510, 511], NumPruned=85072]
[ <DEP: prune_conv => prune_batchnorm on model.9.cv2.bn (BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True))>, Index=[0, 1, 2, 3, 7, 8, 10, 11, 12, 13, 16, 17, 18, 19, 21, 22, 23, 25, 27, 28, 29, 30, 31, 32, 33, 34, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 56, 57, 58, 59, 60, 61, 62, 63, 65, 67, 69, 70, 71, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 92, 95, 96, 97, 99, 100, 102, 103, 104, 105, 106, 107, 109, 110, 111, 113, 114, 115, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 132, 133, 135, 137, 139, 142, 143, 144, 146, 148, 150, 152, 153, 154, 155, 156, 157, 158, 159, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 173, 174, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 215, 216, 217, 219, 220, 221, 222, 223, 224, 225, 226, 228, 229, 230, 232, 233, 234, 235, 236, 237, 239, 240, 241, 242, 243, 246, 247, 248, 249, 251, 252, 253, 254, 257, 258, 259, 260, 263, 264, 265, 266, 267, 268, 270, 271, 272, 273, 274, 275, 276, 277, 278, 280, 281, 282, 283, 284, 285, 286, 287, 288, 292, 293, 294, 295, 296, 297, 299, 301, 302, 303, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 317, 318, 321, 322, 323, 324, 325, 326, 327, 329, 330, 331, 332, 334, 335, 338, 339, 341, 342, 343, 344, 346, 347, 349, 351, 353, 354, 355, 356, 357, 358, 359, 361, 362, 363, 364, 365, 366, 368, 369, 370, 372, 373, 374, 375, 378, 379, 381, 382, 383, 385, 386, 387, 388, 389, 390, 391, 392, 393, 395, 396, 397, 398, 399, 401, 402, 403, 404, 405, 407, 408, 411, 413, 414, 415, 416, 418, 419, 420, 421, 422, 423, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 440, 441, 442, 443, 444, 445, 446, 448, 449, 451, 452, 453, 454, 455, 456, 457, 458, 459, 461, 463, 465, 466, 468, 470, 472, 473, 474, 475, 476, 477, 478, 479, 480, 482, 483, 484, 485, 486, 487, 488, 490, 491, 492, 493, 494, 495, 496, 497, 498, 499, 500, 502, 503, 505, 506, 507, 510, 511], NumPruned=818]
[ <DEP: prune_batchnorm => _prune_elementwise_op on _ElementWiseOp()>, Index=[0, 1, 2, 3, 7, 8, 10, 11, 12, 13, 16, 17, 18, 19, 21, 22, 23, 25, 27, 28, 29, 30, 31, 32, 33, 34, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 56, 57, 58, 59, 60, 61, 62, 63, 65, 67, 69, 70, 71, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 92, 95, 96, 97, 99, 100, 102, 103, 104, 105, 106, 107, 109, 110, 111, 113, 114, 115, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 132, 133, 135, 137, 139, 142, 143, 144, 146, 148, 150, 152, 153, 154, 155, 156, 157, 158, 159, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 173, 174, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 215, 216, 217, 219, 220, 221, 222, 223, 224, 225, 226, 228, 229, 230, 232, 233, 234, 235, 236, 237, 239, 240, 241, 242, 243, 246, 247, 248, 249, 251, 252, 253, 254, 257, 258, 259, 260, 263, 264, 265, 266, 267, 268, 270, 271, 272, 273, 274, 275, 276, 277, 278, 280, 281, 282, 283, 284, 285, 286, 287, 288, 292, 293, 294, 295, 296, 297, 299, 301, 302, 303, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 317, 318, 321, 322, 323, 324, 325, 326, 327, 329, 330, 331, 332, 334, 335, 338, 339, 341, 342, 343, 344, 346, 347, 349, 351, 353, 354, 355, 356, 357, 358, 359, 361, 362, 363, 364, 365, 366, 368, 369, 370, 372, 373, 374, 375, 378, 379, 381, 382, 383, 385, 386, 387, 388, 389, 390, 391, 392, 393, 395, 396, 397, 398, 399, 401, 402, 403, 404, 405, 407, 408, 411, 413, 414, 415, 416, 418, 419, 420, 421, 422, 423, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 440, 441, 442, 443, 444, 445, 446, 448, 449, 451, 452, 453, 454, 455, 456, 457, 458, 459, 461, 463, 465, 466, 468, 470, 472, 473, 474, 475, 476, 477, 478, 479, 480, 482, 483, 484, 485, 486, 487, 488, 490, 491, 492, 493, 494, 495, 496, 497, 498, 499, 500, 502, 503, 505, 506, 507, 510, 511], NumPruned=0]
[ <DEP: _prune_elementwise_op => _prune_elementwise_op on _ElementWiseOp()>, Index=[0, 1, 2, 3, 7, 8, 10, 11, 12, 13, 16, 17, 18, 19, 21, 22, 23, 25, 27, 28, 29, 30, 31, 32, 33, 34, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 56, 57, 58, 59, 60, 61, 62, 63, 65, 67, 69, 70, 71, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 92, 95, 96, 97, 99, 100, 102, 103, 104, 105, 106, 107, 109, 110, 111, 113, 114, 115, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 132, 133, 135, 137, 139, 142, 143, 144, 146, 148, 150, 152, 153, 154, 155, 156, 157, 158, 159, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 173, 174, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 215, 216, 217, 219, 220, 221, 222, 223, 224, 225, 226, 228, 229, 230, 232, 233, 234, 235, 236, 237, 239, 240, 241, 242, 243, 246, 247, 248, 249, 251, 252, 253, 254, 257, 258, 259, 260, 263, 264, 265, 266, 267, 268, 270, 271, 272, 273, 274, 275, 276, 277, 278, 280, 281, 282, 283, 284, 285, 286, 287, 288, 292, 293, 294, 295, 296, 297, 299, 301, 302, 303, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 317, 318, 321, 322, 323, 324, 325, 326, 327, 329, 330, 331, 332, 334, 335, 338, 339, 341, 342, 343, 344, 346, 347, 349, 351, 353, 354, 355, 356, 357, 358, 359, 361, 362, 363, 364, 365, 366, 368, 369, 370, 372, 373, 374, 375, 378, 379, 381, 382, 383, 385, 386, 387, 388, 389, 390, 391, 392, 393, 395, 396, 397, 398, 399, 401, 402, 403, 404, 405, 407, 408, 411, 413, 414, 415, 416, 418, 419, 420, 421, 422, 423, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 440, 441, 442, 443, 444, 445, 446, 448, 449, 451, 452, 453, 454, 455, 456, 457, 458, 459, 461, 463, 465, 466, 468, 470, 472, 473, 474, 475, 476, 477, 478, 479, 480, 482, 483, 484, 485, 486, 487, 488, 490, 491, 492, 493, 494, 495, 496, 497, 498, 499, 500, 502, 503, 505, 506, 507, 510, 511], NumPruned=0]
[ <DEP: _prune_elementwise_op => prune_related_conv on model.10.conv (Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False))>, Index=[0, 1, 2, 3, 7, 8, 10, 11, 12, 13, 16, 17, 18, 19, 21, 22, 23, 25, 27, 28, 29, 30, 31, 32, 33, 34, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 56, 57, 58, 59, 60, 61, 62, 63, 65, 67, 69, 70, 71, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 89, 90, 91, 92, 95, 96, 97, 99, 100, 102, 103, 104, 105, 106, 107, 109, 110, 111, 113, 114, 115, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 132, 133, 135, 137, 139, 142, 143, 144, 146, 148, 150, 152, 153, 154, 155, 156, 157, 158, 159, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 173, 174, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 215, 216, 217, 219, 220, 221, 222, 223, 224, 225, 226, 228, 229, 230, 232, 233, 234, 235, 236, 237, 239, 240, 241, 242, 243, 246, 247, 248, 249, 251, 252, 253, 254, 257, 258, 259, 260, 263, 264, 265, 266, 267, 268, 270, 271, 272, 273, 274, 275, 276, 277, 278, 280, 281, 282, 283, 284, 285, 286, 287, 288, 292, 293, 294, 295, 296, 297, 299, 301, 302, 303, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 317, 318, 321, 322, 323, 324, 325, 326, 327, 329, 330, 331, 332, 334, 335, 338, 339, 341, 342, 343, 344, 346, 347, 349, 351, 353, 354, 355, 356, 357, 358, 359, 361, 362, 363, 364, 365, 366, 368, 369, 370, 372, 373, 374, 375, 378, 379, 381, 382, 383, 385, 386, 387, 388, 389, 390, 391, 392, 393, 395, 396, 397, 398, 399, 401, 402, 403, 404, 405, 407, 408, 411, 413, 414, 415, 416, 418, 419, 420, 421, 422, 423, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 440, 441, 442, 443, 444, 445, 446, 448, 449, 451, 452, 453, 454, 455, 456, 457, 458, 459, 461, 463, 465, 466, 468, 470, 472, 473, 474, 475, 476, 477, 478, 479, 480, 482, 483, 484, 485, 486, 487, 488, 490, 491, 492, 493, 494, 495, 496, 497, 498, 499, 500, 502, 503, 505, 506, 507, 510, 511], NumPruned=104704]
190594 parameters will be pruned
-------------

2022-09-29 12:30:50.396 | INFO     | __main__:layer_pruning:75 -   Params: 7022326 => 3056461

2022-09-29 12:30:50.691 | INFO     | __main__:layer_pruning:89 - 剪枝完成

如果你仅仅就想剪一层，可以这样写：

included_layers = [model.model[3].conv] # 仅仅想剪一个卷积层

这样也可以检测出来效果图。

3.剪枝后的训练

这里需要和稀疏训练区别一下，因为很多人在之前项目中问我有没有稀疏训练。我这里的通道剪枝是离线式的，也就是针对已经训练好的模型进行剪枝，而边训练边剪枝是在线式剪枝，这个训练过程也就是稀疏训练，所以还是有区别的。

训练后的剪枝训练与训练部分是一样的，只不过加一个pt参数而已。命令如下：

python train.py --weights model_data/layer_pruning.pt --data data/mydata.yaml --pt

4.剪枝后的模型预测

剪枝后的预测，和正常预测一样。

python detect.py --weights model_data/layer_pruning.pt --source [你的图像路径]

这里再说明一下！！本文章只是给大家造个轮子，具体最终的剪枝效果，需要根据自己的需求以及实际效果来实现，我对整个backbone剪枝80%后的微调训练反正是效果很不好，对SPPF后其他的层剪枝还稍微好点，网上也有很多人说对backbone剪枝效果不行。

代码：

GitHub - YINYIPENG-EN/Pruning_for_YOLOV5_pytorch

所遇问题：

1.剪枝后的微调训练中如果采用原来优化器中参数训练可能会报以下错误：

训练到一半报错：RuntimeError: The size of tensor a (512) must match the size of tensor b (103) at non-singleton dimension 1

解决办法：出现这种问题可能是由于原先用的SGD，但现在又用Adam训练；另一种是剪枝后由于网络结构发生了改变，原先优化器的一些参数无法加载进去，可以采用key所对应value的shape进行加载，或者采用默认权重进行训练，致于哪个效果好可以自行尝试。

华为云开发者联盟

为开发者提供学习成长、分享交流、生态实践、资源工具等服务，帮助开发者快速成长。

更多推荐

华为云CodeArts IDE For Python 快速使用指南

华为云开发者联盟

小小开发板承载万千创新可能，小熊派的云上奇遇记

华为云开发者联盟

如何快速入驻O3使能伙伴服务作业平台

华为云开发者联盟

所有评论(0)

查看更多评论

爱吃肉的鹏

@z240626191s

已为社区贡献2条内容