目标检测 YOLOv5 – 模型的样子
flyfish
文章目录
目标检测 YOLOv5 – 模型的样子
版本: YOLOv5:v5
以yolov5s.pt为例查看模型的样子
开始加载模型文件
yolov5s.pt
def attempt_load(weights, map_location=None):
模型内容如下
ckpt: {
'epoch': -1,
'best_fitness': array([0.37287]),
'training_results': None,
'model': Model(
(model): Sequential(
(0): Focus(
(conv): Conv(
(conv): Conv2d(12, 32, kernel_size = (3, 3), stride = (1, 1), padding = (1, 1), bias = False)
(bn): BatchNorm2d(32, eps = 0.001, momentum = 0.03, affine = True, track_running_stats = True)
(act): SiLU()
)
)
......
(24): Detect(
(m): ModuleList(
(0): Conv2d(128, 255, kernel_size = (1, 1), stride = (1, 1))
(1): Conv2d(256, 255, kernel_size = (1, 1), stride = (1, 1))
(2): Conv2d(512, 255, kernel_size = (1, 1), stride = (1, 1))
)
)
)
),
'optimizer': None,
'wandb_id': None
}
模型的层
具体哪一层可以通过model.model[下标]的形式获取。负数表示倒着获取
倒数第一层
model.model[-1]
Detect(
(m): ModuleList(
(0): Conv2d(128, 255, kernel_size=(1, 1), stride=(1, 1))
(1): Conv2d(256, 255, kernel_size=(1, 1), stride=(1, 1))
(2): Conv2d(512, 255, kernel_size=(1, 1), stride=(1, 1))
)
)
倒数第二层
model.model[-2]
C3(
(cv1): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv3): Conv(
(conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU(inplace=True)
)
(cv2): Conv(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU(inplace=True)
)
)
)
)
模型的属性
for name,value in vars(model).items():
print('%s=%s'%(name,value))
例如获取类别名称model.names
可以获取的属性包括以下内容
training = False
_parameters = OrderedDict()
_buffers = OrderedDict()
_non_persistent_buffers_set = set()
_backward_hooks = OrderedDict()
_forward_hooks = OrderedDict()
_forward_pre_hooks = OrderedDict()
_state_dict_hooks = OrderedDict()
_load_state_dict_pre_hooks = OrderedDict()
_modules = OrderedDict([('model', Sequential(
(0): Focus(
(conv): Conv(
(conv): Conv2d(12, 32, kernel_size = (3, 3), stride = (1, 1), padding = (1, 1))
(act): SiLU(inplace = True)
)
)
......
(24): Detect(
(m): ModuleList(
(0): Conv2d(128, 255, kernel_size = (1, 1), stride = (1, 1))
(1): Conv2d(256, 255, kernel_size = (1, 1), stride = (1, 1))
(2): Conv2d(512, 255, kernel_size = (1, 1), stride = (1, 1))
)
)
))])
yaml = {
'nc': 80,
'depth_multiple': 0.33,
'width_multiple': 0.5,
'anchors': [
[10, 13, 16, 30, 33, 23],
[30, 61, 62, 45, 59, 119],
[116, 90, 156, 198, 373, 326]
],
'backbone': [
[-1, 1, 'Focus', [64, 3]],
[-1, 1, 'Conv', [128, 3, 2]],
[-1, 3, 'C3', [128]],
[-1, 1, 'Conv', [256, 3, 2]],
[-1, 9, 'C3', [256]],
[-1, 1, 'Conv', [512, 3, 2]],
[-1, 9, 'C3', [512]],
[-1, 1, 'Conv', [1024, 3, 2]],
[-1, 1, 'SPP', [1024, [5, 9, 13]]],
[-1, 3, 'C3', [1024, False]]
],
'head': [
[-1, 1, 'Conv', [512, 1, 1]],
[-1, 1, 'nn.Upsample', ['None', 2, 'nearest']],
[
[-1, 6], 1, 'Concat', [1]
],
[-1, 3, 'C3', [512, False]],
[-1, 1, 'Conv', [256, 1, 1]],
[-1, 1, 'nn.Upsample', ['None', 2, 'nearest']],
[
[-1, 4], 1, 'Concat', [1]
],
[-1, 3, 'C3', [256, False]],
[-1, 1, 'Conv', [256, 3, 2]],
[
[-1, 14], 1, 'Concat', [1]
],
[-1, 3, 'C3', [512, False]],
[-1, 1, 'Conv', [512, 3, 2]],
[
[-1, 10], 1, 'Concat', [1]
],
[-1, 3, 'C3', [1024, False]],
[
[17, 20, 23], 1, 'Detect', ['nc', 'anchors']
]
],
'ch': 3
}
save = [4, 6, 10, 14, 17, 20, 23]
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']
stride = tensor([8., 16., 32.])
nc = 80
hyp = {
'lr0': 0.01,
'lrf': 0.2,
'momentum': 0.937,
'weight_decay': 0.0005,
'warmup_epochs': 3.0,
'warmup_momentum': 0.8,
'warmup_bias_lr': 0.1,
'box': 0.05,
'cls': 0.3,
'cls_pw': 1.0,
'obj': 0.7,
'obj_pw': 1.0,
'iou_t': 0.2,
'anchor_t': 4.0,
'fl_gamma': 0.0,
'hsv_h': 0.015,
'hsv_s': 0.7,
'hsv_v': 0.4,
'degrees': 0.0,
'translate': 0.1,
'scale': 0.9,
'shear': 0.0,
'perspective': 0.0,
'flipud': 0.0,
'fliplr': 0.5,
'mosaic': 1.0,
'mixup': 0.01
}
gr = 1.0
class_weights = tensor([1.20752e-02, ......, 2.12184e+00, 6.56878e-01, 1.56888e+01, 1.59711e+00
], dtype = torch.float64)
_is_full_backward_hook = None
模块的名称以及模块本身
代码
for name, module in model.named_modules():
print(name)
这里只输出名字
model model.0 model.0.conv model.0.conv.conv model.0.conv.act model.1 model.1.conv model.1.act ...... model.22 model.23 model.23.cv1 model.23.cv1.conv model.23.cv1.act model.23.cv2 model.23.cv2.conv model.23.cv2.act model.23.cv3 model.23.cv3.conv model.23.cv3.act model.23.m model.23.m.0 model.23.m.0.cv1 model.23.m.0.cv1.conv model.23.m.0.cv1.act model.23.m.0.cv2 model.23.m.0.cv2.conv model.23.m.0.cv2.act model.24 model.24.m model.24.m.0 model.24.m.1 model.24.m.2
模型的权重
代码
list(model.parameters())[0]
内容
Parameter containing:
tensor([[[[-2.73007e-01, -1.44108e+00, -1.18709e+00],
[-3.13122e-01, -9.47540e-01, -7.23963e-01],
[ 4.31564e-01, 2.05478e+00, 1.50800e+00]],
......
[[ 8.07673e-01, 1.51624e+00, 2.86977e-01],
[-1.81044e+00, -1.48112e+00, -6.51210e-01],
[-5.19720e-01, -1.99577e-01, 1.39392e-01]]]])
模型权重的名字和权重
代码
list(model.named_parameters())
model.0.conv.conv.weight是名字
('model.0.conv.conv.weight', Parameter containing:
tensor([[[[-2.73007e-01, -1.44108e+00, -1.18709e+00],
[-3.13122e-01, -9.47540e-01, -7.23963e-01],
[ 4.31564e-01, 2.05478e+00, 1.50800e+00]],
......
[[ 8.07673e-01, 1.51624e+00, 2.86977e-01],
[-1.81044e+00, -1.48112e+00, -6.51210e-01],
[-5.19720e-01, -1.99577e-01, 1.39392e-01]]]]))
完整的model
Model(
(model): Sequential(
(0): Focus(
(conv): Conv(
(conv): Conv2d(12, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
(1): Conv(
(conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU()
)
(2): C3(
(cv1): Conv(
(conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
)
)
(3): Conv(
(conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU()
)
(4): C3(
(cv1): Conv(
(conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
(2): Bottleneck(
(cv1): Conv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
)
)
(5): Conv(
(conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU()
)
(6): C3(
(cv1): Conv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
(2): Bottleneck(
(cv1): Conv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
)
)
(7): Conv(
(conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU()
)
(8): SPP(
(cv1): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(m): ModuleList(
(0): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
(1): MaxPool2d(kernel_size=9, stride=1, padding=4, dilation=1, ceil_mode=False)
(2): MaxPool2d(kernel_size=13, stride=1, padding=6, dilation=1, ceil_mode=False)
)
)
(9): C3(
(cv1): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
)
)
(10): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(11): Upsample(scale_factor=2.0, mode=nearest)
(12): Concat()
(13): C3(
(cv1): Conv(
(conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
)
)
(14): Conv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(15): Upsample(scale_factor=2.0, mode=nearest)
(16): Concat()
(17): C3(
(cv1): Conv(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
)
)
(18): Conv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU()
)
(19): Concat()
(20): C3(
(cv1): Conv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
)
)
(21): Conv(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(act): SiLU()
)
(22): Concat()
(23): C3(
(cv1): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(act): SiLU()
)
)
)
)
(24): Detect(
(m): ModuleList(
(0): Conv2d(128, 255, kernel_size=(1, 1), stride=(1, 1))
(1): Conv2d(256, 255, kernel_size=(1, 1), stride=(1, 1))
(2): Conv2d(512, 255, kernel_size=(1, 1), stride=(1, 1))
)
)
)
)
完整模型图片展示
图片较大，可下载看
Be First to Comment