Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

运行prune 过程中出现键值不对应的问题 #65

Closed
baidingyuan opened this issue Dec 21, 2021 · 6 comments
Closed

运行prune 过程中出现键值不对应的问题 #65

baidingyuan opened this issue Dec 21, 2021 · 6 comments

Comments

@baidingyuan
Copy link

对X 版本进行裁剪,训练和稀疏训练正常,使用prune 文件时出错,请教一下解决办法
发现是pruned_model_state.keys() 和modelstate.keys() 里面的键值不匹配
出错位置代码
` pruned_model = ModelPruned(maskbndict=maskbndict, cfg=pruned_yaml, ch=3).cuda()
# Compatibility updates
for m in pruned_model.modules():
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]:
m.inplace = True # pytorch 1.7.0 compatibility
elif type(m) is Conv:
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility

from_to_map = pruned_model.from_to_map
pruned_model_state = pruned_model.state_dict()
if pruned_model_state.keys() == modelstate.keys():
    print("1")
else:
    for k in pruned_model_state.keys():
        print(k)
    print("-----------------------------------------------------------------")
    for v in modelstate.keys():
        print(v)`

打印出来裁剪后的模型状态键值远少于裁剪前的
pruned_model_state.keys():

model.0.conv.conv.weight
model.0.conv.bn.weight
model.0.conv.bn.bias
model.0.conv.bn.running_mean
model.0.conv.bn.running_var
model.0.conv.bn.num_batches_tracked
model.1.conv.weight
model.1.bn.weight
model.1.bn.bias
model.1.bn.running_mean
model.1.bn.running_var
model.1.bn.num_batches_tracked
model.2.cv1.conv.weight
model.2.cv1.bn.weight
model.2.cv1.bn.bias
model.2.cv1.bn.running_mean
model.2.cv1.bn.running_var
model.2.cv1.bn.num_batches_tracked
model.2.cv2.conv.weight
model.2.cv2.bn.weight
model.2.cv2.bn.bias
model.2.cv2.bn.running_mean
model.2.cv2.bn.running_var
model.2.cv2.bn.num_batches_tracked
model.2.cv3.conv.weight
model.2.cv3.bn.weight
model.2.cv3.bn.bias
model.2.cv3.bn.running_mean
model.2.cv3.bn.running_var
model.2.cv3.bn.num_batches_tracked
model.2.m.0.cv1.conv.weight
model.2.m.0.cv1.bn.weight
model.2.m.0.cv1.bn.bias
model.2.m.0.cv1.bn.running_mean
model.2.m.0.cv1.bn.running_var
model.2.m.0.cv1.bn.num_batches_tracked
model.2.m.0.cv2.conv.weight
model.2.m.0.cv2.bn.weight
model.2.m.0.cv2.bn.bias
model.2.m.0.cv2.bn.running_mean
model.2.m.0.cv2.bn.running_var
model.2.m.0.cv2.bn.num_batches_tracked
model.3.conv.weight
model.3.bn.weight
model.3.bn.bias
model.3.bn.running_mean
model.3.bn.running_var
model.3.bn.num_batches_tracked
model.4.cv1.conv.weight
model.4.cv1.bn.weight
model.4.cv1.bn.bias
model.4.cv1.bn.running_mean
model.4.cv1.bn.running_var
model.4.cv1.bn.num_batches_tracked
model.4.cv2.conv.weight
model.4.cv2.bn.weight
model.4.cv2.bn.bias
model.4.cv2.bn.running_mean
model.4.cv2.bn.running_var
model.4.cv2.bn.num_batches_tracked
model.4.cv3.conv.weight
model.4.cv3.bn.weight
model.4.cv3.bn.bias
model.4.cv3.bn.running_mean
model.4.cv3.bn.running_var
model.4.cv3.bn.num_batches_tracked
model.4.m.0.cv1.conv.weight
model.4.m.0.cv1.bn.weight
model.4.m.0.cv1.bn.bias
model.4.m.0.cv1.bn.running_mean
model.4.m.0.cv1.bn.running_var
model.4.m.0.cv1.bn.num_batches_tracked
model.4.m.0.cv2.conv.weight
model.4.m.0.cv2.bn.weight
model.4.m.0.cv2.bn.bias
model.4.m.0.cv2.bn.running_mean
model.4.m.0.cv2.bn.running_var
model.4.m.0.cv2.bn.num_batches_tracked
model.4.m.1.cv1.conv.weight
model.4.m.1.cv1.bn.weight
model.4.m.1.cv1.bn.bias
model.4.m.1.cv1.bn.running_mean
model.4.m.1.cv1.bn.running_var
model.4.m.1.cv1.bn.num_batches_tracked
model.4.m.1.cv2.conv.weight
model.4.m.1.cv2.bn.weight
model.4.m.1.cv2.bn.bias
model.4.m.1.cv2.bn.running_mean
model.4.m.1.cv2.bn.running_var
model.4.m.1.cv2.bn.num_batches_tracked
model.4.m.2.cv1.conv.weight
model.4.m.2.cv1.bn.weight
model.4.m.2.cv1.bn.bias
model.4.m.2.cv1.bn.running_mean
model.4.m.2.cv1.bn.running_var
model.4.m.2.cv1.bn.num_batches_tracked
model.4.m.2.cv2.conv.weight
model.4.m.2.cv2.bn.weight
model.4.m.2.cv2.bn.bias
model.4.m.2.cv2.bn.running_mean
model.4.m.2.cv2.bn.running_var
model.4.m.2.cv2.bn.num_batches_tracked
model.5.conv.weight
model.5.bn.weight
model.5.bn.bias
model.5.bn.running_mean
model.5.bn.running_var
model.5.bn.num_batches_tracked
model.6.cv1.conv.weight
model.6.cv1.bn.weight
model.6.cv1.bn.bias
model.6.cv1.bn.running_mean
model.6.cv1.bn.running_var
model.6.cv1.bn.num_batches_tracked
model.6.cv2.conv.weight
model.6.cv2.bn.weight
model.6.cv2.bn.bias
model.6.cv2.bn.running_mean
model.6.cv2.bn.running_var
model.6.cv2.bn.num_batches_tracked
model.6.cv3.conv.weight
model.6.cv3.bn.weight
model.6.cv3.bn.bias
model.6.cv3.bn.running_mean
model.6.cv3.bn.running_var
model.6.cv3.bn.num_batches_tracked
model.6.m.0.cv1.conv.weight
model.6.m.0.cv1.bn.weight
model.6.m.0.cv1.bn.bias
model.6.m.0.cv1.bn.running_mean
model.6.m.0.cv1.bn.running_var
model.6.m.0.cv1.bn.num_batches_tracked
model.6.m.0.cv2.conv.weight
model.6.m.0.cv2.bn.weight
model.6.m.0.cv2.bn.bias
model.6.m.0.cv2.bn.running_mean
model.6.m.0.cv2.bn.running_var
model.6.m.0.cv2.bn.num_batches_tracked
model.6.m.1.cv1.conv.weight
model.6.m.1.cv1.bn.weight
model.6.m.1.cv1.bn.bias
model.6.m.1.cv1.bn.running_mean
model.6.m.1.cv1.bn.running_var
model.6.m.1.cv1.bn.num_batches_tracked
model.6.m.1.cv2.conv.weight
model.6.m.1.cv2.bn.weight
model.6.m.1.cv2.bn.bias
model.6.m.1.cv2.bn.running_mean
model.6.m.1.cv2.bn.running_var
model.6.m.1.cv2.bn.num_batches_tracked
model.6.m.2.cv1.conv.weight
model.6.m.2.cv1.bn.weight
model.6.m.2.cv1.bn.bias
model.6.m.2.cv1.bn.running_mean
model.6.m.2.cv1.bn.running_var
model.6.m.2.cv1.bn.num_batches_tracked
model.6.m.2.cv2.conv.weight
model.6.m.2.cv2.bn.weight
model.6.m.2.cv2.bn.bias
model.6.m.2.cv2.bn.running_mean
model.6.m.2.cv2.bn.running_var
model.6.m.2.cv2.bn.num_batches_tracked
model.7.conv.weight
model.7.bn.weight
model.7.bn.bias
model.7.bn.running_mean
model.7.bn.running_var
model.7.bn.num_batches_tracked
model.8.cv1.conv.weight
model.8.cv1.bn.weight
model.8.cv1.bn.bias
model.8.cv1.bn.running_mean
model.8.cv1.bn.running_var
model.8.cv1.bn.num_batches_tracked
model.8.cv2.conv.weight
model.8.cv2.bn.weight
model.8.cv2.bn.bias
model.8.cv2.bn.running_mean
model.8.cv2.bn.running_var
model.8.cv2.bn.num_batches_tracked
model.9.cv1.conv.weight
model.9.cv1.bn.weight
model.9.cv1.bn.bias
model.9.cv1.bn.running_mean
model.9.cv1.bn.running_var
model.9.cv1.bn.num_batches_tracked
model.9.cv2.conv.weight
model.9.cv2.bn.weight
model.9.cv2.bn.bias
model.9.cv2.bn.running_mean
model.9.cv2.bn.running_var
model.9.cv2.bn.num_batches_tracked
model.9.cv3.conv.weight
model.9.cv3.bn.weight
model.9.cv3.bn.bias
model.9.cv3.bn.running_mean
model.9.cv3.bn.running_var
model.9.cv3.bn.num_batches_tracked
model.9.m.0.cv1.conv.weight
model.9.m.0.cv1.bn.weight
model.9.m.0.cv1.bn.bias
model.9.m.0.cv1.bn.running_mean
model.9.m.0.cv1.bn.running_var
model.9.m.0.cv1.bn.num_batches_tracked
model.9.m.0.cv2.conv.weight
model.9.m.0.cv2.bn.weight
model.9.m.0.cv2.bn.bias
model.9.m.0.cv2.bn.running_mean
model.9.m.0.cv2.bn.running_var
model.9.m.0.cv2.bn.num_batches_tracked
model.10.conv.weight
model.10.bn.weight
model.10.bn.bias
model.10.bn.running_mean
model.10.bn.running_var
model.10.bn.num_batches_tracked
model.13.cv1.conv.weight
model.13.cv1.bn.weight
model.13.cv1.bn.bias
model.13.cv1.bn.running_mean
model.13.cv1.bn.running_var
model.13.cv1.bn.num_batches_tracked
model.13.cv2.conv.weight
model.13.cv2.bn.weight
model.13.cv2.bn.bias
model.13.cv2.bn.running_mean
model.13.cv2.bn.running_var
model.13.cv2.bn.num_batches_tracked
model.13.cv3.conv.weight
model.13.cv3.bn.weight
model.13.cv3.bn.bias
model.13.cv3.bn.running_mean
model.13.cv3.bn.running_var
model.13.cv3.bn.num_batches_tracked
model.13.m.0.cv1.conv.weight
model.13.m.0.cv1.bn.weight
model.13.m.0.cv1.bn.bias
model.13.m.0.cv1.bn.running_mean
model.13.m.0.cv1.bn.running_var
model.13.m.0.cv1.bn.num_batches_tracked
model.13.m.0.cv2.conv.weight
model.13.m.0.cv2.bn.weight
model.13.m.0.cv2.bn.bias
model.13.m.0.cv2.bn.running_mean
model.13.m.0.cv2.bn.running_var
model.13.m.0.cv2.bn.num_batches_tracked
model.14.conv.weight
model.14.bn.weight
model.14.bn.bias
model.14.bn.running_mean
model.14.bn.running_var
model.14.bn.num_batches_tracked
model.17.cv1.conv.weight
model.17.cv1.bn.weight
model.17.cv1.bn.bias
model.17.cv1.bn.running_mean
model.17.cv1.bn.running_var
model.17.cv1.bn.num_batches_tracked
model.17.cv2.conv.weight
model.17.cv2.bn.weight
model.17.cv2.bn.bias
model.17.cv2.bn.running_mean
model.17.cv2.bn.running_var
model.17.cv2.bn.num_batches_tracked
model.17.cv3.conv.weight
model.17.cv3.bn.weight
model.17.cv3.bn.bias
model.17.cv3.bn.running_mean
model.17.cv3.bn.running_var
model.17.cv3.bn.num_batches_tracked
model.17.m.0.cv1.conv.weight
model.17.m.0.cv1.bn.weight
model.17.m.0.cv1.bn.bias
model.17.m.0.cv1.bn.running_mean
model.17.m.0.cv1.bn.running_var
model.17.m.0.cv1.bn.num_batches_tracked
model.17.m.0.cv2.conv.weight
model.17.m.0.cv2.bn.weight
model.17.m.0.cv2.bn.bias
model.17.m.0.cv2.bn.running_mean
model.17.m.0.cv2.bn.running_var
model.17.m.0.cv2.bn.num_batches_tracked
model.18.conv.weight
model.18.bn.weight
model.18.bn.bias
model.18.bn.running_mean
model.18.bn.running_var
model.18.bn.num_batches_tracked
model.20.cv1.conv.weight
model.20.cv1.bn.weight
model.20.cv1.bn.bias
model.20.cv1.bn.running_mean
model.20.cv1.bn.running_var
model.20.cv1.bn.num_batches_tracked
model.20.cv2.conv.weight
model.20.cv2.bn.weight
model.20.cv2.bn.bias
model.20.cv2.bn.running_mean
model.20.cv2.bn.running_var
model.20.cv2.bn.num_batches_tracked
model.20.cv3.conv.weight
model.20.cv3.bn.weight
model.20.cv3.bn.bias
model.20.cv3.bn.running_mean
model.20.cv3.bn.running_var
model.20.cv3.bn.num_batches_tracked
model.20.m.0.cv1.conv.weight
model.20.m.0.cv1.bn.weight
model.20.m.0.cv1.bn.bias
model.20.m.0.cv1.bn.running_mean
model.20.m.0.cv1.bn.running_var
model.20.m.0.cv1.bn.num_batches_tracked
model.20.m.0.cv2.conv.weight
model.20.m.0.cv2.bn.weight
model.20.m.0.cv2.bn.bias
model.20.m.0.cv2.bn.running_mean
model.20.m.0.cv2.bn.running_var
model.20.m.0.cv2.bn.num_batches_tracked
model.21.conv.weight
model.21.bn.weight
model.21.bn.bias
model.21.bn.running_mean
model.21.bn.running_var
model.21.bn.num_batches_tracked
model.23.cv1.conv.weight
model.23.cv1.bn.weight
model.23.cv1.bn.bias
model.23.cv1.bn.running_mean
model.23.cv1.bn.running_var
model.23.cv1.bn.num_batches_tracked
model.23.cv2.conv.weight
model.23.cv2.bn.weight
model.23.cv2.bn.bias
model.23.cv2.bn.running_mean
model.23.cv2.bn.running_var
model.23.cv2.bn.num_batches_tracked
model.23.cv3.conv.weight
model.23.cv3.bn.weight
model.23.cv3.bn.bias
model.23.cv3.bn.running_mean
model.23.cv3.bn.running_var
model.23.cv3.bn.num_batches_tracked
model.23.m.0.cv1.conv.weight
model.23.m.0.cv1.bn.weight
model.23.m.0.cv1.bn.bias
model.23.m.0.cv1.bn.running_mean
model.23.m.0.cv1.bn.running_var
model.23.m.0.cv1.bn.num_batches_tracked
model.23.m.0.cv2.conv.weight
model.23.m.0.cv2.bn.weight
model.23.m.0.cv2.bn.bias
model.23.m.0.cv2.bn.running_mean
model.23.m.0.cv2.bn.running_var
model.23.m.0.cv2.bn.num_batches_tracked
model.24.anchors
model.24.anchor_grid
model.24.m.0.weight
model.24.m.0.bias
model.24.m.1.weight
model.24.m.1.bias
model.24.m.2.weight
model.24.m.2.bias

modelstate.keys():

model.0.conv.conv.weight
model.0.conv.bn.weight
model.0.conv.bn.bias
model.0.conv.bn.running_mean
model.0.conv.bn.running_var
model.0.conv.bn.num_batches_tracked
model.1.conv.weight
model.1.bn.weight
model.1.bn.bias
model.1.bn.running_mean
model.1.bn.running_var
model.1.bn.num_batches_tracked
model.2.cv1.conv.weight
model.2.cv1.bn.weight
model.2.cv1.bn.bias
model.2.cv1.bn.running_mean
model.2.cv1.bn.running_var
model.2.cv1.bn.num_batches_tracked
model.2.cv2.conv.weight
model.2.cv2.bn.weight
model.2.cv2.bn.bias
model.2.cv2.bn.running_mean
model.2.cv2.bn.running_var
model.2.cv2.bn.num_batches_tracked
model.2.cv3.conv.weight
model.2.cv3.bn.weight
model.2.cv3.bn.bias
model.2.cv3.bn.running_mean
model.2.cv3.bn.running_var
model.2.cv3.bn.num_batches_tracked
model.2.m.0.cv1.conv.weight
model.2.m.0.cv1.bn.weight
model.2.m.0.cv1.bn.bias
model.2.m.0.cv1.bn.running_mean
model.2.m.0.cv1.bn.running_var
model.2.m.0.cv1.bn.num_batches_tracked
model.2.m.0.cv2.conv.weight
model.2.m.0.cv2.bn.weight
model.2.m.0.cv2.bn.bias
model.2.m.0.cv2.bn.running_mean
model.2.m.0.cv2.bn.running_var
model.2.m.0.cv2.bn.num_batches_tracked
model.2.m.1.cv1.conv.weight
model.2.m.1.cv1.bn.weight
model.2.m.1.cv1.bn.bias
model.2.m.1.cv1.bn.running_mean
model.2.m.1.cv1.bn.running_var
model.2.m.1.cv1.bn.num_batches_tracked
model.2.m.1.cv2.conv.weight
model.2.m.1.cv2.bn.weight
model.2.m.1.cv2.bn.bias
model.2.m.1.cv2.bn.running_mean
model.2.m.1.cv2.bn.running_var
model.2.m.1.cv2.bn.num_batches_tracked
model.2.m.2.cv1.conv.weight
model.2.m.2.cv1.bn.weight
model.2.m.2.cv1.bn.bias
model.2.m.2.cv1.bn.running_mean
model.2.m.2.cv1.bn.running_var
model.2.m.2.cv1.bn.num_batches_tracked
model.2.m.2.cv2.conv.weight
model.2.m.2.cv2.bn.weight
model.2.m.2.cv2.bn.bias
model.2.m.2.cv2.bn.running_mean
model.2.m.2.cv2.bn.running_var
model.2.m.2.cv2.bn.num_batches_tracked
model.2.m.3.cv1.conv.weight
model.2.m.3.cv1.bn.weight
model.2.m.3.cv1.bn.bias
model.2.m.3.cv1.bn.running_mean
model.2.m.3.cv1.bn.running_var
model.2.m.3.cv1.bn.num_batches_tracked
model.2.m.3.cv2.conv.weight
model.2.m.3.cv2.bn.weight
model.2.m.3.cv2.bn.bias
model.2.m.3.cv2.bn.running_mean
model.2.m.3.cv2.bn.running_var
model.2.m.3.cv2.bn.num_batches_tracked
model.3.conv.weight
model.3.bn.weight
model.3.bn.bias
model.3.bn.running_mean
model.3.bn.running_var
model.3.bn.num_batches_tracked
model.4.cv1.conv.weight
model.4.cv1.bn.weight
model.4.cv1.bn.bias
model.4.cv1.bn.running_mean
model.4.cv1.bn.running_var
model.4.cv1.bn.num_batches_tracked
model.4.cv2.conv.weight
model.4.cv2.bn.weight
model.4.cv2.bn.bias
model.4.cv2.bn.running_mean
model.4.cv2.bn.running_var
model.4.cv2.bn.num_batches_tracked
model.4.cv3.conv.weight
model.4.cv3.bn.weight
model.4.cv3.bn.bias
model.4.cv3.bn.running_mean
model.4.cv3.bn.running_var
model.4.cv3.bn.num_batches_tracked
model.4.m.0.cv1.conv.weight
model.4.m.0.cv1.bn.weight
model.4.m.0.cv1.bn.bias
model.4.m.0.cv1.bn.running_mean
model.4.m.0.cv1.bn.running_var
model.4.m.0.cv1.bn.num_batches_tracked
model.4.m.0.cv2.conv.weight
model.4.m.0.cv2.bn.weight
model.4.m.0.cv2.bn.bias
model.4.m.0.cv2.bn.running_mean
model.4.m.0.cv2.bn.running_var
model.4.m.0.cv2.bn.num_batches_tracked
model.4.m.1.cv1.conv.weight
model.4.m.1.cv1.bn.weight
model.4.m.1.cv1.bn.bias
model.4.m.1.cv1.bn.running_mean
model.4.m.1.cv1.bn.running_var
model.4.m.1.cv1.bn.num_batches_tracked
model.4.m.1.cv2.conv.weight
model.4.m.1.cv2.bn.weight
model.4.m.1.cv2.bn.bias
model.4.m.1.cv2.bn.running_mean
model.4.m.1.cv2.bn.running_var
model.4.m.1.cv2.bn.num_batches_tracked
model.4.m.2.cv1.conv.weight
model.4.m.2.cv1.bn.weight
model.4.m.2.cv1.bn.bias
model.4.m.2.cv1.bn.running_mean
model.4.m.2.cv1.bn.running_var
model.4.m.2.cv1.bn.num_batches_tracked
model.4.m.2.cv2.conv.weight
model.4.m.2.cv2.bn.weight
model.4.m.2.cv2.bn.bias
model.4.m.2.cv2.bn.running_mean
model.4.m.2.cv2.bn.running_var
model.4.m.2.cv2.bn.num_batches_tracked
model.4.m.3.cv1.conv.weight
model.4.m.3.cv1.bn.weight
model.4.m.3.cv1.bn.bias
model.4.m.3.cv1.bn.running_mean
model.4.m.3.cv1.bn.running_var
model.4.m.3.cv1.bn.num_batches_tracked
model.4.m.3.cv2.conv.weight
model.4.m.3.cv2.bn.weight
model.4.m.3.cv2.bn.bias
model.4.m.3.cv2.bn.running_mean
model.4.m.3.cv2.bn.running_var
model.4.m.3.cv2.bn.num_batches_tracked
model.4.m.4.cv1.conv.weight
model.4.m.4.cv1.bn.weight
model.4.m.4.cv1.bn.bias
model.4.m.4.cv1.bn.running_mean
model.4.m.4.cv1.bn.running_var
model.4.m.4.cv1.bn.num_batches_tracked
model.4.m.4.cv2.conv.weight
model.4.m.4.cv2.bn.weight
model.4.m.4.cv2.bn.bias
model.4.m.4.cv2.bn.running_mean
model.4.m.4.cv2.bn.running_var
model.4.m.4.cv2.bn.num_batches_tracked
model.4.m.5.cv1.conv.weight
model.4.m.5.cv1.bn.weight
model.4.m.5.cv1.bn.bias
model.4.m.5.cv1.bn.running_mean
model.4.m.5.cv1.bn.running_var
model.4.m.5.cv1.bn.num_batches_tracked
model.4.m.5.cv2.conv.weight
model.4.m.5.cv2.bn.weight
model.4.m.5.cv2.bn.bias
model.4.m.5.cv2.bn.running_mean
model.4.m.5.cv2.bn.running_var
model.4.m.5.cv2.bn.num_batches_tracked
model.4.m.6.cv1.conv.weight
model.4.m.6.cv1.bn.weight
model.4.m.6.cv1.bn.bias
model.4.m.6.cv1.bn.running_mean
model.4.m.6.cv1.bn.running_var
model.4.m.6.cv1.bn.num_batches_tracked
model.4.m.6.cv2.conv.weight
model.4.m.6.cv2.bn.weight
model.4.m.6.cv2.bn.bias
model.4.m.6.cv2.bn.running_mean
model.4.m.6.cv2.bn.running_var
model.4.m.6.cv2.bn.num_batches_tracked
model.4.m.7.cv1.conv.weight
model.4.m.7.cv1.bn.weight
model.4.m.7.cv1.bn.bias
model.4.m.7.cv1.bn.running_mean
model.4.m.7.cv1.bn.running_var
model.4.m.7.cv1.bn.num_batches_tracked
model.4.m.7.cv2.conv.weight
model.4.m.7.cv2.bn.weight
model.4.m.7.cv2.bn.bias
model.4.m.7.cv2.bn.running_mean
model.4.m.7.cv2.bn.running_var
model.4.m.7.cv2.bn.num_batches_tracked
model.4.m.8.cv1.conv.weight
model.4.m.8.cv1.bn.weight
model.4.m.8.cv1.bn.bias
model.4.m.8.cv1.bn.running_mean
model.4.m.8.cv1.bn.running_var
model.4.m.8.cv1.bn.num_batches_tracked
model.4.m.8.cv2.conv.weight
model.4.m.8.cv2.bn.weight
model.4.m.8.cv2.bn.bias
model.4.m.8.cv2.bn.running_mean
model.4.m.8.cv2.bn.running_var
model.4.m.8.cv2.bn.num_batches_tracked
model.4.m.9.cv1.conv.weight
model.4.m.9.cv1.bn.weight
model.4.m.9.cv1.bn.bias
model.4.m.9.cv1.bn.running_mean
model.4.m.9.cv1.bn.running_var
model.4.m.9.cv1.bn.num_batches_tracked
model.4.m.9.cv2.conv.weight
model.4.m.9.cv2.bn.weight
model.4.m.9.cv2.bn.bias
model.4.m.9.cv2.bn.running_mean
model.4.m.9.cv2.bn.running_var
model.4.m.9.cv2.bn.num_batches_tracked
model.4.m.10.cv1.conv.weight
model.4.m.10.cv1.bn.weight
model.4.m.10.cv1.bn.bias
model.4.m.10.cv1.bn.running_mean
model.4.m.10.cv1.bn.running_var
model.4.m.10.cv1.bn.num_batches_tracked
model.4.m.10.cv2.conv.weight
model.4.m.10.cv2.bn.weight
model.4.m.10.cv2.bn.bias
model.4.m.10.cv2.bn.running_mean
model.4.m.10.cv2.bn.running_var
model.4.m.10.cv2.bn.num_batches_tracked
model.4.m.11.cv1.conv.weight
model.4.m.11.cv1.bn.weight
model.4.m.11.cv1.bn.bias
model.4.m.11.cv1.bn.running_mean
model.4.m.11.cv1.bn.running_var
model.4.m.11.cv1.bn.num_batches_tracked
model.4.m.11.cv2.conv.weight
model.4.m.11.cv2.bn.weight
model.4.m.11.cv2.bn.bias
model.4.m.11.cv2.bn.running_mean
model.4.m.11.cv2.bn.running_var
model.4.m.11.cv2.bn.num_batches_tracked
model.5.conv.weight
model.5.bn.weight
model.5.bn.bias
model.5.bn.running_mean
model.5.bn.running_var
model.5.bn.num_batches_tracked
model.6.cv1.conv.weight
model.6.cv1.bn.weight
model.6.cv1.bn.bias
model.6.cv1.bn.running_mean
model.6.cv1.bn.running_var
model.6.cv1.bn.num_batches_tracked
model.6.cv2.conv.weight
model.6.cv2.bn.weight
model.6.cv2.bn.bias
model.6.cv2.bn.running_mean
model.6.cv2.bn.running_var
model.6.cv2.bn.num_batches_tracked
model.6.cv3.conv.weight
model.6.cv3.bn.weight
model.6.cv3.bn.bias
model.6.cv3.bn.running_mean
model.6.cv3.bn.running_var
model.6.cv3.bn.num_batches_tracked
model.6.m.0.cv1.conv.weight
model.6.m.0.cv1.bn.weight
model.6.m.0.cv1.bn.bias
model.6.m.0.cv1.bn.running_mean
model.6.m.0.cv1.bn.running_var
model.6.m.0.cv1.bn.num_batches_tracked
model.6.m.0.cv2.conv.weight
model.6.m.0.cv2.bn.weight
model.6.m.0.cv2.bn.bias
model.6.m.0.cv2.bn.running_mean
model.6.m.0.cv2.bn.running_var
model.6.m.0.cv2.bn.num_batches_tracked
model.6.m.1.cv1.conv.weight
model.6.m.1.cv1.bn.weight
model.6.m.1.cv1.bn.bias
model.6.m.1.cv1.bn.running_mean
model.6.m.1.cv1.bn.running_var
model.6.m.1.cv1.bn.num_batches_tracked
model.6.m.1.cv2.conv.weight
model.6.m.1.cv2.bn.weight
model.6.m.1.cv2.bn.bias
model.6.m.1.cv2.bn.running_mean
model.6.m.1.cv2.bn.running_var
model.6.m.1.cv2.bn.num_batches_tracked
model.6.m.2.cv1.conv.weight
model.6.m.2.cv1.bn.weight
model.6.m.2.cv1.bn.bias
model.6.m.2.cv1.bn.running_mean
model.6.m.2.cv1.bn.running_var
model.6.m.2.cv1.bn.num_batches_tracked
model.6.m.2.cv2.conv.weight
model.6.m.2.cv2.bn.weight
model.6.m.2.cv2.bn.bias
model.6.m.2.cv2.bn.running_mean
model.6.m.2.cv2.bn.running_var
model.6.m.2.cv2.bn.num_batches_tracked
model.6.m.3.cv1.conv.weight
model.6.m.3.cv1.bn.weight
model.6.m.3.cv1.bn.bias
model.6.m.3.cv1.bn.running_mean
model.6.m.3.cv1.bn.running_var
model.6.m.3.cv1.bn.num_batches_tracked
model.6.m.3.cv2.conv.weight
model.6.m.3.cv2.bn.weight
model.6.m.3.cv2.bn.bias
model.6.m.3.cv2.bn.running_mean
model.6.m.3.cv2.bn.running_var
model.6.m.3.cv2.bn.num_batches_tracked
model.6.m.4.cv1.conv.weight
model.6.m.4.cv1.bn.weight
model.6.m.4.cv1.bn.bias
model.6.m.4.cv1.bn.running_mean
model.6.m.4.cv1.bn.running_var
model.6.m.4.cv1.bn.num_batches_tracked
model.6.m.4.cv2.conv.weight
model.6.m.4.cv2.bn.weight
model.6.m.4.cv2.bn.bias
model.6.m.4.cv2.bn.running_mean
model.6.m.4.cv2.bn.running_var
model.6.m.4.cv2.bn.num_batches_tracked
model.6.m.5.cv1.conv.weight
model.6.m.5.cv1.bn.weight
model.6.m.5.cv1.bn.bias
model.6.m.5.cv1.bn.running_mean
model.6.m.5.cv1.bn.running_var
model.6.m.5.cv1.bn.num_batches_tracked
model.6.m.5.cv2.conv.weight
model.6.m.5.cv2.bn.weight
model.6.m.5.cv2.bn.bias
model.6.m.5.cv2.bn.running_mean
model.6.m.5.cv2.bn.running_var
model.6.m.5.cv2.bn.num_batches_tracked
model.6.m.6.cv1.conv.weight
model.6.m.6.cv1.bn.weight
model.6.m.6.cv1.bn.bias
model.6.m.6.cv1.bn.running_mean
model.6.m.6.cv1.bn.running_var
model.6.m.6.cv1.bn.num_batches_tracked
model.6.m.6.cv2.conv.weight
model.6.m.6.cv2.bn.weight
model.6.m.6.cv2.bn.bias
model.6.m.6.cv2.bn.running_mean
model.6.m.6.cv2.bn.running_var
model.6.m.6.cv2.bn.num_batches_tracked
model.6.m.7.cv1.conv.weight
model.6.m.7.cv1.bn.weight
model.6.m.7.cv1.bn.bias
model.6.m.7.cv1.bn.running_mean
model.6.m.7.cv1.bn.running_var
model.6.m.7.cv1.bn.num_batches_tracked
model.6.m.7.cv2.conv.weight
model.6.m.7.cv2.bn.weight
model.6.m.7.cv2.bn.bias
model.6.m.7.cv2.bn.running_mean
model.6.m.7.cv2.bn.running_var
model.6.m.7.cv2.bn.num_batches_tracked
model.6.m.8.cv1.conv.weight
model.6.m.8.cv1.bn.weight
model.6.m.8.cv1.bn.bias
model.6.m.8.cv1.bn.running_mean
model.6.m.8.cv1.bn.running_var
model.6.m.8.cv1.bn.num_batches_tracked
model.6.m.8.cv2.conv.weight
model.6.m.8.cv2.bn.weight
model.6.m.8.cv2.bn.bias
model.6.m.8.cv2.bn.running_mean
model.6.m.8.cv2.bn.running_var
model.6.m.8.cv2.bn.num_batches_tracked
model.6.m.9.cv1.conv.weight
model.6.m.9.cv1.bn.weight
model.6.m.9.cv1.bn.bias
model.6.m.9.cv1.bn.running_mean
model.6.m.9.cv1.bn.running_var
model.6.m.9.cv1.bn.num_batches_tracked
model.6.m.9.cv2.conv.weight
model.6.m.9.cv2.bn.weight
model.6.m.9.cv2.bn.bias
model.6.m.9.cv2.bn.running_mean
model.6.m.9.cv2.bn.running_var
model.6.m.9.cv2.bn.num_batches_tracked
model.6.m.10.cv1.conv.weight
model.6.m.10.cv1.bn.weight
model.6.m.10.cv1.bn.bias
model.6.m.10.cv1.bn.running_mean
model.6.m.10.cv1.bn.running_var
model.6.m.10.cv1.bn.num_batches_tracked
model.6.m.10.cv2.conv.weight
model.6.m.10.cv2.bn.weight
model.6.m.10.cv2.bn.bias
model.6.m.10.cv2.bn.running_mean
model.6.m.10.cv2.bn.running_var
model.6.m.10.cv2.bn.num_batches_tracked
model.6.m.11.cv1.conv.weight
model.6.m.11.cv1.bn.weight
model.6.m.11.cv1.bn.bias
model.6.m.11.cv1.bn.running_mean
model.6.m.11.cv1.bn.running_var
model.6.m.11.cv1.bn.num_batches_tracked
model.6.m.11.cv2.conv.weight
model.6.m.11.cv2.bn.weight
model.6.m.11.cv2.bn.bias
model.6.m.11.cv2.bn.running_mean
model.6.m.11.cv2.bn.running_var
model.6.m.11.cv2.bn.num_batches_tracked
model.7.conv.weight
model.7.bn.weight
model.7.bn.bias
model.7.bn.running_mean
model.7.bn.running_var
model.7.bn.num_batches_tracked
model.8.cv1.conv.weight
model.8.cv1.bn.weight
model.8.cv1.bn.bias
model.8.cv1.bn.running_mean
model.8.cv1.bn.running_var
model.8.cv1.bn.num_batches_tracked
model.8.cv2.conv.weight
model.8.cv2.bn.weight
model.8.cv2.bn.bias
model.8.cv2.bn.running_mean
model.8.cv2.bn.running_var
model.8.cv2.bn.num_batches_tracked
model.9.cv1.conv.weight
model.9.cv1.bn.weight
model.9.cv1.bn.bias
model.9.cv1.bn.running_mean
model.9.cv1.bn.running_var
model.9.cv1.bn.num_batches_tracked
model.9.cv2.conv.weight
model.9.cv2.bn.weight
model.9.cv2.bn.bias
model.9.cv2.bn.running_mean
model.9.cv2.bn.running_var
model.9.cv2.bn.num_batches_tracked
model.9.cv3.conv.weight
model.9.cv3.bn.weight
model.9.cv3.bn.bias
model.9.cv3.bn.running_mean
model.9.cv3.bn.running_var
model.9.cv3.bn.num_batches_tracked
model.9.m.0.cv1.conv.weight
model.9.m.0.cv1.bn.weight
model.9.m.0.cv1.bn.bias
model.9.m.0.cv1.bn.running_mean
model.9.m.0.cv1.bn.running_var
model.9.m.0.cv1.bn.num_batches_tracked
model.9.m.0.cv2.conv.weight
model.9.m.0.cv2.bn.weight
model.9.m.0.cv2.bn.bias
model.9.m.0.cv2.bn.running_mean
model.9.m.0.cv2.bn.running_var
model.9.m.0.cv2.bn.num_batches_tracked
model.9.m.1.cv1.conv.weight
model.9.m.1.cv1.bn.weight
model.9.m.1.cv1.bn.bias
model.9.m.1.cv1.bn.running_mean
model.9.m.1.cv1.bn.running_var
model.9.m.1.cv1.bn.num_batches_tracked
model.9.m.1.cv2.conv.weight
model.9.m.1.cv2.bn.weight
model.9.m.1.cv2.bn.bias
model.9.m.1.cv2.bn.running_mean
model.9.m.1.cv2.bn.running_var
model.9.m.1.cv2.bn.num_batches_tracked
model.9.m.2.cv1.conv.weight
model.9.m.2.cv1.bn.weight
model.9.m.2.cv1.bn.bias
model.9.m.2.cv1.bn.running_mean
model.9.m.2.cv1.bn.running_var
model.9.m.2.cv1.bn.num_batches_tracked
model.9.m.2.cv2.conv.weight
model.9.m.2.cv2.bn.weight
model.9.m.2.cv2.bn.bias
model.9.m.2.cv2.bn.running_mean
model.9.m.2.cv2.bn.running_var
model.9.m.2.cv2.bn.num_batches_tracked
model.9.m.3.cv1.conv.weight
model.9.m.3.cv1.bn.weight
model.9.m.3.cv1.bn.bias
model.9.m.3.cv1.bn.running_mean
model.9.m.3.cv1.bn.running_var
model.9.m.3.cv1.bn.num_batches_tracked
model.9.m.3.cv2.conv.weight
model.9.m.3.cv2.bn.weight
model.9.m.3.cv2.bn.bias
model.9.m.3.cv2.bn.running_mean
model.9.m.3.cv2.bn.running_var
model.9.m.3.cv2.bn.num_batches_tracked
model.10.conv.weight
model.10.bn.weight
model.10.bn.bias
model.10.bn.running_mean
model.10.bn.running_var
model.10.bn.num_batches_tracked
model.13.cv1.conv.weight
model.13.cv1.bn.weight
model.13.cv1.bn.bias
model.13.cv1.bn.running_mean
model.13.cv1.bn.running_var
model.13.cv1.bn.num_batches_tracked
model.13.cv2.conv.weight
model.13.cv2.bn.weight
model.13.cv2.bn.bias
model.13.cv2.bn.running_mean
model.13.cv2.bn.running_var
model.13.cv2.bn.num_batches_tracked
model.13.cv3.conv.weight
model.13.cv3.bn.weight
model.13.cv3.bn.bias
model.13.cv3.bn.running_mean
model.13.cv3.bn.running_var
model.13.cv3.bn.num_batches_tracked
model.13.m.0.cv1.conv.weight
model.13.m.0.cv1.bn.weight
model.13.m.0.cv1.bn.bias
model.13.m.0.cv1.bn.running_mean
model.13.m.0.cv1.bn.running_var
model.13.m.0.cv1.bn.num_batches_tracked
model.13.m.0.cv2.conv.weight
model.13.m.0.cv2.bn.weight
model.13.m.0.cv2.bn.bias
model.13.m.0.cv2.bn.running_mean
model.13.m.0.cv2.bn.running_var
model.13.m.0.cv2.bn.num_batches_tracked
model.13.m.1.cv1.conv.weight
model.13.m.1.cv1.bn.weight
model.13.m.1.cv1.bn.bias
model.13.m.1.cv1.bn.running_mean
model.13.m.1.cv1.bn.running_var
model.13.m.1.cv1.bn.num_batches_tracked
model.13.m.1.cv2.conv.weight
model.13.m.1.cv2.bn.weight
model.13.m.1.cv2.bn.bias
model.13.m.1.cv2.bn.running_mean
model.13.m.1.cv2.bn.running_var
model.13.m.1.cv2.bn.num_batches_tracked
model.13.m.2.cv1.conv.weight
model.13.m.2.cv1.bn.weight
model.13.m.2.cv1.bn.bias
model.13.m.2.cv1.bn.running_mean
model.13.m.2.cv1.bn.running_var
model.13.m.2.cv1.bn.num_batches_tracked
model.13.m.2.cv2.conv.weight
model.13.m.2.cv2.bn.weight
model.13.m.2.cv2.bn.bias
model.13.m.2.cv2.bn.running_mean
model.13.m.2.cv2.bn.running_var
model.13.m.2.cv2.bn.num_batches_tracked
model.13.m.3.cv1.conv.weight
model.13.m.3.cv1.bn.weight
model.13.m.3.cv1.bn.bias
model.13.m.3.cv1.bn.running_mean
model.13.m.3.cv1.bn.running_var
model.13.m.3.cv1.bn.num_batches_tracked
model.13.m.3.cv2.conv.weight
model.13.m.3.cv2.bn.weight
model.13.m.3.cv2.bn.bias
model.13.m.3.cv2.bn.running_mean
model.13.m.3.cv2.bn.running_var
model.13.m.3.cv2.bn.num_batches_tracked
model.14.conv.weight
model.14.bn.weight
model.14.bn.bias
model.14.bn.running_mean
model.14.bn.running_var
model.14.bn.num_batches_tracked
model.17.cv1.conv.weight
model.17.cv1.bn.weight
model.17.cv1.bn.bias
model.17.cv1.bn.running_mean
model.17.cv1.bn.running_var
model.17.cv1.bn.num_batches_tracked
model.17.cv2.conv.weight
model.17.cv2.bn.weight
model.17.cv2.bn.bias
model.17.cv2.bn.running_mean
model.17.cv2.bn.running_var
model.17.cv2.bn.num_batches_tracked
model.17.cv3.conv.weight
model.17.cv3.bn.weight
model.17.cv3.bn.bias
model.17.cv3.bn.running_mean
model.17.cv3.bn.running_var
model.17.cv3.bn.num_batches_tracked
model.17.m.0.cv1.conv.weight
model.17.m.0.cv1.bn.weight
model.17.m.0.cv1.bn.bias
model.17.m.0.cv1.bn.running_mean
model.17.m.0.cv1.bn.running_var
model.17.m.0.cv1.bn.num_batches_tracked
model.17.m.0.cv2.conv.weight
model.17.m.0.cv2.bn.weight
model.17.m.0.cv2.bn.bias
model.17.m.0.cv2.bn.running_mean
model.17.m.0.cv2.bn.running_var
model.17.m.0.cv2.bn.num_batches_tracked
model.17.m.1.cv1.conv.weight
model.17.m.1.cv1.bn.weight
model.17.m.1.cv1.bn.bias
model.17.m.1.cv1.bn.running_mean
model.17.m.1.cv1.bn.running_var
model.17.m.1.cv1.bn.num_batches_tracked
model.17.m.1.cv2.conv.weight
model.17.m.1.cv2.bn.weight
model.17.m.1.cv2.bn.bias
model.17.m.1.cv2.bn.running_mean
model.17.m.1.cv2.bn.running_var
model.17.m.1.cv2.bn.num_batches_tracked
model.17.m.2.cv1.conv.weight
model.17.m.2.cv1.bn.weight
model.17.m.2.cv1.bn.bias
model.17.m.2.cv1.bn.running_mean
model.17.m.2.cv1.bn.running_var
model.17.m.2.cv1.bn.num_batches_tracked
model.17.m.2.cv2.conv.weight
model.17.m.2.cv2.bn.weight
model.17.m.2.cv2.bn.bias
model.17.m.2.cv2.bn.running_mean
model.17.m.2.cv2.bn.running_var
model.17.m.2.cv2.bn.num_batches_tracked
model.17.m.3.cv1.conv.weight
model.17.m.3.cv1.bn.weight
model.17.m.3.cv1.bn.bias
model.17.m.3.cv1.bn.running_mean
model.17.m.3.cv1.bn.running_var
model.17.m.3.cv1.bn.num_batches_tracked
model.17.m.3.cv2.conv.weight
model.17.m.3.cv2.bn.weight
model.17.m.3.cv2.bn.bias
model.17.m.3.cv2.bn.running_mean
model.17.m.3.cv2.bn.running_var
model.17.m.3.cv2.bn.num_batches_tracked
model.18.conv.weight
model.18.bn.weight
model.18.bn.bias
model.18.bn.running_mean
model.18.bn.running_var
model.18.bn.num_batches_tracked
model.20.cv1.conv.weight
model.20.cv1.bn.weight
model.20.cv1.bn.bias
model.20.cv1.bn.running_mean
model.20.cv1.bn.running_var
model.20.cv1.bn.num_batches_tracked
model.20.cv2.conv.weight
model.20.cv2.bn.weight
model.20.cv2.bn.bias
model.20.cv2.bn.running_mean
model.20.cv2.bn.running_var
model.20.cv2.bn.num_batches_tracked
model.20.cv3.conv.weight
model.20.cv3.bn.weight
model.20.cv3.bn.bias
model.20.cv3.bn.running_mean
model.20.cv3.bn.running_var
model.20.cv3.bn.num_batches_tracked
model.20.m.0.cv1.conv.weight
model.20.m.0.cv1.bn.weight
model.20.m.0.cv1.bn.bias
model.20.m.0.cv1.bn.running_mean
model.20.m.0.cv1.bn.running_var
model.20.m.0.cv1.bn.num_batches_tracked
model.20.m.0.cv2.conv.weight
model.20.m.0.cv2.bn.weight
model.20.m.0.cv2.bn.bias
model.20.m.0.cv2.bn.running_mean
model.20.m.0.cv2.bn.running_var
model.20.m.0.cv2.bn.num_batches_tracked
model.20.m.1.cv1.conv.weight
model.20.m.1.cv1.bn.weight
model.20.m.1.cv1.bn.bias
model.20.m.1.cv1.bn.running_mean
model.20.m.1.cv1.bn.running_var
model.20.m.1.cv1.bn.num_batches_tracked
model.20.m.1.cv2.conv.weight
model.20.m.1.cv2.bn.weight
model.20.m.1.cv2.bn.bias
model.20.m.1.cv2.bn.running_mean
model.20.m.1.cv2.bn.running_var
model.20.m.1.cv2.bn.num_batches_tracked
model.20.m.2.cv1.conv.weight
model.20.m.2.cv1.bn.weight
model.20.m.2.cv1.bn.bias
model.20.m.2.cv1.bn.running_mean
model.20.m.2.cv1.bn.running_var
model.20.m.2.cv1.bn.num_batches_tracked
model.20.m.2.cv2.conv.weight
model.20.m.2.cv2.bn.weight
model.20.m.2.cv2.bn.bias
model.20.m.2.cv2.bn.running_mean
model.20.m.2.cv2.bn.running_var
model.20.m.2.cv2.bn.num_batches_tracked
model.20.m.3.cv1.conv.weight
model.20.m.3.cv1.bn.weight
model.20.m.3.cv1.bn.bias
model.20.m.3.cv1.bn.running_mean
model.20.m.3.cv1.bn.running_var
model.20.m.3.cv1.bn.num_batches_tracked
model.20.m.3.cv2.conv.weight
model.20.m.3.cv2.bn.weight
model.20.m.3.cv2.bn.bias
model.20.m.3.cv2.bn.running_mean
model.20.m.3.cv2.bn.running_var
model.20.m.3.cv2.bn.num_batches_tracked
model.21.conv.weight
model.21.bn.weight
model.21.bn.bias
model.21.bn.running_mean
model.21.bn.running_var
model.21.bn.num_batches_tracked
model.23.cv1.conv.weight
model.23.cv1.bn.weight
model.23.cv1.bn.bias
model.23.cv1.bn.running_mean
model.23.cv1.bn.running_var
model.23.cv1.bn.num_batches_tracked
model.23.cv2.conv.weight
model.23.cv2.bn.weight
model.23.cv2.bn.bias
model.23.cv2.bn.running_mean
model.23.cv2.bn.running_var
model.23.cv2.bn.num_batches_tracked
model.23.cv3.conv.weight
model.23.cv3.bn.weight
model.23.cv3.bn.bias
model.23.cv3.bn.running_mean
model.23.cv3.bn.running_var
model.23.cv3.bn.num_batches_tracked
model.23.m.0.cv1.conv.weight
model.23.m.0.cv1.bn.weight
model.23.m.0.cv1.bn.bias
model.23.m.0.cv1.bn.running_mean
model.23.m.0.cv1.bn.running_var
model.23.m.0.cv1.bn.num_batches_tracked
model.23.m.0.cv2.conv.weight
model.23.m.0.cv2.bn.weight
model.23.m.0.cv2.bn.bias
model.23.m.0.cv2.bn.running_mean
model.23.m.0.cv2.bn.running_var
model.23.m.0.cv2.bn.num_batches_tracked
model.23.m.1.cv1.conv.weight
model.23.m.1.cv1.bn.weight
model.23.m.1.cv1.bn.bias
model.23.m.1.cv1.bn.running_mean
model.23.m.1.cv1.bn.running_var
model.23.m.1.cv1.bn.num_batches_tracked
model.23.m.1.cv2.conv.weight
model.23.m.1.cv2.bn.weight
model.23.m.1.cv2.bn.bias
model.23.m.1.cv2.bn.running_mean
model.23.m.1.cv2.bn.running_var
model.23.m.1.cv2.bn.num_batches_tracked
model.23.m.2.cv1.conv.weight
model.23.m.2.cv1.bn.weight
model.23.m.2.cv1.bn.bias
model.23.m.2.cv1.bn.running_mean
model.23.m.2.cv1.bn.running_var
model.23.m.2.cv1.bn.num_batches_tracked
model.23.m.2.cv2.conv.weight
model.23.m.2.cv2.bn.weight
model.23.m.2.cv2.bn.bias
model.23.m.2.cv2.bn.running_mean
model.23.m.2.cv2.bn.running_var
model.23.m.2.cv2.bn.num_batches_tracked
model.23.m.3.cv1.conv.weight
model.23.m.3.cv1.bn.weight
model.23.m.3.cv1.bn.bias
model.23.m.3.cv1.bn.running_mean
model.23.m.3.cv1.bn.running_var
model.23.m.3.cv1.bn.num_batches_tracked
model.23.m.3.cv2.conv.weight
model.23.m.3.cv2.bn.weight
model.23.m.3.cv2.bn.bias
model.23.m.3.cv2.bn.running_mean
model.23.m.3.cv2.bn.running_var
model.23.m.3.cv2.bn.num_batches_tracked
model.24.anchors
model.24.anchor_grid
model.24.m.0.weight
model.24.m.0.bias
model.24.m.1.weight
model.24.m.1.bias
model.24.m.2.weight
model.24.m.2.bias
@baidingyuan baidingyuan changed the title 运行purne 过程中出现键值不对应的问题 运行prune 过程中出现键值不对应的问题 Dec 21, 2021
@huangzongmou
Copy link

用最新的配置文件

@baidingyuan
Copy link
Author

用最新的配置文件

我的文件应该都是最新的，请问您具体指的是什么文件呢？请问你有成功裁减x模型吗？

@midasklr
Copy link
Owner

midasklr commented Jan 3, 2022 •
edited
Loading

已经更新了,可以拉下最新代码试试,因为之前只是试了yolov5s,所以将

yolov5prune/prune.py

Lines 399 to 400 in 8a0eff3

pruned_yaml["depth_multiple"] = model_yamls["depth_multiple"]
pruned_yaml["width_multiple"] = model_yamls["width_multiple"]

写死了.
现在应该支持所有s-x和s6-x6模型了.

@baidingyuan
Copy link
Author

已经更新了,可以拉下最新代码试试,因为之前只是试了yolov5s,所以将

yolov5prune/prune.py

Lines 399 to 400 in 8a0eff3

pruned_yaml["depth_multiple"] = model_yamls["depth_multiple"]
pruned_yaml["width_multiple"] = model_yamls["width_multiple"]

写死了.
现在应该支持所有s-x和s6-x6模型了.

太感谢了，已经可以顺利裁剪了。

@xbw666
Copy link

xbw666 commented Oct 29, 2022

Traceback (most recent call last):
File "D:\projects\Pruned_Yolov5_DeepAI\prune.py", line 806, in
main(opt)
File "D:\projects\Pruned_Yolov5_DeepAI\prune.py", line 779, in main
run_prune(**vars(opt))
File "D:\Anaconda3\envs\yolov5\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "D:\projects\Pruned_Yolov5_DeepAI\prune.py", line 503, in run_prune
assert pruned_model_state.keys() == modelstate.keys()
AssertionError
对yolov5s进行稀疏训练，训练后进行prune操作的时候，出现了上述的错误

@huangzongmou
Copy link

huangzongmou commented Oct 29, 2022 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@huangzongmou @xbw666 @midasklr @baidingyuan