怎么得到网络结构？

[wangshankun]

不是项目本身问题，学习时候遇到问题；不知道大家遇到过没有，我用torch.save保存的模型，用netron打开没有结构化显示。ctdet_coco_dla_1x.pth本身也只有weight，更无法查看结构了，不知道有什么好的方法可以看到网络结构。

[YU-FAITH]

Can u speak English？？

[Sundrops]

Here is the caffe prototxt of Centernet_dlav0_34. If you want to get caffe prototxts of Centernet with other backbones, you can convert the pytorch model to caffe model via PytorchToCaffe

[wangshankun]

Can u speak English？？

how to shown model structure? same to https://github.com/xingyizhou/CenterNet/issues/40

[wangshankun]

Here is the caffe prototxt of Centernet_dlav0_34. If you want to get caffe prototxts of Centernet with other backbones, you can convert the pytorch model to caffe model via PytorchToCaffe

Thanks for your effort ！

[Sundrops]

It's more convenient for you to study with the caffe prototxt of Centernet_res_18.

[Tim5Tang]

@Sundrops i use the PytorchToCaffe to convert the Centernet but failed, did you have the fallow question Traceback (most recent call last): File "example/resnet_pytorch_2_caffe.py", line 13, in resnet18.load_state_dict(checkpoint) File "/home/*/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 719, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for ResNet: Missing key(s) in state_dict: "conv1.weight", "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "layer1.0.conv1.weight", "layer1.0.bn1.weight", "layer1.0.bn1.bias", "layer1.0.bn1.running_mean", "layer1.0.bn1.running_var", "layer1.0.conv2.weight", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.1.conv1.weight", "layer1.1.bn1.weight", "layer1.1.bn1.bias", "layer1.1.bn1.running_mean", "layer1.1.bn1.running_var", "layer1.1.conv2.weight", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.1.bn2.running_mean", "layer1.1.bn2.running_var", "layer2.0.conv1.weight", "layer2.0.bn1.weight", "layer2.0.bn1.bias", "layer2.0.bn1.running_mean", "layer2.0.bn1.running_var", "layer2.0.conv2.weight", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.0.downsample.0.weight", "layer2.0.downsample.1.weight", "layer2.0.downsample.1.bias", "layer2.0.downsample.1.running_mean", "layer2.0.downsample.1.running_var", "layer2.1.conv1.weight", "layer2.1.bn1.weight", "layer2.1.bn1.bias", "layer2.1.bn1.running_mean", "layer2.1.bn1.running_var", "layer2.1.conv2.weight", "layer2.1.bn2.weight", "layer2.1.bn2.bias", "layer2.1.bn2.running_mean", "layer2.1.bn2.running_var", "layer3.0.conv1.weight", "layer3.0.bn1.weight", "layer3.0.bn1.bias", "layer3.0.bn1.running_mean", "layer3.0.bn1.running_var", "layer3.0.conv2.weight", "layer3.0.bn2.weight", "layer3.0.bn2.bias", "layer3.0.bn2.running_mean", "layer3.0.bn2.running_var", "layer3.0.downsample.0.weight", "layer3.0.downsample.1.weight", "layer3.0.downsample.1.bias", "layer3.0.downsample.1.running_mean", "layer3.0.downsample.1.running_var", "layer3.1.conv1.weight", "layer3.1.bn1.weight", "layer3.1.bn1.bias", "layer3.1.bn1.running_mean", "layer3.1.bn1.running_var", "layer3.1.conv2.weight", "layer3.1.bn2.weight", "layer3.1.bn2.bias", "layer3.1.bn2.running_mean", "layer3.1.bn2.running_var", "layer4.0.conv1.weight", "layer4.0.bn1.weight", "layer4.0.bn1.bias", "layer4.0.bn1.running_mean", "layer4.0.bn1.running_var", "layer4.0.conv2.weight", "layer4.0.bn2.weight", "layer4.0.bn2.bias", "layer4.0.bn2.running_mean", "layer4.0.bn2.running_var", "layer4.0.downsample.0.weight", "layer4.0.downsample.1.weight", "layer4.0.downsample.1.bias", "layer4.0.downsample.1.running_mean", "layer4.0.downsample.1.running_var", "layer4.1.conv1.weight", "layer4.1.bn1.weight", "layer4.1.bn1.bias", "layer4.1.bn1.running_mean", "layer4.1.bn1.running_var", "layer4.1.conv2.weight", "layer4.1.bn2.weight", "layer4.1.bn2.bias", "layer4.1.bn2.running_mean", "layer4.1.bn2.running_var", "fc.weight", "fc.bias". Unexpected key(s) in state_dict: "epoch", "state_dict".

[Sundrops]

No. Maybe you can try resnet18.load_state_dict(checkpoint["state_dict"]).

[monoloxo]

git上有一个netron的工具，可以在线查看主流框架的网络结构。

[XzlXcc]

git上有一个netron的工具，可以在线查看主流框架的网络结构。

Have you visualized it through the tool?

[wangshankun]

git上有一个netron的工具，可以在线查看主流框架的网络结构。

最开始就是用netron了 ctdet_coco_dla_1x.pth在torchsummary、tensorboardX、make_dot、Netron都没办法正常显示，最多显示一部分node

[djshen]

I visualized ctdet_coco_dla_2x by directly modifying pytorch and centernet code.

[XzlXcc]

I visualized ctdet_coco_dla_2x by directly modifying pytorch and centernet code.

Hi, which tool do you use to visualize it?

[djshen]

I modified torch/nn/modules/module.py Specifically, I add some code in Module.__call__ function to trace the inputs and outputs of the modules (store each of the tensors or modules and give it a unique name). Then I print the connections between inputs and modules in dot format, and visualize it by graphviz.

[2018newyangyu]

I modified torch/nn/modules/module.py Specifically, I add some code in Module.__call__ function to trace the inputs and outputs of the modules (store each of the tensors or modules and give it a unique name). Then I print the connections between inputs and modules in dot format, and visualize it by graphviz.

@djshen Can you visiualize the hourglass?

[djshen]

@2018newyangyu https://i.imgur.com/0GVHoDU.png

[JacobYuan7]

@djshen sorry to interrupt, but I can't open this link even through a VPN, can you offer a new link?

[djshen]

@2018newyangyu

Click


[monoloxo]

@lsccccc Sorry can not provide more help, I just used it to view the network map of yolo

[liukaigua]

@lsccccc Sorry can not provide more help, I just used it to view the network map of yolo

thank u anyway

[zjp99]

I modified torch/nn/modules/module.py Specifically, I add some code in Module.__call__ function to trace the inputs and outputs of the modules (store each of the tensors or modules and give it a unique name). Then I print the connections between inputs and modules in dot format, and visualize it by graphviz.

can you show your code?

[clemente0731]

Here is the caffe prototxt of Centernet_dlav0_34. If you want to get caffe prototxts of Centernet with other backbones, you can convert the pytorch model to caffe model via PytorchToCaffe

THANKS FOR YOUR JOB!!! :)

[Vankeee]

@djshen Thanks for sharing the pics! I have a question about the nodes. What does P_weight_1 mean?(Sorry, I am newbee)

[djshen]

@djshen Thanks for sharing the pics! I have a question about the nodes. What does P_weight_1 mean?(Sorry, I am newbee)

In this graph, the node name starting with "P_" is a parameter and is passed to the corresponding operation such as a convolution.

[Vankeee]

@djshen Thanks.I see that. P_weight_1 is the parameter of the first covolution layer.