Open wangshankun opened 5 years ago
Can u speak English??
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
Can u speak English??
how to shown model structure? same to https://github.com/xingyizhou/CenterNet/issues/40
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 !
It's more convenient for you to study with the caffe prototxt of Centernet_res_18.
@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
No. Maybe you can try resnet18.load_state_dict(checkpoint["state_dict"]).
git上有一个netron的工具,可以在线查看主流框架的网络结构。
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?
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
I visualized ctdet_coco_dla_2x by directly modifying pytorch and centernet code.
I visualized ctdet_coco_dla_2x by directly modifying pytorch and centernet code.
Hi, which tool do you use to visualize it?
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.
I modified
torch/nn/modules/module.py
Specifically, I add some code inModule.__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 indot
format, and visualize it by graphviz.
@djshen Can you visiualize the hourglass?
@2018newyangyu https://i.imgur.com/0GVHoDU.png
@djshen sorry to interrupt, but I can't open this link even through a VPN, can you offer a new link?
@2018newyangyu
@lsccccc Sorry can not provide more help, I just used it to view the network map of yolo
@lsccccc Sorry can not provide more help, I just used it to view the network map of yolo
thank u anyway
I modified
torch/nn/modules/module.py
Specifically, I add some code inModule.__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 indot
format, and visualize it by graphviz.
can you show your code?
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!!! :)
@djshen Thanks for sharing the pics! I have a question about the nodes. What does P_weight_1 mean?(Sorry, I am newbee)
@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.
@djshen Thanks.I see that. P_weight_1 is the parameter of the first covolution layer.
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。