leelabcnbc / cnnvis-pytorch Goto Github PK

View Code? Open in Web Editor NEW

154.0 154.0 19.0 14.41 MB

visualization of CNN in PyTorch

Jupyter Notebook 99.89% Python 0.11%

cnnvis-pytorch's People

Contributors

Stargazers

Watchers

Forkers

ciaua benjamesbabala zmoon111 jianweilin mishraanup kevinlemon ivjia sibylfiresoul muzi-8 shiguang2017 farlandliu oracle1983 ocean1100 psavine42 yuleichin barbecacov vandbt vanellope0602 adrien-dorise

cnnvis-pytorch's Issues

https://github.com/leelabcnbc/cnnvis-pytorch

code:

so, forward one time, and backward multiple times.

vis_param_dict['layer'] = 'classifier.6'
vis_param_dict['method'] = util.GradType.NAIVE

which one coresponds

this is the max one. I assume it's the correct one.

indeed, it's correct.

55 is n01729977, corresponding to "green snake, grass snake".

vis_param_dict['index'] = 55

alexnet gives 64, which is n01749939, or green mamba. not sure which one is correct.

loss.backward(retain_variables=True)
error:

TypeError Traceback (most recent call last)
in ()
8 vis_param_dict['index'] = 55
9 # alexnet gives 64, which is n01749939, or green mamba. not sure which one is correct.
---> 10 loss.backward(retain_variables=True)

TypeError: backward() got an unexpected keyword argument 'retain_variables'

code:

Some question about use in Py3.5

The repo is awesome and useful, but when I try to use it in my own project wrote in py3.5, which get some errors like below:

----> 3 from enum import Enum, auto
      4 from functools import partial
      5 

ImportError: cannot import name 'auto'

The auto is unique in py3.6 and don't contain in py3.5, how can I change the code to let it work?

Looking for your help

leelabcnbc / cnnvis-pytorch Goto Github PK

cnnvis-pytorch's People

Contributors

Stargazers

Watchers

Forkers

cnnvis-pytorch's Issues

https://github.com/leelabcnbc/cnnvis-pytorch

so, forward one time, and backward multiple times.

which one coresponds

this is the max one. I assume it's the correct one.

indeed, it's correct.

55 is n01729977, corresponding to "green snake, grass snake".

alexnet gives 64, which is n01749939, or green mamba. not sure which one is correct.

code:

Some question about use in Py3.5

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent