DIM
DIM copied to clipboard
rdevon
Deep InfoMax (DIM), or "Learning Deep Representations by Mutual Information Estimation and Maximization"
Hello, I don't have a pure math background and I've tried to make my own naive implemenation of DIM where the "discriminator" is just a standard binary crossentropy sigmoid classifier...
Hi, I was looking through your code, namely here: [https://github.com/rdevon/DIM/blob/bac4765a8126746675f517c7bfa1b04b88044d51/cortex_DIM/functions/dim_losses.py#L109](here) and noticed that in the docstring it states that the losses take the feature maps l and m directly. However,...
Thank you for sharing your code. I'm happy to try this seemingly attractive representation learning idea on a different backbone. e.g. ResNet50. Gladly, you mentioned ResNet50 on Table3 in your...
First of I really appreciate you for your git page Second, how can I use resent arch but not it's wight? you know in contrast of other works accuracy (like...
Hello, thanks for your great paper and codes! How can I select the "Concat-and-convolve architecture" for maximizing local MI?
Hi, when I load .t7 file, I can see 4 nets as dict in variable. 'Controller.encoder' 'conv[2](256,4,4).classifier' 'fc[4](1024,).classifier' 'glob[-1](64,).classifier' what is the role of each net in code? which one...
Hi, thank you for your interesting work and releasing the code! Would you kindly release the code bout > training a generator by matching to a prior implicitly ? Thanks...
In Figure 4: Scatter plots of MI(x; y) versus JSD(p(x, y)||p(x)p(y)), what is the formula/function used to compute the MI(x; y)?
Hello author, I have been wondering what 'data.images' is. Lead to "file "/home/hexing/anaconda3/envs/02_dim_torch040/lib/python3.6/site-packages/cortex/_lib/models.py", line 348, in _check_contract for k, v in inputs.items(): AttributeError: 'str' object has no attribute 'items'
