Elhamahm

Selim_sef densenet161 input shape wrong in docs

12

Hello, I got the bug error “**RuntimeError: Given groups=1, weight of size 96 4 7 7, expected input[4, 3, 320, 320] to have 4 channels, but got 3 channels instead”...

If there is a way to continue training the model based on pre-trained model (saved weights)

1

I have trained the model for 25 epochs and saved the model. Now I intend to continue the training of model for 10 more epochs based on previously saved model...

Hello, For densenet161 model, when I use focal and dice loss functions, then it caused the following bug issue in training step. Any help and advise for solving this issue...

Execuation falis based on graph coarsening with SFDP_windows.exe

4

I executed harp coding on a windows OS and using sfdp_windows.exe, but it failed. Since subprocess.call function that applies graph_coarsening based on sfdp_windows.exe returns a non-zero value.

Hi, I could run the Harp using LINE as the underlying network embedding model, but it fails when using deepwalk embedding model. I have attached a schema of both runs...