Nicolas Coudray

Hi - I get the same error and was wondering if there was any update/solution Thanks

Hi Mona, You can follow the example in: 
https://github.com/ncoudray/DeepPATH/tree/master/DeepPATH_code/example_TCGA_lung For mutations, we now favor binary classifications which are easier to deal with. Example at the end of this thread:
#37...

Hi - yes this is the list. All those which are not marked as "EGFR" are considered as non-EGFR in this list. Best, N.

Hi - The classifier and loss are done on a patch bases. So there is no aggregation done during the training. HTH, Best

Hi - The only reason why it's not implemented for svs is because we never needed it. Yes, you should just add mask.jpg and it should work. I don't have...

Hmhm.... what's the content of the output log file then?... Also, how are the masked? I think we expect them to be 8 bits with '0' for background and '255'...

Hi Lisa - The json file required here was the one downloaded from the legacy website. The format has changed since but the code has not been updated to deal...

Hi Wei, I am sorry but I don't have a fix for this right now. Not sure what's causing it. Are all the tiles saved? For the following steps (if...

Hi - The Model in Fig 1 just refers to trained version of the inception architecture.

Hi Mona - The average is just a simple average of all the probability for a given class. Above, if you just have 2 tiles, for class "0" average probability...