e96031413

@Almostlover0608 Hi, I found that the train_baseline code did not calculate the best accuracy during training Thus, the output ```GG! best accuracy 0.000000``` appears in the output.

``` $ wget http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/CUB_200_2011.tgz --2021-01-24 09:14:33-- http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/CUB_200_2011.tgz Resolving www.vision.caltech.edu (www.vision.caltech.edu)... 34.208.54.77 Connecting to www.vision.caltech.edu (www.vision.caltech.edu)|34.208.54.77|:80... connected. HTTP request sent, awaiting response... 301 Moved Permanently Location: https://drive.google.com/file/d/1hbzc_P1FuxMkcabkgn9ZKinBwW683j45/view [following] --2021-01-24 09:14:33-- https://drive.google.com/file/d/1hbzc_P1FuxMkcabkgn9ZKinBwW683j45/view...

@hugovergnes Thanks for your suggestion, reduce the batch size works for me.

Thanks for your reply Unfortunately, the error still occurs. I also check the class TaskonomyLoader from taskonomy_loader.py. In line 45, I can understand that when I use the flag ```-d=/taskonomy/```,...

After removing '/', I type the command as below: ``` python3 train_taskonomy.py -d=taskonomy/ -a=xception_taskonomy_new -j 4 -b 64 -lr=.1 --fp16 -sbn --tasks=sdnerac -r ``` Same error again

Yes, there are more than one folder. ``` $ ls -l taskonomy total 8 drwxrwxrwx 1 root root 763196 Dec 19 12:11 class_object drwxrwxrwx 1 root root 763196 Dec 19...

@lerndeep Hi, do you solve the problem? I have the same question too.

I solve the issue by copy [comet/CUB/data/additional_transforms.py](https://github.com/snap-stanford/comet/blob/master/CUB/data/additional_transforms.py) to ```comet/TM/data/```

After execute the same command to train, I encounter the following error: ``` _________Gene count processed_________ mgi2go_set 24581 adata_set 2866 union 0 ./filelists/tabula_muris/go-basic.obo: fmt(1.2) rel(2018-10-24) 47,358 GO Terms Num filtered...

@manthanguptaa The issue still exists.