Amiri
Amiri
 I used RN50 backbone and also got the strange result , but when evaluating the Cross-dataset , the result is the same as the paper.
@zhangletian2 do u solve the issue?
@azshue Thank you for reply. I evaluated the caltech101 and UCF101, they all got the same accuracy as the paper, but when evalutaing the Imagenet-adversial and Imagenet-rendition, i will get...
That's my tpt.sh , I use the default setting. ```sh #!/bin/bash data_root='/workspace/CaFo/data' testsets=$1 arch=RN50 # arch=ViT-B/16 bs=64 ctx_init=a_photo_of_a python ./tpt_classification.py ${data_root} --test_sets ${testsets} \ -a ${arch} -b ${bs} --gpu 0...
I think it is running as expected , i print the classname to check whether it is right , and it only has 200 classes in ImageNet-A and ImageNet-R. ```python...
Thanks, i will check it in my code
you should translate the way claude use computer tool to osworld format