I just use the code of https://www.kaggle.com/paultimothymooney/starter-kernel-for-imagenet-a-adversarial-examples and load the model in the follow waynet = pvt_medium() checkpoint = torch.load("../input/pvt-medium/4f268100-d9ba-11eb-8129-547eacb8081d", map_location='cpu') if 'model' in checkpoint: msg = net.load_state_dict(checkpoint['model']) else: msg = net.load_state_dict(checkpoint) net.cuda() net.eval() the code and model of pvt is therehttps://github.com/whai362/PVT/tree/v2/classification.
I get the result pvt_medium Accuracy on ImageNet-A Dataset (%): 0.9333 Baseline RMS Calib Error (%): 51.24 AURRA (%): 0.96 As you can see, the result is very bad.
Is there anything wrong? could you help me to fix my mistake. Thanks very much.
1104662797
commented
2 years ago
I just use the code of
https://www.kaggle.com/paultimothymooney/starter-kernel-for-imagenet-a-adversarial-examplesand load the model in the follow waynet = pvt_medium() checkpoint = torch.load("../input/pvt-medium/4f268100-d9ba-11eb-8129-547eacb8081d", map_location='cpu') if 'model' in checkpoint: msg = net.load_state_dict(checkpoint['model']) else: msg = net.load_state_dict(checkpoint) net.cuda() net.eval()the code and model of pvt is therehttps://github.com/whai362/PVT/tree/v2/classification. I get the resultpvt_medium Accuracy on ImageNet-A Dataset (%): 0.9333 Baseline RMS Calib Error (%): 51.24 AURRA (%): 0.96As you can see, the result is very bad. Is there anything wrong? could you help me to fix my mistake. Thanks very much.