Closed rentainhe closed 2 years ago
Hi! I've test the CSwin-Tiny-224 released pretrained weight, this is my data transforms during testing:
DEFAULT_CROP_SIZE = 0.9 scale_size = int(math.floor(image_size / DEFAULT_CROP_SIZE)) transform = transforms.Compose( [ transforms.Resize(scale_size, interpolation=3) # 3: bibubic if image_size == 224 else transforms.Resize(image_size, interpolation=3), transforms.CenterCrop(image_size), transforms.ToTensor(), transforms.Normalize(IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD), ] )
I can only get 80.5% on imagenet2012 dataset which is inconsistent with the results as you mentioned in this repo, did I miss some details about the data-augmentation during testing?
Our code contains the test code, please refer to https://github.com/microsoft/CSWin-Transformer/blob/main/main.py and find the difference
Hi! I've test the CSwin-Tiny-224 released pretrained weight, this is my data transforms during testing:
I can only get 80.5% on imagenet2012 dataset which is inconsistent with the results as you mentioned in this repo, did I miss some details about the data-augmentation during testing?