Different settings in random_sized_crop

[wjfwzzc]

In pycls, aspect_ratio are sampled uniformly in linear space:

pycls/pycls/datasets/transforms.py

Line 38 in 2c361ee

aspect_ratio = np.random.uniform(3.0 / 4.0, 4.0 / 3.0)

However in torchvision, aspect_ratio are sampled uniformly in log space:
https://github.com/pytorch/vision/blob/79ee22da44d43dabcc0fd30da2c914c5f04143eb/torchvision/transforms/transforms.py#L849-L854

So does timm:
https://github.com/rwightman/pytorch-image-models/blob/e8a64fb88108b592da192e98054095b1ee25e96e/timm/data/transforms.py#L106-L107

Seems that issue #123 reports the performance decrease. Could anyone check that?