Hello,
I am trying to replicate some fastai vision results in Keras (work requirement). What would be the TensorFlow Keras layers equivalent to the the first three layers (0, 1, and 2) of the fastai head?
Here is the fastai head:
(0): AdaptiveAvgPool2d(output_size=1)
(1): AdaptiveMaxPool2d(output_size=1)
(2): Flatten()
(3): BatchNorm1d(3328, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(4): Dropout(p=0.25, inplace=False)
(5): Linear(in_features=3328, out_features=512, bias=True)
(6): ReLU(inplace=True)
(7): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(8): Dropout(p=0.5, inplace=False)
(9): Linear(in_features=512, out_features=2, bias=True)