Open lagejoao opened 4 years ago
@tanzhenyu I've realised you changed some logic quite recently https://github.com/keras-team/keras-applications/commit/e52c477a9ccb86b4c7bef7569d59f0c0b2e01cb6. Any input here?
Yep I think it should be other way around, I will make a change
I'll do it, then. Ok for you?
Sure, thanks
When preprocessing an image using a
tf.Tensor
and anp.array
I get different behaviours for the same representation.When casting the numpy output to type
uint8
we will get a closer representation to the symbolic output.I see a possible issue on https://github.com/keras-team/keras-applications/blob/master/keras_applications/imagenet_utils.py#L143 where there's a cast on the wrong tensor. Shouldn't it be
instead of casting the
mean_tensor
asuint8
with the following