Open qinst64 opened 6 years ago
Yeah looks like Keras is right, good catch, fixing.
@jakebian Vgg16 is going great but when I use keras.applications.inception_v3
as the quiver input, the prediction is not as expected (quite bad).
Then I compared inception_v3.py and vgg16.py and find actually their preprocess_input
are different. On the other hand, I may or may not use imagenet_util.preprocess_input
for my own models.
I guess one solution is letting preprocess_input
be a paramerer of quiver_engine.server.launch
so one can apply custermized pre-processing.
in the quiver code
quiver_engine/imagenet_uitls.py
:in keras
keras/applications/imagenet_utils.py
:minus+transpose
andtranspose+minus
are apparently different, which leading prediction different results beween quiver vs. keras. However, I am not sure which of them is right.