Closed maxkohlbrenner closed 5 years ago
@maxkohlbrenner,
I will share my inference codes in the near future. Key recipes for ImageNet are the following:
cv2.resize(img, (h, w), interpolation=cv2.INTER_CUBIC)
,
while the keras default is img.resize((w, h), pil_image.NEAREST)
.
You can try pil_image.BICUBIC
or opencv2 like me.Thank you very much @taehoonlee! This solved my problem.
Hi, according to https://keras.io/applications/#vgg16, the vgg16 pre-trained model has a validation top-1 accuracy of 71.3%. I deployed the network with the given weights and preprocessing function and arrived at a top-1 accuracy of 64.2% on the ilsvrc12 validation set. Can anyone confirm the reported accuracy of the pre-trained network?
Thank you very much for your help! Cheers, Max