aaditya prakash

This is because the pre-trained model already existing in the repo was trained on the older version of Keras. It is best to train your model, however to save computation...

Check the dev branch On Mon, Jul 11, 2022, 7:25 AM jsnumss ***@***.***> wrote: > May I ask why the code is missing? > > — > Reply to this...

1. skimage and scikit-image are same libraries. 2. Looks like you have very old version of skimage. What is the output of this command: ```bash python -c 'import skimage; print(skimage.__version__)'...

From the error, it looks like that your input (x) is not of the same size. Most of the networks train a single batch at a fixed size. Check the...

They are different networks. You can use interchangeably use the weights. Change the network structure in VQA_DEMO to match the network as you trained from this repo.

Squeeze your input so that this (1L, 26L, 300L) becomes (26L, 300L). See this: https://numpy.org/doc/stable/reference/generated/numpy.squeeze.html

If one of them doesn't have the embedding layer then remove it from the other one. I don't remember the specifics of the network but definitely, you want it to...

Yes; they are totally different and meant for different purposes. There are plenty of codebases for training VQA that are more recent, maintained, and compatible with the latest libraries. I...

I have updated the link. Try now. Thanks and Regards Adi On Wed, Sep 22, 2021 at 3:04 PM Aryan Gupta ***@***.***> wrote: > The download link is broken while...

Yes, you are right `img_norm` is defined here https://github.com/iamaaditya/VQA_Keras/blob/d6999208fa52d6259f98518027d99d813e05bb12/utils/get_data.py#L53 Image normalization is required because the CNN (VGG16) was trained with normalized images. Thus, in order to get the maximum benefit...