hammad001

Results 4 issues of hammad001

I am using the two trained generators provided in the repository. Yet, the generated images are way blurrier than the one in the DCGAN paper. Anything I am doing wrong?...

For rationale mode, the repository provides code for calculating Question and correct answer pairs BERT embeddings only for train and validation set. While for test set, embeddings are calculated for...

Include tf placeholders rather than constants for calculating bert embeddings. Otherwise, it violates the tensorflow's 2GB protocol. fixes #15

While fine tuning VCR task in Distributed Data Parallel mode, it hangs when loading model to gpu.