Marcelo Mendonca

Help for using the code in practice

2

Hi man, great job! I'm interested in using your code in my project, but although I'm used to the theory behind RNN's and specially GRU's, I'm not skilled enough for...

Understanding ssim

1

Hi man, great job! I'm trying to understand your code by following the paper. However I didn't get what is the purpose of SSIM class at all. Please, could you...

Hi, I have a question. How many iterations were needed to obtain J&F = 69.5 in training stage 1 with only MS-COCO? Thanks!

In train.py `main()` function, instead of `val_triplet_sampler = davis.TripletSampler(dataset=val_data_source, num_triplets=args.num_val_batches, randomize=True)` must be `val_triplet_sampler = davis.TripletSampler(dataset=val_data_source, num_triplets=args.val_batch_size, randomize=True)` to avoid throwing an exception due to incompatible tensor dimensions.