Vaishnavi Khindkar

Can anyone please provide any link to download processed data for BDD100k for day time settings as required here? Thanks, Vaishnavi Khindkar

Hi, Thank you so much for this repo!! It's amazing and very useful. Can you please help me understand the parameter transformer_depth? And what is the difference between num_heads and...

Hi @shinh I am facing below error in multiprocessing.pool , while training segnet - ==================== [mpiexec@vaish-GS65-Stealth-Thin-8RE] match_arg (utils/args/args.c:163): unrecognized argument x [mpiexec@vaish-GS65-Stealth-Thin-8RE] HYDU_parse_array (utils/args/args.c:178): argument matching returned error [mpiexec@vaish-GS65-Stealth-Thin-8RE] parse_args...

Can you please provide this bottleneck_features/DogResnet50Data.npz ? Thanks, Vaishnavi

Issue while loading the model using TIS (Triton Inference Server) : For the model to support batching the shape should have at least 1 dimension and the first dimension must be -1

2

**I have exported code using following format:** torch.onnx.export(crnn.module, # use .module to unwrap the model example_input, # model input (or a tuple for multiple inputs) "bhaasha_model.onnx", # where to save...