Baran Nama comments

Results 42 comments of


                                            Baran Nama

loss computing in sample_validation_data

I have experimented on Ubuntu 16.04, never tried on Windows.

loss computing in sample_validation_data

@william-yan please check the issue https://github.com/quancore/social-lstm/issues/6

Bug in test.py

I think, you are right. Feel free to send a PR.

getting error while running train.py with different dataset of MOT17Det

Please double-check the data format you are trying is the exact same with the format in _data_ folder

Loss function computation

x_seq represents the observed part of a trajectory and y_seq is unknown part (will be predicted). During the training, we are using known (observed) part of a trajectory for the...

unsloth with vllm in 8/4 bits

@danielhanchen I think it is: https://github.com/vllm-project/vllm/issues/1155

unsloth with vllm in 8/4 bits

@patleeman @danielhanchen well yes, maybe we should support AWQ so we can use qlora models with vllm?

Are there any issues with anonymous polls right now?

I have also the issue today and I have given the feedback to the developer.

i unable get S3 bucket in former2

same here

i unable get S3 bucket in former2

@iann0036 thank you for the answer. The problem is that on S3 table, it says loading but it never gets loaded. I tried to re-scan and refresh the page but...