Ofri Masad

Results 18 comments of Ofri Masad

May I ask which dataset are you training on?

can you please send me the Adobe dataset. The author is not answering emails. Thanks in advance. [email protected]

Default dataloader params have shuffle=False

fixed in PR https://github.com/Deci-AI/super-gradients/pull/581 version 3.0.4

Is there support for 2 channel and 4 channel training

Hi @ajithkumarmcw . It seems like we have a bug in not passing the in_channel parameter on instantiation. a ticket was opened, and this will be fixed in the coming...

Feature/sg 000 no explicit pil

just remember that many users are installing SG and then installing PyTorch again (because of CUDA compatibility). So the version of pillow defined in torch will run-over our version.

AttributeError: module 'signal' has no attribute 'SIGKILL'. Did you mean: 'SIGILL'?

Hi @ngocnd2402. This is a general error of Python on Windows. We do not support Windows officially, but if you provide some more information, perhaps we could help. Could you...

Error in building wheels

Hi @soumyadbanik . Does this happen on building wheels or on `pip install super-gradients` ? Can you provide some environment details? OS, Conda (?), python version, installed packages Thanks

Invalid version: '8.3.*'

@MetehanYasar11 can your check the version of setuptools you have? `pip list | grep setuptools`

Weights & Biases initialization should be decoupled from the Logger

@soumik12345 I am afraid it is a bit more complicated... For example, assume that you want to resume a training run, how can the logger know that the run is...

YOLO-NAS L fails to detect small objects

I think it is just the video you chose. You see, the model is predicting in 640x640 (you can train it on higher resolution, of course). In our example, the...

Update Weights & Biases Integration + Add Prediction Visualization for Object Detection

Thank you for the code contribution @soumik12345. :) I apologize for the delayed review.