Krishna Adithya V

I am trying to follow a person from the waist below. As shown in the video: https://drive.google.com/file/d/126XaDYGfX2VGzE8l8kg21cEQ4VuXrG9u/view?usp=sharing But I am guessing open pose will fail in this case

pip install git+https://github.com/minerllabs/minerl error

6

* What went wrong: * Execution failed for task ':compileJava'. * > Compilation failed; see the compiler error output for details. * Try: * Run with --stacktrace option to get...

from datasets import load_dataset ModuleNotFoundError: No module named 'datasets'

2

Traceback (most recent call last): File "train_text_to_image.py", line 17, in from datasets import load_dataset ModuleNotFoundError: No module named 'datasets' Traceback (most recent call last): File "/usr/local/bin/accelerate", line 8, in sys.exit(main())...

what gpu used to finetune the 2D model?

5

I treid finetuning the model on 24 gb vram GPU but it runs out of memory and only trains with batch size 2

actual shape : img : torch.Size([64, 256, 256, 3]) pred_mask : torch.Size([64, 1, 256, 256]) gt_mask; torch.Size([64, 1, 256, 256]) vis code shape : img : torch.Size([4, 256, 256, 256])...

how is num_class decided?

5

I saw few threads in the issues but I am still a bit confused with the class, so I am training the model to do vein segmentation and the mask...

train_learnable_sam.py : TypeError: to() received an invalid combination of arguments - got (detype=torch.dtype, )

1

line 176 train_learnable_sam.py "detype" needs to be changed to dtype