bryanlinnan

Model Size bigger than expect

4

Hi Kaiyang, I trained mobilenetv2 which should be about 12M size, but the output model "model.pth.tar-50" is about 40M, is this normal? the output model seems to contain more than...

Wonder why need to add config.subdivisions to the training process? could you please explain how does it work ?

why the batch size only support 1

RuntimeError: sigmoid_focal_loss_forward_impl: implementation for device cuda:0 not found

1

Follow the install instruction as : PyTorch 2.0 + CUDA 11.8 ``` conda create -n sparsebev python=3.8 conda activate sparsebev conda install pytorch==2.0.0 torchvision==0.15.0 pytorch-cuda=11.8 -c pytorch -c nvidia ```...

RuntimeError: Tensor on device meta is not on the expected device cuda:0!

7

Hi bro, During the "model.generate" in the script run_llava_mini.py, i met the error: RuntimeError: Tensor on device meta is not on the expected device cuda:0! btw CUDA is 11.6, GPU...