RuntimeError: CUDA out of memory.

[jmwang0117]

RuntimeError: CUDA out of memory. Tried to allocate 360.00 MiB (GPU 0; 10.76 GiB total capacity; 6.21 GiB already allocated; 200.56 MiB free; 6.76 GiB reserved in total by PyTorch)

I use my data but produce some problems, I don't know how to solve this problem,please help me? I use 2080Ti

[dunbar12138]

You can reduce the batch size (N_rand) or the chunk size in the config file to fit in a GPU with small memory.

[jmwang0117]

I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued. My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)

[Yuchen-Song]

I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued. My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)

@jmwang0117 Have you fixed that problem?

[Seagullflysxt]

I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued. My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)

Hi,could I ask what pytorch version you use? Did you modified any code from the original repo?I use the version 1.7.0,but encounterd problem every time I reached to 4999iters

[jmwang0117]

I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued. My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)

Hi,could I ask what pytorch version you use? Did you modified any code from the original repo?I use the version 1.7.0,but encounterd problem every time I reached to 4999iters

Block code that generates video

[jmwang0117]

I found that after completing the first 10,000 training sessions, the mp4 video will be rendered first, and then the training will be continued. My problem is that there is not enough memory when rendering to generate mp4 video (eg: fern_2v_spiral_010000_disp.mp4). Is this step of generating video necessary? Can I complete the training first, and then render (--render_only)

@jmwang0117 Have you fixed that problem?

Block code that generates video