Skip to content

torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 131064.51 GiB. GPU 0 has a total capacity of 80.00 GiB of which 57.64 GiB is free. #78

@Aristomir

Description

@Aristomir

I run:
CUDA_VISIBLE_DEVICES=0 python -m src.main +experiment=dl3dv
dataset.test_chunk_interval=1
dataset.roots=[datasets/dl3dv]
dataset.image_shape=[512,960]
dataset.ori_image_shape=[540,960]
model.encoder.upsample_factor=8
model.encoder.lowest_feature_resolution=8
model.encoder.gaussian_adapter.gaussian_scale_max=0.1
checkpointing.pretrained_model=pretrained/depthsplat-gs-small-re10kdl3dv-448x768-randview4-10-c08188db.pth
mode=test
dataset/view_sampler=evaluation
dataset.view_sampler.num_context_views=12
dataset.view_sampler.index_path=assets/dl3dv_start_0_distance_100_ctx_12v_video.json
test.save_video=true
test.stablize_camera=true
test.compute_scores=false
test.render_chunk_size=10
output_dir=outputs/depthsplat-dl3dv-512x960
displays torch.OutOfMemoryError: CUDA out of memory, but I have 80GB of VRAM

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions