2000lf

RuntimeError: CUDA error: no kernel image is available for execution on the device

1

when I train raise `RuntimeError: CUDA error: no kernel image is available for execution on the device` **Environment** ``` sys.platform: linux Python: 3.7.16 (default, Jan 17 2023, 22:20:44) [GCC 11.2.0]...

I encountered an error when training the model with the Kitti dataset.

1

` File "/home/shiying/zjx/envs/anaconda3/envs/mmdet/lib/python3.8/site-packages/mmcv/utils/registry.py", line 61, in build_from_cfg raise KeyError( KeyError: 'KittiDataset is not in the dataset registry' `

I change the img_backbone swintransformer with Vim in bevfusion like this `from .models_mamba import vim_small_patch16_stride8_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2 as imb `` self.imb = vim_small_patch16_stride8_224_bimambav2_final_pool_mean_abs_pos_embed_with_midclstok_div2( pretrained=False)` `def extract_img_feat(` `self,` `x,` `points,` `lidar2image,` `camera_intrinsics,` `camera2lidar,`...

[Bug] nuscenes评估报错

3

### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmdetection3d/issues) and [Discussions](https://github.com/open-mmlab/mmdetection3d/discussions) but cannot get the expected help. - [X] I have read the [FAQ documentation](https://mmdetection3d.readthedocs.io/en/latest/notes/faq.html) but cannot get the expected help....

The reverse sampling results are not ideal

1

``` noise = torch.randn_like(im).to(device) t = torch.full((im.shape[0],), diffusion_config['num_timesteps']-1, device=device) #t = torch.randint(0, diffusion_config['num_timesteps'], (im.shape[0],)).to(device) xt = scheduler.add_noise(im, noise, t) for i in tqdm(reversed(range(diffusion_config['num_timesteps']))): # Get prediction of noise noise_pred =...

RuntimeError:CUDA out of memory

4

Can I remove the attention layer for high resolution img?