Yilin Yang

报错，无法运行

4

Traceback (most recent call last): File "D:/Undergradute/project/Multi-view battleplane detection based on Machine learning/crawlers/google_Image/main.py", line 194, in main() File "D:/Undergradute/project/Multi-view battleplane detection based on Machine learning/crawlers/google_Image/main.py", line 183, in main download(should_path)...

Can't train the model. ModuleNotFoundError: No module named 'sparse_image_warp'

1

Traceback (most recent call last): File "tools/run_net.py", line 6, in from slowfast.utils.misc import launch_job File "/root/auditory-slow-fast/slowfast/utils/misc.py", line 20, in from slowfast.datasets.utils import pack_pathway_output File "/root/auditory-slow-fast/slowfast/datasets/__init__.py", line 5, in from .epickitchens...

Default process group has not been initialized

4

2024-10-04 22:58:25,605 semantic_segmentation INFO: Using 1 GPUs 2024-10-04 22:58:25,605 semantic_segmentation INFO: Namespace(aux=True, batch_size=16, contrast_kd_temperature=1.0, contrast_temperature=0.1, crop_size=[360, 360], data='../autodl-tmp/CamVid/CamVid', dataset='camvid', device='cuda', distributed=False, ignore_label=-1, kd_temperature=1.0, lambda_kd=1.0, lambda_memory_pixel=0.1, lambda_memory_region=0.1, lambda_minibatch_pixel=1.0, local_rank=0, log_dir='../autodl-tmp/CamVid/log', log_iter=10,...

Hi! I revisited the code. I think there might be something that can be refined here. As for the dtw function, when two or all of option_diag, option_up and option_left...

Hi! I was wondering since the LLM predict the next token, why would you use the first input_token in token alignment and get the aligned_logit and index? It seems that...

Hi! According to the paper, it seems that we should use per_step_index with highest logit to do minimal editing distance. However, in the code, you directly used input_ids, which might...