Nidacoke
commented
1 year ago Open cjf-repo opened 1 year ago
Nidacoke
commented
1 year ago 
gukehan2000
commented
1 year ago 我也是 而且特别吃显存 就这个图10000多MB显存 请问知道怎么改呢
gukehan2000
commented
1 year ago 我也是 而且特别吃显存 就这个图10000多MB显存 请问知道怎么改呢
home/anaconda3/envs/github-2/lib/python3.8/site-packages/transformers/modeling_utils.py:862: FutureWarning: The device argument is deprecated and will be removed in v5 of Transformers.
warnings.warn(
/home/anaconda3/envs/github-2/lib/python3.8/site-packages/torch/utils/checkpoint.py:25: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
Traceback (most recent call last):
File "/home/naconda3/envs/github-2/lib/python3.8/site-packages/gradio/routes.py", line 401, in run_predict
output = await app.get_blocks().process_api(
File "/home/anaconda3/envs/github-2/lib/python3.8/site-packages/gradio/blocks.py", line 1302, in process_api
result = await self.call_function(
File "/home/anaconda3/envs/github-2/lib/python3.8/site-packages/gradio/blocks.py", line 1025, in call_function
prediction = await anyio.to_thread.run_sync(
File "/home/anaconda3/envs/github-2/lib/python3.8/site-packages/anyio/to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/home/anaconda3/envs/github-2/lib/python3.8/site-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "/home/naconda3/envs/github-2/lib/python3.8/site-packages/anyio/_backends/_asyncio.py", line 867, in run
result = context.run(func, args)
File "/home/MyProject/Grounded-Segment-Anything-main/gradio_app.py", line 286, in run_groundedsam
masks, , _ = sam_predictor.predict_torch(
File "/home/anaconda3/envs/github-2/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(args, *kwargs)
File "/home/MyProject/Grounded-Segment-Anything-main/segment_anything/segment_anything/predictor.py", line 229, in predict_torch
low_res_masks, iou_predictions = self.model.mask_decoder(
File "/home/gukehan/anaconda3/envs/github-2/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(input, *kwargs)
File "/home/MyProject/Grounded-Segment-Anything-main/segment_anything/segment_anything/modeling/mask_decoder.py", line 94, in forward
masks, iou_pred = self.predict_masks(
File "/home/MyProject/Grounded-Segment-Anything-main/segment_anything/segment_anything/modeling/mask_decoder.py", line 144, in predict_masks
masks = (hyper_in @ upscaled_embedding.view(b, c, h w)).view(b, -1, h, w)
RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1, 256, 256] because the unspecified dimension size -1 can be any value and is ambiguous
lijain
commented
1 year ago +1
Dratlan
commented
1 year ago +1
wanghao-cst
commented
1 year ago I got the same issue: RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1, 256, 256] because the unspecified dimension size -1 can be any value and is ambiguous
chenminupup
commented
1 year ago I got the same issue: RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1, 256, 256] because the unspecified dimension size -1 can be any value and is ambiguous
I got the same issue，can you solve it now?
piclez
commented
2 months ago
运行的gradio_app.py选择seg的时候（其他的也一样），这里到5s左右就直接显示error，但是代码是没有报错，并且运行到了最后的return [image, mask_pil]这一步，而单独运行grounded_sam_demo.py是可以出来结果的，是我哪里需要修改吗，网页上没有显示出结果