search

SuperMedIntel / Medical-SAM-Adapter

Adapting Segment Anything Model for Medical Image Segmentation
GNU General Public License v3.0
1.02k stars 90 forks source link

Error in validation, Shape mismatch, can't divide axis of length X in chunks of Y #126

Open rafiibnsultan opened 2 months ago

rafiibnsultan commented 2 months ago

Although there is no issue in training, but in validation stage I always get this type of error for BTCV dataset, on default processing:

Traceback (most recent call last): File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/transform.py", line 141, in apply_transform return _apply_transform(transform, data, unpack_items, lazy, overrides, log_stats) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/transform.py", line 98, in _apply_transform return transform(data, lazy=lazy) if isinstance(transform, LazyTrait) else transform(data) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/io/dictionary.py", line 164, in call data = self._loader(d[key], reader) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/io/array.py", line 302, in call img = EnsureChannelFirst()(img) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/utility/array.py", line 204, in call raise ValueError(msg) ValueError: Metadata not available and channel_dim=None, EnsureChannelFirst is not in use.

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/transform.py", line 141, in apply_transform return _apply_transform(transform, data, unpack_items, lazy, overrides, log_stats) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/transform.py", line 98, in _apply_transform return transform(data, lazy=lazy) if isinstance(transform, LazyTrait) else transform(data) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/compose.py", line 322, in call result = execute_compose( File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/compose.py", line 111, in execute_compose data = apply_transform( File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/transform.py", line 171, in apply_transform raise RuntimeError(f"applying transform {transform}") from e RuntimeError: applying transform <monai.transforms.io.dictionary.LoadImaged object at 0x7feb3cdd5d90>

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "/home/hm4013/.conda/envs/mul2/lib/python3.9/threading.py", line 980, in _bootstrap_inner self.run() File "/home/hm4013/.conda/envs/mul2/lib/python3.9/threading.py", line 917, in run self._target(*self._args, **self._kwargs) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/data/thread_buffer.py", line 49, in enqueue_values for src_val in self.src: File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 630, in next data = self._next_data() File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 673, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 52, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/data/dataset.py", line 109, in getitem return self._transform(index) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/data/dataset.py", line 908, in _transform return super()._transform(index) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/data/dataset.py", line 95, in _transform return apply_transform(self.transform, data_i) if self.transform is not None else data_i File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/monai/transforms/transform.py", line 171, in apply_transform raise RuntimeError(f"applying transform {transform}") from e RuntimeError: applying transform <monai.transforms.compose.Compose object at 0x7feb3cdd5700> Traceback (most recent call last):
File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/einops/einops.py", line 523, in reduce return _apply_recipe( File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/einops/einops.py", line 234, in _apply_recipe init_shapes, axes_reordering, reduced_axes, added_axes, final_shapes, n_axes_w_added = _reconstruct_from_shape( File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/einops/einops.py", line 187, in _reconstruct_from_shape_uncached raise EinopsError(f"Shape mismatch, can't divide axis of length {length} in chunks of {known_product}") einops.EinopsError: Shape mismatch, can't divide axis of length 311 in chunks of 96

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/hm4013/Medical-SAM-Adapter/val.py", line 102, in main() File "/home/hm4013/Medical-SAM-Adapter/val.py", line 94, in main tol, (eiou, edice) = function.validation_sam(args, nice_test_loader, start_epoch, net) File "/home/hm4013/Medical-SAM-Adapter/function.py", line 306, in validation_sam imge= net.image_encoder(imgs) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl return forward_call(*args, *kwargs) File "/home/hm4013/Medical-SAM-Adapter/models/sam/modeling/image_encoder.py", line 134, in forward x = blk(x) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl return self._call_impl(args, kwargs) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl return forward_call(*args, kwargs) File "/home/hm4013/Medical-SAM-Adapter/models/ImageEncoder/vit/adapter_block.py", line 87, in forward xd = rearrange(x, '(b d) h w c -> (b h w) d c ', d=depth) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/einops/einops.py", line 591, in rearrange return reduce(tensor, pattern, reduction="rearrange", axes_lengths) File "/home/hm4013/.conda/envs/mul2/lib/python3.9/site-packages/einops/einops.py", line 533, in reduce raise EinopsError(message + "\n {}".format(e)) einops.EinopsError: Error while processing rearrange-reduction pattern "(b d) h w c -> (b h w) d c ". Input tensor shape: torch.Size([311, 14, 14, 768]). Additional info: {'d': 96}. Shape mismatch, can't divide axis of length 311 in chunks of 96