IndexError: list index out of range #1182

RadiantJeral · 2019-12-10T03:38:19Z

🐛 Bug

Traceback (most recent call last):
File "/home/lucifer/LibSrcs/pycharm-community-2018.3.2/helpers/pydev/pydevd.py", line 1741, in
main()
File "/home/lucifer/LibSrcs/pycharm-community-2018.3.2/helpers/pydev/pydevd.py", line 1735, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "/home/lucifer/LibSrcs/pycharm-community-2018.3.2/helpers/pydev/pydevd.py", line 1135, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/lucifer/LibSrcs/pycharm-community-2018.3.2/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/my_run/run_local/e2e_faster_rcnn_R_50_C4_1x/train_net_e2e_faster_rcnn_R_50_C4_1x.py", line 201, in
main()
File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/my_run/run_local/e2e_faster_rcnn_R_50_C4_1x/train_net_e2e_faster_rcnn_R_50_C4_1x.py", line 194, in main
model = train(cfg, args.local_rank, args.distributed)
File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/my_run/run_local/e2e_faster_rcnn_R_50_C4_1x/train_net_e2e_faster_rcnn_R_50_C4_1x.py", line 94, in train
arguments,
File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/engine/trainer.py", line 72, in do_train
for iteration, (images, targets, _) in enumerate(data_loader, start_iter):
File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 537, in next
return self._process_next_batch(batch)
File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 577, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
IndexError: Traceback (most recent call last):
File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/dataset.py", line 85, in getitem
return self.datasets[dataset_idx][sample_idx]
File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/data/datasets/coco.py", line 94, in getitem
target = target.clip_to_image(remove_empty=True)
File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/structures/bounding_box.py", line 223, in clip_to_image
return self[keep]
File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/structures/bounding_box.py", line 208, in getitem
bbox.add_field(k, v[item])
File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/structures/segmentation_mask.py", line 555, in getitem
selected_instances = self.instances.getitem(item)
File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/structures/segmentation_mask.py", line 464, in getitem
selected_polygons.append(self.polygons[i])
IndexError: list index out of range

To Reproduce

reproducible code:

from maskrcnn_benchmark.config import cfg
from maskrcnn_benchmark.data.build import make_data_loader


config_path = '/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/my_run/run_local/' \
              'e2e_faster_rcnn_R_50_C4_1x/e2e_faster_rcnn_R_50_C4_1x.yaml'
cfg.merge_from_file(config_path)
dl = make_data_loader(cfg)

for iteration, (images, targets) in enumerate(dl):
    print(iteration)

Dataset [ConcatDataset] has no categories attribute, labels.json file won't be created
Traceback (most recent call last):
  File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 3319, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-173e8ccc2b92>", line 1, in <module>
    runfile('/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/my_code/dev/02_debugs/debug_dataloader.py', wdir='/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/my_code/dev/02_debugs')
  File "/home/lucifer/LibSrcs/pycharm-community-2018.3.2/helpers/pydev/_pydev_bundle/pydev_umd.py", line 198, in runfile
    pydev_imports.execfile(filename, global_vars, local_vars)  # execute the script
  File "/home/lucifer/LibSrcs/pycharm-community-2018.3.2/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/my_code/dev/02_debugs/debug_dataloader.py", line 8, in <module>
    for iteration, (images, targets, _) in enumerate(dl, 0):
  File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 551, in __next__
    return self._process_next_batch(batch)
  File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 577, in _process_next_batch
    raise batch.exc_type(batch.exc_msg)
IndexError: Traceback (most recent call last):
  File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in <listcomp>
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "/home/lucifer/.virtualenvs/maskrcnn-benchmark/lib/python3.6/site-packages/torch/utils/data/dataset.py", line 85, in __getitem__
    return self.datasets[dataset_idx][sample_idx]
  File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/data/datasets/coco.py", line 94, in __getitem__
    target = target.clip_to_image(remove_empty=True)
  File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/structures/bounding_box.py", line 223, in clip_to_image
    return self[keep]
  File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/structures/bounding_box.py", line 208, in __getitem__
    bbox.add_field(k, v[item])
  File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/structures/segmentation_mask.py", line 555, in __getitem__
    selected_instances = self.instances.__getitem__(item)
  File "/home/lucifer/Projects/05_maskrcnn-benchmark/maskrcnn-benchmark/maskrcnn_benchmark/structures/segmentation_mask.py", line 464, in __getitem__
    selected_polygons.append(self.polygons[i])
IndexError: list index out of range

Expected behavior

I have tried follow by #881,#1053,#725 and so on. But they seems not work for my situation.

any help is appreciated

Environment

Collecting environment information...
PyTorch version: 1.0.0.dev20190409
Is debug build: No
CUDA used to build PyTorch: 9.0.176
OS: Ubuntu 16.04.5 LTS
GCC version: (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609
CMake version: version 3.5.1
Python version: 3.6
Is CUDA available: Yes
CUDA runtime version: Could not collect
GPU models and configuration: GPU 0: GeForce GTX 1070
Nvidia driver version: 384.130
cuDNN version: Could not collect
Versions of relevant libraries:
[pip3] numpy==1.17.4
[pip3] torch-nightly==1.0.0.dev20190409
[pip3] torchvision-nightly==0.2.3
[conda] Could not collect:

Additional context

The text was updated successfully, but these errors were encountered:

RadiantJeral · 2019-12-10T07:06:07Z

Inspired by #1053, #1181 and #1182 had ben fixed.

Modify the followed file.py:
maskrcnn_benchmark/structures/segmentation_mask.py
maskrcnn_benchmark/modeling/balanced_positive_negative_sampler.py

substitue for all torch.bool with torch.uint8

AllenYuQ · 2020-02-18T10:03:59Z

I meet the same situation and I modify the followed file.py:
maskrcnn_benchmark/structures/segmentation_mask.py
maskrcnn_benchmark/modeling/balanced_positive_negative_sampler.py

substitue for all torch.bool with torch.uint8.
It still doesn't work and the error message is：
RuntimeError: empty is not implemented for type CUDABoolType.
My pytorch vision is 1.0 too.

madurner · 2020-03-05T12:41:44Z

@FuckThatcher I have exactly the same behavior. Changing from torch.bool to torch.uint8 "fixes" the list index out of range error but results in the RuntimeError: empty is not implemented for type CUDABoolType. Could you already solve this?

@Jinksi isn't this pull request #4 not exactly the otherway round as @RadiantJeral explained up here?

AllenYuQ · 2020-03-05T14:37:54Z

@FuckThatcher I have exactly the same behavior. Changing from torch.bool to torch.uint8 "fixes" the list index out of range error but results in the RuntimeError: empty is not implemented for type CUDABoolType. Could you already solve this?
@Jinksi isn't this pull request #4 not exactly the otherway round as @RadiantJeral explained up here?

Yes，I meet the same runtime error after modification as in coco_eval.py
rles = [mask_util.encode(np.array(mask[0, :, :, np.newaxis], dtype=np.uint8, order="F"))[0]
for mask in mask ]

@FuckThatcher I have exactly the same behavior. Changing from torch.bool to torch.uint8 "fixes" the list index out of range error but results in the RuntimeError: empty is not implemented for type CUDABoolType. Could you already solve this?

@Jinksi isn't this pull request #4 not exactly the otherway round as @RadiantJeral explained up here?

You need continue to modify coco_eval.py like below:
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], dtype=np.uint8, order="F"))[0]
for mask in mask ]

Jinksi · 2020-03-05T21:28:25Z

@maximilian-durner yeh sure is.
Sorry to confuse you, this PR (Jinksi#4) was on my own fork of the project, not aimed to be a PR for this official repo.

RadiantJeral closed this as completed Dec 10, 2019

RadiantJeral reopened this Dec 10, 2019

This was referenced Dec 10, 2019

returned non-zero exit status 1. RuntimeError: _th_or not supported on CUDAType for Bool #1172

Open

RuntimeError: s__th_or is not implemented for type CUDABoolType #1181

Open

Jinksi mentioned this issue Feb 17, 2020

Segmentation index error fix Jinksi/maskrcnn-benchmark#4

Merged

jiaxi-wu mentioned this issue Jul 23, 2020

Error About COCO jiaxi-wu/MPSR#3

Open

yukang2017 mentioned this issue Aug 20, 2020

if 'caption' in anns[0]: IndexError: list index out of range megvii-model/DetNAS#21

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

IndexError: list index out of range #1182

IndexError: list index out of range #1182

RadiantJeral commented Dec 10, 2019

RadiantJeral commented Dec 10, 2019

AllenYuQ commented Feb 18, 2020

madurner commented Mar 5, 2020

AllenYuQ commented Mar 5, 2020

Jinksi commented Mar 5, 2020

IndexError: list index out of range #1182

IndexError: list index out of range #1182

Comments

RadiantJeral commented Dec 10, 2019

🐛 Bug

To Reproduce

Expected behavior

Environment

Additional context

RadiantJeral commented Dec 10, 2019

AllenYuQ commented Feb 18, 2020

madurner commented Mar 5, 2020

AllenYuQ commented Mar 5, 2020

Jinksi commented Mar 5, 2020