search

dbolya / yolact

A simple, fully convolutional model for real-time instance segmentation.
MIT License
4.97k stars 1.32k forks source link

MALFORMED INPUT #799

Open NowLoadY opened 1 year ago

NowLoadY commented 1 year ago

(does anyone know how to solve it please?)

After running with no any problems for a while, I get an error, Here is what i got:

PS D:\coding\python_learning\yolact> python eval.py --trained_model=weights/yolact_im700_54_800000.pth --score_threshold=0.15 --top_k=15 --video_multiframe=4 --video=0 Config not specified. Parsed yolact_im700_config from the file name.

Loading model...C:\ProgramData\Anaconda3\envs\pytorch_tensorflow_keras_3.8.13\lib\site-packages\torch\jit_recursive.py:234: UserWarning: 'downsample_layers' was found in ScriptModule constants, but it is a non-constant submodule. Consider removing it. warnings.warn("'{}' was found in ScriptModule constants, " C:\ProgramData\Anaconda3\envs\pytorch_tensorflow_keras_3.8.13\lib\site-packages\torch\jit_recursive.py:234: UserWarning: 'pred_layers' was found in ScriptModule constants, but it is a non-constant submodule. Consider removing it. warnings.warn("'{}' was found in ScriptModule constants, " C:\ProgramData\Anaconda3\envs\pytorch_tensorflow_keras_3.8.13\lib\site-packages\torch\jit_recursive.py:234: UserWarning: 'lat_layers' was found in ScriptModule constants, but it is a non-constant submodule. Consider removing it. warnings.warn("'{}' was found in ScriptModule constants, " Done. Initializing model... Done.

Press Escape to close. Processing FPS: 11.16 | Video Playback FPS: 11.22 | Frames in Buffer: 3 Traceback (most recent call last): File "eval.py", line 1105, in evaluate(net, dataset) File "eval.py", line 892, in evaluate evalvideo(net, args.video) File "eval.py", line 832, in evalvideo frame_buffer.put(frame['value'].get()) File "C:\ProgramData\Anaconda3\envs\pytorch_tensorflow_keras_3.8.13\lib\multiprocessing\pool.py", line 771, in get raise self._value File "C:\ProgramData\Anaconda3\envs\pytorch_tensorflow_keras_3.8.13\lib\multiprocessing\pool.py", line 125, in worker result = (True, func(*args, **kwds)) File "eval.py", line 712, in prep_frame return prep_display(preds, frame, None, None, undo_transform=False, class_color=True, fps_str=fps_str) File "eval.py", line 149, in prep_display t = postprocess(dets_out, w, h, visualize_lincomb = args.display_lincomb, File "D:\coding\python_learning\yolact\layers\output_utils.py", line 98, in postprocess boxes[:, 1], boxes[:, 3] = sanitize_coordinates(boxes[:, 1], boxes[:, 3], h, cast=False) RuntimeError: The following operation failed in the TorchScript interpreter. Traceback of TorchScript (most recent call last): RuntimeError: MALFORMED INPUT: Index out of bounds in check_bounds. Index: 511; bounds: [0, 1). - ret_val(dtype=int64_t, sizes=[1], strides=[1])