Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Apache License 2.0
12.36k
stars
2.84k
forks
source link
ValueError: all input arrays must have the same shape and stuck at Adding OutScale op: #8903
shell''' 2024-04-02 12:44:20,667-INFO: devices: gpu
Exception in thread Thread-1:
Traceback (most recent call last):
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\threading.py", line 980, in _bootstrap_inner
self.run()
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\threading.py", line 917, in run
self._target(*self._args, **self._kwargs)
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\paddle\io\dataloader\dataloader_iter.py", line 235, in _thread_loop
batch = self._dataset_fetcher.fetch(
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\paddle\io\dataloader\fetcher.py", line 86, in fetch
data = self.collate_fn(data)
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\ppdet\data\reader.py", line 96, in call
batch_data = default_collate_fn(data)
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\ppdet\data\utils.py", line 60, in default_collate_fn
return {
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\ppdet\data\utils.py", line 61, in
key: default_collate_fn([d[key] for d in batch])
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\ppdet\data\utils.py", line 52, in default_collate_fn
batch = np.stack(batch, axis=0)
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\numpy\core\shape_base.py", line 449, in stack
raise ValueError('all input arrays must have the same shape')
ValueError: all input arrays must have the same shape '''
[X] 我确认已经提供了Bug复现步骤、代码改动说明、以及环境信息，确认问题是可以复现的。I confirm that the bug replication steps, code change instructions, and environment information have been provided, and the problem can be reproduced.
问题确认 Search before asking
Bug组件 Bug Component
Other
Bug描述 Describe the Bug
py'''python run.py --config_path deploy\auto_compression\configs\ppyoloe_plus_s_qat_dis.yaml --save_dir output1''' above with custom coco dataset
shell''' 2024-04-02 12:44:20,667-INFO: devices: gpu Exception in thread Thread-1: Traceback (most recent call last): File "C:\Users\Fstech\anaconda3\envs\aivision\lib\threading.py", line 980, in _bootstrap_inner self.run() File "C:\Users\Fstech\anaconda3\envs\aivision\lib\threading.py", line 917, in run self._target(*self._args, **self._kwargs) File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\paddle\io\dataloader\dataloader_iter.py", line 235, in _thread_loop batch = self._dataset_fetcher.fetch( File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\paddle\io\dataloader\fetcher.py", line 86, in fetch data = self.collate_fn(data) File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\ppdet\data\reader.py", line 96, in call batch_data = default_collate_fn(data) File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\ppdet\data\utils.py", line 60, in default_collate_fn return { File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\ppdet\data\utils.py", line 61, in
key: default_collate_fn([d[key] for d in batch])
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\ppdet\data\utils.py", line 52, in default_collate_fn
batch = np.stack(batch, axis=0)
File "C:\Users\Fstech\anaconda3\envs\aivision\lib\site-packages\numpy\core\shape_base.py", line 449, in stack
raise ValueError('all input arrays must have the same shape')
ValueError: all input arrays must have the same shape '''
Adding OutScale op:|█████████████████████████████████████████████████| 1653/1653
stuck after this line.
复现环境 Environment
paddlepaddle-gpu 2.5 cuda=11.7 cudnn = 8.4
Bug描述确认 Bug description confirmation
是否愿意提交PR？ Are you willing to submit a PR?