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
12.65k
stars
2.87k
forks
source link
I trained faster_crnn model but I recieved an error when it called get_loss function #8759
[X] 我已经查询历史issue，没有发现相似的bug。I have searched the issues and found no similar bug report.
Bug组件 Bug Component
Training
Bug描述 Describe the Bug
/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/pkg_resources/init.py:121: DeprecationWarning: pkg_resources is deprecated as an API
warnings.warn("pkg_resources is deprecated as an API", DeprecationWarning)
/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/pkg_resources/init.py:2870: DeprecationWarning: Deprecated call to pkg_resources.declare_namespace('mpl_toolkits').
Implementing implicit namespace packages (as specified in PEP 420) is preferred to pkg_resources.declare_namespace. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages
declare_namespace(pkg)
/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/pkg_resources/init.py:2870: DeprecationWarning: Deprecated call to pkg_resources.declare_namespace('google').
Implementing implicit namespace packages (as specified in PEP 420) is preferred to pkg_resources.declare_namespace. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages
declare_namespace(pkg)
W1218 11:49:59.975874 5014 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 8.6, Driver API Version: 11.4, Runtime API Version: 10.2
W1218 11:49:59.979482 5014 gpu_resources.cc:91] device: 0, cuDNN Version: 8.1.
[12/18 11:50:01] ppdet.utils.checkpoint INFO: Finish loading model weights: /home/aiotlabws/.cache/paddle/weights/ResNet50_cos_pretrained.pdparams
Hello
Traceback (most recent call last):
File "tools/train.py", line 209, in
main()
File "tools/train.py", line 205, in main
run(FLAGS, cfg)
File "tools/train.py", line 158, in run
trainer.train(FLAGS.eval)
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/engine/trainer.py", line 577, in train
outputs = model(data)
File "/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 929, in call
return self._dygraph_call_func(*inputs, kwargs)
File "/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 915, in _dygraph_call_func
outputs = self.forward(*inputs, *kwargs)
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/architectures/meta_arch.py", line 61, in forward
out = self.get_loss()
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/architectures/faster_rcnn.py", line 113, in get_loss
rpn_loss, bbox_loss = self._forward()
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/architectures/faster_rcnn.py", line 80, in _forward
rois, rois_num, rpn_loss = self.rpn_head(body_feats, self.inputs)
File "/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 929, in call
return self._dygraph_call_func(inputs, kwargs)
File "/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 915, in _dygraph_call_func
outputs = self.forward(*inputs, **kwargs)
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/proposal_generator/rpn_head.py", line 141, in forward
rois, rois_num = self._gen_proposal(scores, deltas, anchors, inputs)
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/proposal_generator/rpn_head.py", line 206, in _gen_proposal
rpn_rois, rpn_rois_prob, rpn_rois_num, post_nms_top_n = prop_gen(
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/proposal_generator/proposal_generator.py", line 70, in call
rpn_rois, rpn_rois_prob, rpn_rois_num = generate_proposals(
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/ops.py", line 1014, in generate_proposals
rpn_rois, rpn_roi_probs, rpn_rois_num = C_ops.generate_proposals_v2(
RuntimeError: (PreconditionNotMet) The Tensor's element number must be equal or greater than zero. The Tensor's shape is [-1138971471, 4] now
[Hint: Expected numel() >= 0, but received numel():-4555885884 < 0:0.] (at /paddle/paddle/phi/core/dense_tensor_impl.cc:108)
[operator < generate_proposals_v2 > error]
复现环境 Environment
Bug描述确认 Bug description confirmation
[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.
lyuwenyu
commented
8 months ago
问题确认 Search before asking
Bug组件 Bug Component
Training
Bug描述 Describe the Bug
/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/pkg_resources/init.py:121: DeprecationWarning: pkg_resources is deprecated as an API warnings.warn("pkg_resources is deprecated as an API", DeprecationWarning) /mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/pkg_resources/init.py:2870: DeprecationWarning: Deprecated call to
main()
File "tools/train.py", line 205, in main
run(FLAGS, cfg)
File "tools/train.py", line 158, in run
trainer.train(FLAGS.eval)
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/engine/trainer.py", line 577, in train
outputs = model(data)
File "/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 929, in call
return self._dygraph_call_func(*inputs, kwargs)
File "/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 915, in _dygraph_call_func
outputs = self.forward(*inputs, *kwargs)
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/architectures/meta_arch.py", line 61, in forward
out = self.get_loss()
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/architectures/faster_rcnn.py", line 113, in get_loss
rpn_loss, bbox_loss = self._forward()
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/architectures/faster_rcnn.py", line 80, in _forward
rois, rois_num, rpn_loss = self.rpn_head(body_feats, self.inputs)
File "/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 929, in call
return self._dygraph_call_func(inputs, kwargs)
File "/mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 915, in _dygraph_call_func
outputs = self.forward(*inputs, **kwargs)
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/proposal_generator/rpn_head.py", line 141, in forward
rois, rois_num = self._gen_proposal(scores, deltas, anchors, inputs)
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/proposal_generator/rpn_head.py", line 206, in _gen_proposal
rpn_rois, rpn_rois_prob, rpn_rois_num, post_nms_top_n = prop_gen(
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/proposal_generator/proposal_generator.py", line 70, in call
rpn_rois, rpn_rois_prob, rpn_rois_num = generate_proposals(
File "/mnt/disk1/anhnct/School/MachineLearning/Project/Traffic_Sign_Detection_paddle_faster_rcnn/PaddleDetection/ppdet/modeling/ops.py", line 1014, in generate_proposals
rpn_rois, rpn_roi_probs, rpn_rois_num = C_ops.generate_proposals_v2(
RuntimeError: (PreconditionNotMet) The Tensor's element number must be equal or greater than zero. The Tensor's shape is [-1138971471, 4] now
[Hint: Expected numel() >= 0, but received numel():-4555885884 < 0:0.] (at /paddle/paddle/phi/core/dense_tensor_impl.cc:108)
[operator < generate_proposals_v2 > error]
pkg_resources.declare_namespace('mpl_toolkits'). Implementing implicit namespace packages (as specified in PEP 420) is preferred topkg_resources.declare_namespace. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages declare_namespace(pkg) /mnt/disk1/anaconda3/envs/anhnct/lib/python3.8/site-packages/pkg_resources/init.py:2870: DeprecationWarning: Deprecated call topkg_resources.declare_namespace('google'). Implementing implicit namespace packages (as specified in PEP 420) is preferred topkg_resources.declare_namespace. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages declare_namespace(pkg) W1218 11:49:59.975874 5014 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 8.6, Driver API Version: 11.4, Runtime API Version: 10.2 W1218 11:49:59.979482 5014 gpu_resources.cc:91] device: 0, cuDNN Version: 8.1. [12/18 11:50:01] ppdet.utils.checkpoint INFO: Finish loading model weights: /home/aiotlabws/.cache/paddle/weights/ResNet50_cos_pretrained.pdparams Hello Traceback (most recent call last): File "tools/train.py", line 209, in复现环境 Environment
Bug描述确认 Bug description confirmation
是否愿意提交PR？ Are you willing to submit a PR?