mxbonn / anchor_pruning Goto Github PK
View Code? Open in Web Editor NEWOfficial code of the paper "Anchor pruning for object detection"
Home Page: https://doi.org/10.1016/j.cviu.2022.103445
Official code of the paper "Anchor pruning for object detection"
Home Page: https://doi.org/10.1016/j.cviu.2022.103445
Traceback (most recent call last):
File "tools/mmdet_train.py", line 239, in
main()
File "tools/mmdet_train.py", line 235, in main
meta=meta)
File "/home/featurize/mmdetection-2.25.0/mmdet/apis/train.py", line 244, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/environment/miniconda3/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run
epoch_runner(data_loaders[i], **kwargs)
File "/environment/miniconda3/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 50, in train
self.run_iter(data_batch, train_mode=True, **kwargs)
File "/environment/miniconda3/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 30, in run_iter
**kwargs)
File "/environment/miniconda3/lib/python3.7/site-packages/mmcv/parallel/data_parallel.py", line 75, in train_step
return self.module.train_step(*inputs[0], **kwargs[0])
File "/home/featurize/mmdetection-2.25.0/mmdet/models/detectors/base.py", line 248, in train_step
losses = self(**data)
File "/environment/miniconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/environment/miniconda3/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 98, in new_func
return old_func(*args, **kwargs)
File "/home/featurize/mmdetection-2.25.0/mmdet/models/detectors/base.py", line 172, in forward
return self.forward_train(img, img_metas, **kwargs)
File "/home/featurize/mmdetection-2.25.0/mmdet/models/detectors/single_stage.py", line 84, in forward_train
gt_labels, gt_bboxes_ignore)
File "/home/featurize/mmdetection-2.25.0/mmdet/models/dense_heads/base_dense_head.py", line 335, in forward_train
losses = self.loss(*loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
File "/environment/miniconda3/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 186, in new_func
return old_func(*args, **kwargs)
File "/home/featurize/mmdetection-2.25.0/mmdet/models/dense_heads/anchor_head.py", line 519, in loss
num_total_samples=num_total_samples)
File "/home/featurize/mmdetection-2.25.0/mmdet/core/utils/misc.py", line 30, in multi_apply
return tuple(map(list, zip(*map_results)))
File "/home/featurize/mmdetection-2.25.0/mmdet/models/dense_heads/anchor_head.py", line 434, in loss_single
cls_score, labels, label_weights, avg_factor=num_total_samples)
File "/environment/miniconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/featurize/mmdetection-2.25.0/mmdet/models/losses/focal_loss.py", line 240, in forward
avg_factor=avg_factor)
File "/home/featurize/mmdetection-2.25.0/mmdet/models/losses/focal_loss.py", line 140, in sigmoid_focal_loss
alpha, None, 'none')
File "/environment/miniconda3/lib/python3.7/site-packages/mmcv/ops/focal_loss.py", line 56, in forward
input, target, weight, output, gamma=ctx.gamma, alpha=ctx.alpha)
RuntimeError: max(): Expected reduction dim to be specified for input.numel() == 0. Specify the reduction dim with the 'dim' argument.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.