ming71 / sla Goto Github PK
View Code? Open in Web Editor NEW[RS 2021] Official implementation of "Sparse Label Assignment for Oriented Object Detection inAerial Images"
License: MIT License
[RS 2021] Official implementation of "Sparse Label Assignment for Oriented Object Detection inAerial Images"
License: MIT License
代码里面涉及到的data目录,怎么没有呢
[I want to change installed location,please ming71]
creating build/lib.linux-x86_64-3.8
x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -g -fwrapv -O2 build/temp.linux-x86_64-3.8/sort_vert.o build/temp.linux-x86_64-3.8/sort_vert_kernel.o -L/usr/local/lib/python3.8/dist-packages/torch/lib -L/usr/local/cuda/lib64 -L/usr/lib/x86_64-linux-gnu -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.8/sort_vertices.cpython-38-x86_64-linux-gnu.so
creating build/bdist.linux-x86_64
creating build/bdist.linux-x86_64/egg
byte-compiling build/bdist.linux-x86_64/egg/sort_vertices.py to sort_vertices.cpython-38.pyc
creating build/bdist.linux-x86_64/egg/EGG-INFO
copying sort_vertices.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO
copying sort_vertices.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying sort_vertices.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
copying sort_vertices.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
zip_safe flag not set; analyzing archive contents...
pycache.sort_vertices.cpython-38: module references file
removing 'build/bdist.linux-x86_64/egg' (and everything under it)
removing '/usr/lib/python3.8/site-packages/sort_vertices-0.0.0-py3.8-linux-x86_64.egg' (and everything under it)
creating /usr/lib/python3.8/site-packages/sort_vertices-0.0.0-py3.8-linux-x86_64.egg
Extracting sort_vertices-0.0.0-py3.8-linux-x86_64.egg to /usr/lib/python3.8/site-packages
byte-compiling /usr/lib/python3.8/site-packages/sort_vertices-0.0.0-py3.8-linux-x86_64.egg/sort_vertices.py to sort_vertices.cpython-38.pyc
sort-vertices 0.0.0 is already the active version in easy-install.pth
Installed /usr/lib/python3.8/site-packages/sort_vertices-0.0.0-py3.8-linux-x86_64.egg
Processing dependencies for sort-vertices==0.0.0
Finished processing dependencies for sort-vertices==0.0.0
sort-vertices==0.0.0 Installed to ----------------------> /usr/local/lib/python3.8/dist-packages
Traceback (most recent call last):
File "/root/.pycharm_helpers/pydev/pydevd.py", line 1483, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "/root/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/root/autodl-tmp/rxh/mmrotate/tools/train.py", line 192, in
main()
File "/root/autodl-tmp/rxh/mmrotate/tools/train.py", line 181, in main
train_detector(
File "/root/autodl-tmp/rxh/mmrotate/mmrotate/apis/train.py", line 140, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 136, in run
epoch_runner(data_loaders[i], **kwargs)
File "/root/autodl-tmp/rxh/mmrotate/mmrotate/utils/my_epoch_based_runner.py", line 23, in train
self.run_iter(data_batch, train_mode=True, **kwargs)
File "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 31, in run_iter
outputs = self.model.train_step(data_batch, self.optimizer,
python-BaseException
File "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/mmcv/parallel/data_parallel.py", line 77, in train_step
return self.module.train_step(*inputs[0], **kwargs[0])
File "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/mmdet/models/detectors/base.py", line 248, in train_step
losses = self(**data)
File "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 116, in new_func
return old_func(*args, **kwargs)
File "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/mmdet/models/detectors/base.py", line 172, in forward
return self.forward_train(img, img_metas, **kwargs)
File "/root/autodl-tmp/rxh/mmrotate/mmrotate/models/detectors/single_stage.py", line 87, in forward_train
losses = self.bbox_head.forward_train(x, img_metas, gt_bboxes,
File "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/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 "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 205, in new_func
return old_func(*args, **kwargs)
File "/root/autodl-tmp/rxh/mmrotate/mmrotate/models/dense_heads/rotated_match_head.py", line 331, in loss
losses_cls, losses_bbox = multi_apply(
File "/root/miniconda3/envs/mmrotate/lib/python3.8/site-packages/mmdet/core/utils/misc.py", line 30, in multi_apply
return tuple(map(list, zip(*map_results)))
File "/root/autodl-tmp/rxh/mmrotate/mmrotate/models/dense_heads/rotated_match_head.py", line 249, in loss_single
mask_pos, mask_neg, bbox_indexes = match(anchors_xyxy, bboxes_xyxy, bbox_target, anchors[:, :4], self.iou_thresh, process=globalvar.get_value('process'), batch=batch)
File "/root/autodl-tmp/rxh/mmrotate/mmrotate/models/dense_heads/rotated_match_head.py", line 381, in match
sampled_bg_indices = np.random.choice(bg_indices.cpu(), size=num_bg)
File "mtrand.pyx", line 915, in numpy.random.mtrand.RandomState.choice
ValueError: 'a' cannot be empty unless no samples are taken
hard_indices = ((max_ious > 0.1) & (max_ious < iou_thresh[0])).nonzero().squeeze()
bg_indices = (max_ious < 1e-2).nonzero().squeeze()
sampled_hard_indices = np.random.choice(hard_indices.cpu(), size=num_hard)
sampled_bg_indices = np.random.choice(bg_indices.cpu(), size=num_bg)
在debug后发现bg_indices是空的,原因是max_ious没有小于1e-2的,
tensor([0.1603, 0.1990, 0.2419, 0.1708, 0.2114, 0.2560, 0.1604, 0.1991, 0.2420,
0.2273, 0.2722, 0.3195, 0.2264, 0.2711, 0.3182, 0.1992, 0.2778, 0.3442,
0.2928, 0.4537, 0.5659, 0.2928, 0.4075, 0.4993, 0.2671, 0.3646, 0.4870,
0.2928, 0.4537, 0.5900, 0.2928, 0.4222, 0.4993, 0.2671, 0.3646, 0.4870,
......
0.0886, 0.1406, 0.2088, 0.0732, 0.1130, 0.1426, 0.0998, 0.1542, 0.2280,
0.0447, 0.0686, 0.0991, 0.0367, 0.0592, 0.0886, 0.0512, 0.0761, 0.1076,
0.0230, 0.0414, 0.0669, 0.0239, 0.0424, 0.0680, 0.0169, 0.0344, 0.0591],
device='cuda:0')
这个1e-2是怎么取值的,我把这个值调大会不会和背景没什么关系了,还有hard_indices有时候也会出现这种情况,这种要怎么办呢
100%|████████████████████████████████████████████████████████████████████████████████| 57/57 [01:18<00:00, 1.38s/it]
AP
ship: 29.489750676913513
mAP: 29.489750676913513
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.