How to show result of testing?

[wlh0517]

When I run testing code in "all.sh", it shows the below picture.

INFO test_engine.py: 330: im_detect: range [15001, 30000] of 30000: 29911/30000 0.613s + 0.001s (eta: 0:00:54) INFO test_engine.py: 330: im_detect: range [15001, 30000] of 30000: 29921/30000 0.613s + 0.001s (eta: 0:00:48) INFO test_engine.py: 330: im_detect: range [15001, 30000] of 30000: 29931/30000 0.613s + 0.001s (eta: 0:00:42) INFO test_engine.py: 330: im_detect: range [15001, 30000] of 30000: 29941/30000 0.613s + 0.001s (eta: 0:00:36) INFO test_engine.py: 330: im_detect: range [15001, 30000] of 30000: 29951/30000 0.613s + 0.001s (eta: 0:00:30) INFO test_engine.py: 330: im_detect: range [15001, 30000] of 30000: 29961/30000 0.613s + 0.001s (eta: 0:00:23) INFO test_engine.py: 330: im_detect: range [15001, 30000] of 30000: 29971/30000 0.613s + 0.001s (eta: 0:00:17) INFO test_engine.py: 330: im_detect: range [15001, 30000] of 30000: 29981/30000 0.613s + 0.001s (eta: 0:00:11) INFO test_engine.py: 330: im_detect: range [15001, 30000] of 30000: 29991/30000 0.613s + 0.001s (eta: 0:00:05) /home/dd/software/anaconda3/envs/fsod/lib/python3.6/site-packages/torch/nn/functional.py:1006: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead. warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.") Traceback (most recent call last): File "/home/dd/wlh/FSOD-code/tools/test_net.py", line 131, in check_expected_results=True) File "/home/dd/wlh/FSOD-code/lib/core/test_engine.py", line 130, in run_inference all_results = result_getter() File "/home/dd/wlh/FSOD-code/lib/core/test_engine.py", line 127, in result_getter gpu_id=gpu_id File "/home/dd/wlh/FSOD-code/lib/core/test_engine.py", line 361, in test_net ), det_file File "/home/dd/wlh/FSOD-code/lib/utils/io.py", line 43, in save_object pickle.dump(obj, f, pickle.HIGHEST_PROTOCOL) MemoryError

Traceback (most recent call last): File "tools/test_net.py", line 131, in check_expected_results=True) File "/home/dd/wlh/FSOD-code/lib/core/test_engine.py", line 130, in run_inference all_results = result_getter() File "/home/dd/wlh/FSOD-code/lib/core/test_engine.py", line 110, in result_getter multi_gpu=multi_gpu_testing File "/home/dd/wlh/FSOD-code/lib/core/test_engine.py", line 165, in test_net_on_dataset args, dataset_name, proposal_file, num_images, num_classes, output_dir File "/home/dd/wlh/FSOD-code/lib/core/test_engine.py", line 197, in multi_gpu_test_net_on_dataset args.load_ckpt, args.load_detectron, opts File "/home/dd/wlh/FSOD-code/lib/utils/subprocess.py", line 107, in process_in_parallel log_subprocess_output(i, p, output_dir, tag, start, end) File "/home/dd/wlh/FSOD-code/lib/utils/subprocess.py", line 145, in log_subprocess_output assert ret == 0, 'Range subprocess failed (exit code: {})'.format(ret) AssertionError: Range subprocess failed (exit code: 1) (fsod) dd@dd-desktop:~/wlh/FSOD-code$ python

How to solve this problem? And I want to know how to show the picture after detection. I want to get the picture as that in your paper.

[wlh0517]

'all.sh' is 'CUDA_VISIBLE_DEVICES=0,1 python3 tools/test_net.py --multi-gpu-testing --dataset fsod --cfg configs/fsod/voc_e2e_faster_rcnn_R-50-C4_1x_old_1.yaml --load_ckpt Outputs/fsod36000/ckpt/model_step71999.pth '

[TMoonLi]

I encountered the same problem as you, did you solve it?

[AmingWu]

@wlh156423 , did you solve this problem? I also encountered the same problem.

[liuweijie19980216]

I also met this problem,maybe it's because the computer doesn't have enough memory. Then I changed the compute that has memory of 32G and worked well.

[fhong-jpg]

@liuweijie19980216 Could you share me the trained model? Thanks.