Faster-RCNN训练问题解决

I1013 09:20:29.058217 17752 net.cpp:270] This network produces output cls_probI1013 09:20:29.058230 17752 net.cpp:283] Network initialization done.I1013 09:20:29.122452 17752 net.cpp:816] Ignoring source layer dataI1013 09:20:29.153412 17752 net.cpp:816] Ignoring source layer loss_clsI1013 09:20:29.153426 17752 net.cpp:816] Ignoring source layer loss_bboxI1013 09:20:29.153744 17752 net.cpp:816] Ignoring source layer silence_rpn_cls_scoreI1013 09:20:29.153748 17752 net.cpp:816] Ignoring source layer silence_rpn_bbox_predim_detect: 1/276 0.152s 0.000sim_detect: 2/276 0.139s 0.000sim_detect: 3/276 0.134s 0.000sim_detect: 4/276 0.132s 0.000sim_detect: 5/276 0.130s 0.000s

im_detect: 272/276 0.124s 0.000sim_detect: 273/276 0.124s 0.000sim_detect: 274/276 0.124s 0.000sim_detect: 275/276 0.124s 0.000sim_detect: 276/276 0.124s 0.000sEvaluating detectionsWriting obj VOC results fileVOC07 metric? YesTraceback (most recent call last):  File "./tools/test_net.py", line 90, in <module>    test_net(net, imdb, max_per_image=args.max_per_image, vis=args.vis)  File "/home/py-faster-rcnn/tools/../lib/fast_rcnn/test.py", line 295, in test_net    imdb.evaluate_detections(all_boxes, output_dir)  File "/home/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 332, in evaluate_detections    self._do_python_eval(output_dir)  File "/home/py-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 295, in _do_python_eval    use_07_metric=use_07_metric)  File "/home/py-faster-rcnn/tools/../lib/datasets/voc_eval.py", line 126, in voc_eval    R = [obj for obj in recs[imagename] if obj['name'] == classname]KeyError: 'IMG_0805'

解决: 删除data/VOCdekit2007下的annotations_cache文件夹

on.I1014 05:35:49.888906 31318 net.cpp:228] conv3 does not need backward computation.I1014 05:35:49.888907 31318 net.cpp:228] pool2 does not need backward computation.I1014 05:35:49.888909 31318 net.cpp:228] norm2 does not need backward computation.I1014 05:35:49.888911 31318 net.cpp:228] relu2 does not need backward computation.I1014 05:35:49.888912 31318 net.cpp:228] conv2 does not need backward computation.I1014 05:35:49.888914 31318 net.cpp:228] pool1 does not need backward computation.I1014 05:35:49.888916 31318 net.cpp:228] norm1 does not need backward computation.I1014 05:35:49.888918 31318 net.cpp:228] relu1 does not need backward computation.I1014 05:35:49.888919 31318 net.cpp:228] conv1 does not need backward computation.I1014 05:35:49.888921 31318 net.cpp:270] This network produces output bbox_predI1014 05:35:49.888922 31318 net.cpp:270] This network produces output cls_probI1014 05:35:49.888936 31318 net.cpp:283] Network initialization done.I1014 05:35:49.957736 31318 net.cpp:816] Ignoring source layer dataI1014 05:35:49.988982 31318 net.cpp:816] Ignoring source layer loss_clsI1014 05:35:49.988991 31318 net.cpp:816] Ignoring source layer loss_bboxI1014 05:35:49.989269 31318 net.cpp:816] Ignoring source layer silence_rpn_cls_scoreI1014 05:35:49.989274 31318 net.cpp:816] Ignoring source layer silence_rpn_bbox_predim_detect: 1/276 0.155s 0.000sim_detect: 2/276 0.139s 0.000sim_detect: 3/276 0.133s 0.000sim_detect: 4/276 0.130s 0.000sim_detect: 5/276 0.129s 0.000sim_detect: 6/276 0.127s 0.000sim_detect: 7/276 0.127s 0.000sim_detect: 8/276 0.127s 0.000sim_detect: 9/276 0.126s 0.000sim_detect: 10/276 0.126s 0.000sim_detect: 11/276 0.125s 0.000sim_detect: 12/276 0.125s 0.000sim_detect: 13/276 0.125s 0.000sim_detect: 14/276 0.125s 0.000sim_detect: 15/276 0.125s 0.000sim_detect: 16/276 0.125s 0.000sim_detect: 17/276 0.125s 0.000sim_detect: 18/276 0.124s 0.000sim_detect: 19/276 0.124s 0.000sim_detect: 20/276 0.124s 0.000sim_detect: 21/276 0.124s 0.000sim_detect: 22/276 0.124s 0.000sim_detect: 263/276 0.122s 0.000sim_detect: 264/276 0.122s 0.000sim_detect: 265/276 0.122s 0.000sim_detect: 266/276 0.122s 0.000sim_detect: 267/276 0.122s 0.000sim_detect: 268/276 0.122s 0.000sim_detect: 269/276 0.122s 0.000sim_detect: 270/276 0.122s 0.000sim_detect: 271/276 0.122s 0.000sim_detect: 272/276 0.122s 0.000sim_detect: 273/276 0.122s 0.000sim_detect: 274/276 0.122s 0.000sim_detect: 275/276 0.122s 0.000sim_detect: 276/276 0.122s 0.000sEvaluating detectionsWriting obj VOC results fileVOC07 metric? YesReading annotation for 1/276Reading annotation for 101/276Reading annotation for 201/276Saving cached annotations to /home/py-faster-rcnn/data/VOCdevkit2007/annotations_cache/annots.pklAP for obj = 0.1282Mean AP = 0.1282~~~~~~~~Results:0.1280.128~~~~~~~~--------------------------------------------------------------Results computed with the **unofficial** Python eval code.Results should be very close to the official MATLAB eval code.Recompute with `./tools/reval.py --matlab ...` for your paper.-- Thanks, The Management--------------------------------------------------------------real0m59.349suser0m59.772ssys0m3.548s

转载请注明：http://blog.csdn.net/forest_world