Faster RCNN训练成功

I1020 15:18:13.768215  2304 net.cpp:228] rpn_cls_score_reshape does not need backward computation.
I1020 15:18:13.768218  2304 net.cpp:228] rpn_bbox_pred does not need backward computation.
I1020 15:18:13.768220  2304 net.cpp:228] rpn_cls_score does not need backward computation.
I1020 15:18:13.768223  2304 net.cpp:228] rpn_conv1_rpn_relu1_0_split does not need backward computation.
I1020 15:18:13.768224  2304 net.cpp:228] rpn_relu1 does not need backward computation.
I1020 15:18:13.768226  2304 net.cpp:228] rpn_conv1 does not need backward computation.
I1020 15:18:13.768229  2304 net.cpp:228] conv5_relu5_0_split does not need backward computation.
I1020 15:18:13.768231  2304 net.cpp:228] relu5 does not need backward computation.
I1020 15:18:13.768234  2304 net.cpp:228] conv5 does not need backward computation.
I1020 15:18:13.768237  2304 net.cpp:228] relu4 does not need backward computation.
I1020 15:18:13.768240  2304 net.cpp:228] conv4 does not need backward computation.
I1020 15:18:13.768244  2304 net.cpp:228] relu3 does not need backward computation.
I1020 15:18:13.768245  2304 net.cpp:228] conv3 does not need backward computation.
I1020 15:18:13.768249  2304 net.cpp:228] pool2 does not need backward computation.
I1020 15:18:13.768251  2304 net.cpp:228] norm2 does not need backward computation.
I1020 15:18:13.768254  2304 net.cpp:228] relu2 does not need backward computation.
I1020 15:18:13.768257  2304 net.cpp:228] conv2 does not need backward computation.
I1020 15:18:13.768260  2304 net.cpp:228] pool1 does not need backward computation.
I1020 15:18:13.768263  2304 net.cpp:228] norm1 does not need backward computation.
I1020 15:18:13.768266  2304 net.cpp:228] relu1 does not need backward computation.
I1020 15:18:13.768270  2304 net.cpp:228] conv1 does not need backward computation.
I1020 15:18:13.768273  2304 net.cpp:270] This network produces output bbox_pred
I1020 15:18:13.768276  2304 net.cpp:270] This network produces output cls_prob
I1020 15:18:13.768296  2304 net.cpp:283] Network initialization done.
I1020 15:18:13.828038  2304 net.cpp:816] Ignoring source layer data
I1020 15:18:13.858983  2304 net.cpp:816] Ignoring source layer loss_cls
I1020 15:18:13.858994  2304 net.cpp:816] Ignoring source layer loss_bbox
I1020 15:18:13.859267  2304 net.cpp:816] Ignoring source layer silence_rpn_cls_score
I1020 15:18:13.859273  2304 net.cpp:816] Ignoring source layer silence_rpn_bbox_pred
im_detect: 1/100 0.124s 0.000s
im_detect: 2/100 0.077s 0.000s
im_detect: 3/100 0.061s 0.000s
im_detect: 4/100 0.053s 0.000s
im_detect: 5/100 0.048s 0.000s
im_detect: 6/100 0.045s 0.000s
im_detect: 7/100 0.042s 0.000s
im_detect: 8/100 0.041s 0.000s
im_detect: 9/100 0.039s 0.000s
im_detect: 10/100 0.038s 0.000s
im_detect: 11/100 0.037s 0.000s
im_detect: 12/100 0.036s 0.000s
im_detect: 13/100 0.036s 0.000s
im_detect: 14/100 0.035s 0.000s
im_detect: 15/100 0.034s 0.000s
im_detect: 16/100 0.034s 0.000s
im_detect: 17/100 0.034s 0.000s
im_detect: 18/100 0.033s 0.000s
im_detect: 19/100 0.033s 0.000s
im_detect: 20/100 0.033s 0.000s
im_detect: 21/100 0.033s 0.000s
im_detect: 22/100 0.032s 0.000s
im_detect: 23/100 0.032s 0.000s
im_detect: 24/100 0.032s 0.000s
im_detect: 25/100 0.032s 0.000s
im_detect: 26/100 0.032s 0.000s
im_detect: 27/100 0.031s 0.000s
im_detect: 28/100 0.031s 0.000s
im_detect: 29/100 0.031s 0.000s
im_detect: 30/100 0.031s 0.000s
im_detect: 31/100 0.031s 0.000s
im_detect: 32/100 0.031s 0.000s
im_detect: 33/100 0.031s 0.000s
im_detect: 34/100 0.031s 0.000s
im_detect: 35/100 0.031s 0.000s
im_detect: 36/100 0.030s 0.000s
im_detect: 37/100 0.030s 0.000s
im_detect: 38/100 0.030s 0.000s
im_detect: 39/100 0.030s 0.000s
im_detect: 40/100 0.030s 0.000s
im_detect: 41/100 0.030s 0.000s
im_detect: 42/100 0.030s 0.000s
im_detect: 43/100 0.030s 0.000s
im_detect: 44/100 0.030s 0.000s
im_detect: 45/100 0.030s 0.000s
im_detect: 46/100 0.030s 0.000s
im_detect: 47/100 0.030s 0.000s
im_detect: 48/100 0.030s 0.000s
im_detect: 49/100 0.030s 0.000s
im_detect: 50/100 0.030s 0.000s
im_detect: 51/100 0.030s 0.000s
im_detect: 52/100 0.030s 0.000s
im_detect: 53/100 0.030s 0.000s
im_detect: 54/100 0.029s 0.000s
im_detect: 55/100 0.029s 0.000s
im_detect: 56/100 0.029s 0.000s
im_detect: 57/100 0.029s 0.000s
im_detect: 58/100 0.029s 0.000s
im_detect: 59/100 0.029s 0.000s
im_detect: 60/100 0.029s 0.000s
im_detect: 61/100 0.029s 0.000s
im_detect: 62/100 0.029s 0.000s
im_detect: 63/100 0.029s 0.000s
im_detect: 64/100 0.029s 0.000s
im_detect: 65/100 0.029s 0.000s
im_detect: 66/100 0.029s 0.000s
im_detect: 67/100 0.029s 0.000s
im_detect: 68/100 0.029s 0.000s
im_detect: 69/100 0.029s 0.000s
im_detect: 70/100 0.029s 0.000s
im_detect: 71/100 0.029s 0.000s
im_detect: 72/100 0.029s 0.000s
im_detect: 73/100 0.029s 0.000s
im_detect: 74/100 0.029s 0.000s
im_detect: 75/100 0.029s 0.000s
im_detect: 76/100 0.029s 0.000s
im_detect: 77/100 0.029s 0.000s
im_detect: 78/100 0.029s 0.000s
im_detect: 79/100 0.029s 0.000s
im_detect: 80/100 0.029s 0.000s
im_detect: 81/100 0.029s 0.000s
im_detect: 82/100 0.029s 0.000s
im_detect: 83/100 0.029s 0.000s
im_detect: 84/100 0.029s 0.000s
im_detect: 85/100 0.029s 0.000s
im_detect: 86/100 0.029s 0.000s
im_detect: 87/100 0.029s 0.000s
im_detect: 88/100 0.029s 0.000s
im_detect: 89/100 0.029s 0.000s
im_detect: 90/100 0.029s 0.000s
im_detect: 91/100 0.029s 0.000s
im_detect: 92/100 0.029s 0.000s
im_detect: 93/100 0.029s 0.000s
im_detect: 94/100 0.029s 0.000s
im_detect: 95/100 0.029s 0.000s
im_detect: 96/100 0.029s 0.000s
im_detect: 97/100 0.029s 0.000s
im_detect: 98/100 0.029s 0.000s
im_detect: 99/100 0.029s 0.000s
im_detect: 100/100 0.029s 0.000s
Evaluating detections
Writing obj VOC results file
VOC07 metric? Yes
Reading annotation for 1/100
Saving cached annotations to /home/py-faster-rcnn/data/VOCdevkit2007/annotations_cache/annots.pkl
AP for obj = 0.4998
Mean AP = 0.4998
~~~~~~~~
Results:
0.500
0.500
~~~~~~~~

--------------------------------------------------------------
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
--------------------------------------------------------------

real	0m15.138s
user	0m14.596s
sys	0m1.168s
@-PC:~/py-faster-rcnn$ 

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