Mean AP = 0.0000

[ferdinan97]

Saving cached annotations to /home/ferdinan3105/Downloads/py-faster-rcnn/data/VOCdevkit2007/annotations_cache/annots.pkl /home/ferdinan3105/Downloads/py-faster-rcnn/tools/../lib/datasets/voc_eval.py:194: RuntimeWarning: invalid value encountered in divide rec = tp / float(npos) /home/ferdinan3105/Downloads/py-faster-rcnn/tools/../lib/datasets/voc_eval.py:41: RuntimeWarning: invalid value encountered in greater_equal if np.sum(rec >= t) == 0: AP for truck = 0.0000 AP for remote = 0.0000 AP for tv = 0.0000 AP for laptop = 0.0000 AP for mouse = 0.0000 AP for keyboard = 0.0000 Mean AP = 0.0000

Results: 0.000 0.000 0.000 0.000 0.000 0.000 0.000 i try to train my own dataset with caffe using this source: https://github.com/xinleipan/py-faster-rcnn-with-new-dataset. and after the train the mean AP it's always 0 for my dataset but when i train default dataset from ImageNet it the AP is not 0. but for your information when i try train my dataset with tensorflow it have a pretty good accuracy. Can someone help me with this ? this my prototxt: train.txt solver.txt text.txt text.txt is test