search

chenxinpeng / SSD_scene_text_detection

Detect text in natural images with SSD, Single Shot Detection
225 stars 103 forks source link

Issue related to training #9

Open pranayamhatre175 opened 7 years ago

pranayamhatre175 commented 7 years ago

Hi

while executing VGG_scenetext_SSD_300x300.sh file I got following error

Check failed: numpriors num_locclasses 4 == bottom[0]->channels() (58464 vs. 29232) Number of priors must match number of location predictions. Check failure stack trace: Aborted (core dumped)

Can you please provide me solution for solving this issue? Thank you

HelloTobe commented 7 years ago

@pranayamhatre175 Hi, do you know how to calculate the pricision, recall and f-measure?

Could you provide me with the source codes (matlab or python)?

pranayamhatre175 commented 7 years ago

@HelloTobe Hi, use sklearn.metrics.precision_recall_fscore_support to compute pricision, recall and f-measure. reffer this link : http://scikit-learn.org/stable/modules/generated/sklearn.metrics.precision_recall_fscore_support.html#sklearn-metrics-precision-recall-fscore-support

HelloTobe commented 7 years ago

@pranayamhatre175 Thank you very much!

Have you reimplement the paper TextBoxes：A Fast Text Detector with a Single Deep Neural Network? There are a lot of questions i want to ask you.