mks0601 / A-Convolutional-Neural-Network-Cascade-for-Face-Detection

TensorFlow implementation of "A Convolutional Neural Network Cascade for Face Detection", CVPR 2015
http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Li_A_Convolutional_Neural_2015_CVPR_paper.pdf
109 stars 62 forks source link

calib_12net accuracy #17

Closed bk202 closed 5 years ago

bk202 commented 6 years ago

Hi, I have reached a accuracy bottleneck of 61% for the 12 calibration net while attempting to train my own C-CNN. Can you please tell me if you have overcome that bottleneck or not, and if a low calibration net accuracy have any impact on the entire network? Thank you.

ZZ94 commented 6 years ago

Hi, did you encounter the error (ValueError: cannot reshape array of size 619500 into shape (500,413,1)) when running the train12_net file?

bk202 commented 6 years ago

@ZZ94 No, I was implementing the C-CNN in my own code, so I didn't encounter this issue.

ZZ94 commented 6 years ago

@bk202 ok thank you