abner2015

The training results are good, but the test results are very poor.

2

when i use my dataset train the ocr model , the training results are good, but the test results are very poor. i do not need segment the roi ....

After trained faster-rcnn use other image formats like .bmp, running demo had error: Error using gpuArray/subsref Index exceeds matrix dimension. Error in proposal_im_detect (line 16) im_blob = im_blob(:, :, [3,...

make error

4

i had chaned the paths. when i run "make", the error as: #include "caffe/proto/caffe.pb.h" ^ compilation terminated. make: *** [objs/mxnet_to_caffe.o] error 1 what is the reason? Thank you!

when i run infer_cnn_ocr.py after trained ,all of the result is 0. gen captcha: 8183 [ 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1 0.1] [ 0.1 0.1 0.1...

I have two identical GPUs in my machine but when fine tune resnet56 it seems only one of them is used.h i had try the two cmd $caffe train -solver...