There was a problem with training.

[zhanghongruiupup]

multigpu_train.py, The program is displayed as:"Generator use 10 batches for buffering, this may take a while, you can tune this yourself. 0 training images in /data/ocr/icdar2015/" Then it stopped moving.

[1LOVESJohnny]

change the actual data directory as you put them local.

[Eatzhy]

images的路径不对，比如训练的img在data/ocr/icdar2015/train/下面，你就把路径改一下； 这个时候可能会报另一个错误，text file ./data/ocr/icdar2015/train/imgs/gt_img_211.txt does not exists 然后改icdar.py中604行，改成： txt_fn = im_fn.replace(os.path.basename(im_fn), 'gt_%s.txt' % os.path.basename(im_fn).split('.')[0]) txt_fn = txt_fn.replace('imgs','gt')