argman / EAST

A tensorflow implementation of EAST text detector
GNU General Public License v3.0
3.02k stars 1.05k forks source link

我运行multigpu_train.py的时候出现问题 #340

Open songmimi opened 4 years ago

songmimi commented 4 years ago

Generator use 10 batches for buffering, this may take a while, you can tune this yourself. 11 training images in data/ocr/icdar text file gt_data/ocr/icdar/img_994.txt does not exists text file gt_data/ocr/icdar/img_993.txt does not exists text file gt_data/ocr/icdar/img_999.txt does not exists text file gt_data/ocr/icdar/img_991.txt does not exists text file gt_data/ocr/icdar/img_995.txt does not exists 这是我的代码运行结果,老是显示gt格式不存在,可是我的gt在的,而且我的icdar2015数据集是我在官网下载的,我的问题困扰我好久了,希望大家帮我一下

WoshiBoluo commented 4 years ago

亲你现在能正常跑起来了吗

ho1messi commented 4 years ago

readme 里面 Train 部分有提到要改标注文件名称或者代码 改代码的话就把 icdar.py 里 604 行改成 txt_fn = im_fn.replace(os.path.basename(imfn), 'gt%s.txt' % os.path.basename(im_fn).split('.')[0]) 就好了

Note: you should change the gt text file of icdar2015's filename to img_.txt instead of gtimg.txt(or you can change the code in icdar.py), and some extra characters should be removed from the file. See the examples in training_samples/

pankSM commented 4 years ago

您好,请问您训练时候怎么使用的的gpu?我按照教程来的,结果只使用显卡60M, 基本没使用gpu