search

AstarLight / Lets_OCR

A repository for OCR, which inlcudes some classical OCR algorithms Pytorch implementation such as CTPN, EAST and CRNN.
MIT License
656 stars 327 forks source link

train 数据集时候，未收敛便提前终止了，并且和题主给的训练图片也不太一样，len(train_loader)输出的是7，不知道哪里出错了 #68

Open joeqincai opened 5 years ago

joeqincai commented 5 years ago

image

ShangLe0607 commented 5 years ago

@joeqincai 你好，我的训练的报错是这个，求助一下大佬这是什么原因呢？？ [0/20][20/282] Loss: 42.145580 [0/20][40/282] Loss: 19.428555 [0/20][60/282] Loss: 17.523825 [0/20][80/282] Loss: 16.701580 [0/20][100/282] Loss: 16.425825 [0/20][120/282] Loss: 16.065802 [0/20][140/282] Loss: 15.806343 [0/20][160/282] Loss: 15.621722 [0/20][180/282] Loss: 15.718269 [0/20][200/282] Loss: 15.642500 [0/20][220/282] Loss: 15.453972 [0/20][240/282] Loss: 15.550603 [0/20][260/282] Loss: 15.239004 Traceback (most recent call last): File "train.py", line 166, in cost = trainBatch(net, criterion, optimizer, train_iter) File "train.py", line 77, in trainBatch t, l = converter.encode(cpu_texts) File "/opt/crnn/lib/convert.py", line 52, in encode index = self.dict[char] KeyError: '\ufeff'

joeqincai commented 5 years ago

你提前按键终止了，loss降不下来，可能修改lr------------------ 原始邮件 ------------------ 发件人: "ShangLe0607"notifications@github.com 发送时间: 2019年10月30日(星期三) 上午10:26 收件人: "AstarLight/Lets_OCR"Lets_OCR@noreply.github.com; 抄送: "joeqincai"827173695@qq.com;"Mention"mention@noreply.github.com; 主题: Re: [AstarLight/Lets_OCR] train 数据集时候，未收敛便提前终止了，并且和题主给的训练图片也不太一样，len(train_loader)输出的是7，不知道哪里出错了 (#68)

@joeqincai 你好，我的训练的报错是这个，求助一下大佬这是什么原因呢？？ [0/20][20/282] Loss: 42.145580 [0/20][40/282] Loss: 19.428555 [0/20][60/282] Loss: 17.523825 [0/20][80/282] Loss: 16.701580 [0/20][100/282] Loss: 16.425825 [0/20][120/282] Loss: 16.065802 [0/20][140/282] Loss: 15.806343 [0/20][160/282] Loss: 15.621722 [0/20][180/282] Loss: 15.718269 [0/20][200/282] Loss: 15.642500 [0/20][220/282] Loss: 15.453972 [0/20][240/282] Loss: 15.550603 [0/20][260/282] Loss: 15.239004 Traceback (most recent call last): File "train.py", line 166, in cost = trainBatch(net, criterion, optimizer, train_iter) File "train.py", line 77, in trainBatch t, l = converter.encode(cpu_texts) File "/opt/crnn/lib/convert.py", line 52, in encode index = self.dict[char] KeyError: '\ufeff'

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

ShangLe0607 commented 5 years ago

@joeqincai 我没有提前按键中止，是运行到这里报错了