Comments (15)
修改main.py line 231:
for i, e in enumerate(train_loader):
images = e.images
targets = e.targets
target_lengths = e.target_lengths
可以跑了
from sightseq.
Hi @jianghonggang , you should rename data_dev.txt to dev.txt and data_train.txt to train.txt, I forget to give this information.
from sightseq.
Hi @jianghonggang , you should modify data_dev.txt to dev.txt and data_train.txt to train.txt, I forget to give this information.
I have modified dataset.py 25 line:
label_path = os.path.join(data_root, '{}.txt'.format(mode)) to
label_path = os.path.join(data_root, 'data_{}.txt'.format(mode))
from sightseq.
好吧,北京的同学,我们还是中文交流吧
from sightseq.
好吧,北京的同学,我们还是中文交流吧
Jiang 准备跑什么数据,可否告知一下?
from sightseq.
现在跑的是Chinese_dataset.rar解压后的数据,还没上自己的训练数据。
from sightseq.
我现在没有硬件(gpu)测试模型,线上放的模型是一个 epoch 出来的结果(Chinese dataset 这个准确率是 97.5%),多跑两个 epoch 准确率应该有进一步提升,如果方便,可以 push 一下模型出来
from sightseq.
现在的问题是程序跑不起来,运行main.py时报错:
TypeError: 'DigitsBatchTrain' object is not iterable
from sightseq.
现有的参数如果不收敛,可能需要加 criterion = nn.CTCLoss(zero_infinity=True)
需要最新的 pytroch nightly 版本。
from sightseq.
现在的问题是程序跑不起来,运行main.py时报错:
TypeError: 'DigitsBatchTrain' object is not iterable
python 3.6+?
from sightseq.
python: 3.6.8
pytorch: 1.0.1
from sightseq.
--alphabet ./data/alphabet_decode_5990.txt
这个参数呢?
from sightseq.
对,是这个参数
from sightseq.
./data/images
文件夹下应该没有子文件夹
from sightseq.
修改main.py line 231:
for i, e in enumerate(train_loader): images = e.images targets = e.targets target_lengths = e.target_lengths
可以跑了
好诡异,不知道 python 有这个操作,估计是 DigitsBatchTrain
这个类写得不规范
from sightseq.
Related Issues (20)
- Help Needed HOT 7
- Questions about dataset object HOT 4
- RuntimeError: CUDA error: an illegal memory access was encountered HOT 7
- loss become inf , then Nan HOT 18
- 中文识别率不高问题 HOT 20
- Input size HOT 1
- dimensions in forward pass HOT 4
- 中文识别率不高是不是因为感受野的原因? HOT 16
- 有关loss变为nan的情况,我看了之前的解答,但还是想问问 HOT 2
- Getting accuracy as 0.00 HOT 1
- 关于加载预训练模型的问题 HOT 1
- How is the picture processed in sequence_generate? HOT 1
- 能提供新的依赖版本么? HOT 5
- The vanilla cnn downsampling architecture cannot recover spatial information of a image HOT 1
- annotation file format for English data HOT 2
- Not found recurrent layer in model files HOT 1
- Must the training data be of equal length? HOT 1
- 训练结果在其他图片上的结果很差? HOT 3
- 同一批测试数据,test-only 的accuracy和 训练时的validate accuracy 差很多? HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sightseq.