Comments (7)
did you run it with adadelta?
from crnn.pytorch.
When I use the pretrained model @meijieru offers, the problem gone, so maybe I have not get enough data to train my model from scratch.
from crnn.pytorch.
I have solve the problem,adadelta or adam is ok @abhiML. I use 800 pictures to train crnn from scratch, which is stupid , when I use the retrained model, the problem disappear.
Here is what I got:
from crnn.pytorch.
Well I was using adam on the Synth dataset. It showed me infinite loss. But when I used adadelta it ran perfect. I did not use the pretrained model.
from crnn.pytorch.
@abhiML It should be the learning rate problem that bothers you, because adadelta requires no manual setting of a learning rate, so when using some momentum methods like adam, you should carefully set the initial learning rate, 1e-3 works well in my situation.
from crnn.pytorch.
Since it has been solved, I closed this issue temporally. Feel free to re-open it when necessary.
from crnn.pytorch.
I also encountered the same situation, because my data set was self-built. Is there any other way besides loading the pre-trained model?
from crnn.pytorch.
Related Issues (20)
- About loss HOT 1
- loss值是特别大,但是还不知道那么下降,怎么解决这个问题?
- Height of image to 1
- Why My CTC Loss is always Nan or Inf value? HOT 6
- 出现报错RuntimeError: CUDA error: an illegal memory access was encountered HOT 3
- 不收敛,loss下降到15左右就震荡不动了 HOT 3
- What is the difference between warp_ctc_pytorch.ctcloss and torch.nn.ctcloss? HOT 3
- 训练icdar2015
- 训练自己的数据时报错:an illegal memory access was encountered HOT 1
- Utility of method oneHot in utils.py
- Is it normal for the model to predict the same string for the whole train batch and val?
- raise UnidentifiedImageError( PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x0000024631A5E360> HOT 1
- CRNN过拟合求解The Problem Of Overfitting
- The Problem Of Over fitting过拟合问题
- The loss occurred in Nan's case,What is the reason? HOT 1
- 关于模型结构最后两层的BN层 HOT 1
- Why is the pooling layer in the network different from the 1 * 2 pooling in the original paper?
- thi project support python3?
- 训练数据集用的是什么??? HOT 1
- RuntimeError: CUDA error: an illegal memory access was encountered HOT 1
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 crnn.pytorch.