Comments (6)
Hi, it doesn’t matter.
-
You really need more data, maybe
100000
sample for1000
classes. -
But even 100 samples should print loss either. Change the
batchSize
inparams.py
to1
and see what will happen. If there is still nothing printed, it’s not the sample problem.
from crnn-pytorch.
Hi, check the file size of your lmdb file. I guess you didn’t access the image successfully. The txt
file should looks like
absolute/path/to/your/image/1.jpg
المفضل
If there are still problems, you can tell me.
from crnn-pytorch.
I checked the lmdv files and they are 100 KB and 9 KB for training and 70 KB and 8 KB for val. They are small because I am using small data (100 sample). My txt files look like your example.
/Volumes/EXTERNAL/Models/crnn_pytorch-master/to_lmdb/val_images/img_almofdalh_11.jpg
المفضل
from crnn-pytorch.
Hi, check the following params in params.py
# training process
displayInterval = 100 # interval to be print the train loss
valInterval = 1000 # interval to val the model loss and accuray
saveInterval = 1000 # interval to save model
n_test_disp = 10 # number of samples to display when val the model
Look at the comment and you will know the reason is that your training sample amount didn’t reach the displayInterval
valInterval
...so change them smaller, for example 100%64=1
is ok for you(64 is the batch size)
from crnn-pytorch.
Thank you for your reply, and sorry for asking so many question. I made the changes that you suggest, but still does not print the loss. It just run for 15 - 20 mins and stop. I may need more data, right?
from crnn-pytorch.
I changed the batchSize, and it start printing.
Thanks
from crnn-pytorch.
Related Issues (20)
- KeyError : ' ' HOT 1
- Problem loading checkpointed model
- inference accuracy HOT 10
- Output indicates "PAD" char for all columns HOT 3
- Train problem HOT 1
- A question about pre-trained model HOT 3
- Problem about ctc_loss variable input_length while training HOT 1
- Mean vals and norm vals
- No predictions when training or testing the net !!!
- create image Tensor HOT 2
- Traanning Question HOT 3
- number images train
- Training Problems HOT 2
- 梯度爆炸,loss显示持续显示为inf HOT 1
- img.sub_(0.5).div_(0.5)
- 运行demo用cenn.pth预训练模型显示Expected 512, got 64
- val loss:nan, accuray:0 HOT 1
- [Friendly reminder] About the accuracy of demo.py
- val gpu slow HOT 1
- size mismatch for rnn.1.embedding.weight
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.