Comments (11)
What do you mean with it stops? Is the accuracy not increasing anymore? Is the script crashing? ...?
from crnn-lid.
@Bartzi Yeah The validation accuracy is not increasing for last 9 epochs.
from crnn-lid.
Well, in order to help. I would need more information. What are you training on? Your own data? What is the current validation accuracy? Did you change anything in the code? What is your train configuration?
from crnn-lid.
Yes I am training on my own Data. Dataset contains English and Japanese audios.
Current validation accuracy 0.84.
Training configuration:
batch_size: 64
learning_rate: 0.001
num_epochs: 50
data_loader: "ImageLoader"
color_mode: "L" # L = bw or RGB
input_shape: [129, 500, 1]
model: "topcoder_crnn_finetune" # _finetune"
segment_length: 10 # number of seconds each spectogram represents
pixel_per_second: 50
label_names: ["EN", "JP"]
num_classes: 2
from crnn-lid.
It could be that your model converges, or that your learning rate is too high at this point. You could add a callback that scales the learning rate of the Adam optimizer, maybe that helps.
from crnn-lid.
@Bartzi Thanks a lot for your suggestion! Would you kindly tell me how can I modify callback object in training script to scale the learning rate?!
from crnn-lid.
The best tip is to have a look at the documentation of Keras 😉
This page, for instance, could be helpful: https://faroit.com/keras-docs/1.2.2/callbacks/
from crnn-lid.
@Bartzi Thanks a lot!
I found : ReduceLROnPlateau
.
We can add this to update the learning rate if the accuracy doesn't improve after certain epochs.
Currently the learning rate we are using is 0.001
.
Can you suggest me the lower bound for lr ?
Actually I cannot guess how less will be too less!
from crnn-lid.
As with most things in Deep Learning: You have to try. But my first idea would be to set it to 0.0001
and see what happens. Going any lower than 1e-6
as starting learning rate is not a good idea, so that would be too low.
from crnn-lid.
@Bartzi Thanks a lot.
The model still converges. Stops at epoch 23. No improvement of validation accuracy for last 20 epochs.
early_stopping_callback = EarlyStopping(monitor='val_loss', min_delta=0, patience=15, verbose=1, mode="min")
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=5, min_lr=0.0001)
I collected the data from youtube. The problem is My dataset is not so big. Only 3328 mel-spec images for training set.
Problem occurred while downloading data. Youtube_dl sent too many requests
error. So I couldn't download as much data as I wanted.
Can it be a problem with my data? Am I trying to train on really poor data?!
from crnn-lid.
Yes, that low amount of training data might very well be a problem.
Maybe you can try to gather more data, I think this should help with your results.
from crnn-lid.
Related Issues (20)
- Train issue. HOT 2
- Training steps. HOT 9
- train.py error
- Train error with finetune_crnn model. HOT 4
- voxforge download script is corrupted on OSX Catalina
- Failing to import model package HOT 2
- Fails to load weight file HOT 4
- value of nb_val_samples is none: validation_data_generator.get_num_files() returns 0 HOT 1
- Size issue with convolutions HOT 2
- Training comes to a stand-still
- Predict new audio - audio is not found HOT 15
- Unable to open model HOT 5
- on the usage of an additional labels HOT 1
- "SpectrogramGenerator Exception: [Errno 2] No such file or directory: 'tmp_images/tmp_91484.png' audio_segment/malayalam" HOT 4
- Delete this issue
- downloading dataset error
- SpectrogramGenerator Exception: [Errno 2] No such file or directory: HOT 3
- Changing to shorter segments HOT 1
- Model Overfitting HOT 2
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-lid.