search

jiegzhan / multi-class-text-classification-cnn

Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN (Convolutional Neural Network) and Word Embeddings on Tensorflow.
Apache License 2.0
426 stars 198 forks source link

Accuracy on test set is {} based on the best model {} ????????? #20

Open lemo2012 opened 6 years ago

lemo2012 commented 6 years ago

In you codes, the accuracy on test set is based on the latest model after all the train step finished, not based on the best model saved in checkpoint. Am I right?

changukshin commented 6 years ago

No. Please see step 6.2 in train.py

The variable ‘path’ is the path of best model. Not the latest model.

We assume the least validation loss model is the best model.

Please look forward about ‘validation based early stopping’.