VAE loss and classification accuracy

[yuyingg0921]

hi :) sorry to bother you again
I tried train_vae.py to train a vae model without competition layer but got high loss (60-70).
(and dimension is 128)
earlystopping happened in about 20-50 epoch though I already tried a larger patience.
The loss includes kld and reconstruction error but is this loss value in normal scale?
and then I used pred_vae.py to predict 20news document embeddings.
but after running run_classifier.py, I can only get about 22% classification accuracy.

Do you have any suggestion for improving the vae model!?
thank you

[hugochan]

@yuyingg0921 You should be able to get reasonably good results using VAE. Can you share your hyper-parameters when training the model?

[yuyingg0921]

yes. most parameters are default value.
batch size =100
validation size = 1000
epoch = 100
dimensions = [128,128] , [512/512]
I also tried with and without a competition layer.

train_vae.py:
python train_vae.py -i output_20news/train.corpus -nd 128 128 -sm model_vae

with larger earlystopping patience:

run_classifier.py:

[Somayeh12]

Hi,
I run your code with 20newsgroup, I get the earlystopping too. it stops at epoch 33/100 and the loss is 0.48.
Any suggestion?

[hugochan]

@yuyingg0921 @Somayeh12 You might want to try running the code using the same TensorFlow version as mentioned in requirements.txt. See #24