Gaurav Bhatt

You need to set `random_state` parameter in the `skrnn_sample` module. By default it is set at `98`, that's why you are getting same image for multiple calls. While sampling from...

This is not an error. The ```dl.process_data``` module simply prints some of the unknown/undefined words in the pre-trained model. We are using GloVe pre-trained embeddings which have been trained on...

Can you post the issue?

What is the size of your dataset? You need to have a sufficient dataset for your model to learn anything.

Have a look at the following links:- https://www.kaggle.com/c/sentiment-analysis-on-movie-reviews https://www.kaggle.com/bittlingmayer/amazonreviews https://datascience.stackexchange.com/questions/11220/training-dataset-for-sentiment-analysis-of-movie-reviews

@sachka is right. When you set the **train** value as **false**, the number of trainable parameters are reduced. This could help to converge quickly. 

This may not be a really optimised solution but slowing the downloading rate helps to bypass the "too many request error". Use the following bash script to download audioset. Currently...