Sandeep Thapa

@pandababyer I have experimented with a couple of models that do the regression with sigmoid to output the frame importance score. Because the frame score is so sparse (at least...

> Here is the [link](https://drive.google.com/open?id=14tcW0T6ps9FQmbqmtHW3OG5lqodCeg78). Thanks for this.

FIX: Go to core.py file inside ttf folder. In the in the init function change optimizer to tf.keras.optimizers.Adam(....). Why? Read the following: https://stackoverflow.com/questions/55682718/module-tensorflow-api-v2-train-has-no-attribute-gradientdescentoptimizer

I found the solution. Adding ` await page.setExtraHTTPHeaders({ 'Accept-Language': 'en-GB,en-US;q=0.9,en;q=0.8' }); ` ` await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36') ` and setting headless...

> I ended up using [fastFM](https://github.com/ibayer/fastFM) and ultimately, when we went to production, we used ALS on pySpark. Another option is perhaps trying [lightfm](https://github.com/lyst/lightfm). Good luck! fastFm does not support...