Maxim Podkolzine
Maxim Podkolzine
@bautroibaola This is a common problem in ML: there is no way to tell the model is ready. What people usually do is train it as long as they have...
@bautroibaola The current model is predicting exactly 1 step ahead. You have the following options: - Select a large time period, say a week (but you'll have much less data...
Hi @ochoch I think you're right. At that time I thought it was a good idea to shuffle the data, but I now I'd say it leads to overfitting and...
Hi @ochoch sorry for the delay. Unfortunately that's the way it is: there is so much noise and so little signal in financial data. If you are able to find...
@huazai665 Sure! You can plug in in different places depending on how different your data is from poloniex data. The simplest option is to transform your market data to the...
Thanks @soham-samanta. But I'm not sure I understand how the change improves the readme?
Your issue is unclear. Please provide the original spec that you used, the output and then changes that you've made.
Thanks for report. This is so strange, readme file is all ASCII. I'll try to reproduce it when I have some free time On Tue, 1 May 2018, 15:16 Jianyi...
@AlexanderFreeman Yeah, this case isn't covered by current examples. What model do you use? And what TF API? By the way, you don't see any variables because they're hidden in...
Unfortunately, it doesn't work that easily. You can load a model which graph matches exactly to the defined graph. For example, if you use [TF slim API](https://github.com/tensorflow/models/tree/master/research/slim), you can load...