So basically you are basing your assumptions on an older release, when we repeatedly mentionned that newer versions should improve.
Your behavior could be explained by so many implementations details, and yet you are focusing on solving the wrong issue.
The blog post I linked to, which I guess you didn’t look at, indicates that streaming has improved a lot with respect to latency since 0.5.1.
The streaming API gives the exact same output as feeding the entire file at once. If you’re seeing differences, it’s likely a bug in your code. For example, you could be dropping frames.
Yes. The reason being I’ll have to train with transfer learning on 0.6.x. I’m reading all 0.6.x files now and thanks a lot, I’ll take this up now.
I’m looking at it now and will take this up and see how fast we can move to 0.6.x (as we’ve to retrain as well).
I’m looking at it. Surely that could be the case. I’ll analyse it if that is the real problem. But I’ll do that once we update to the newer version.
Just a small thing here, for 0.7.x-stable, what’re the timeline?
Please rely on current master for transfer learning. The old transfer-learning2 branch is deprecated and dead, features has been merged properly.
Okay. So I’ll use the master branch. That seems a major change. Congrats for the merger.
Congrats goes to @josh_meyer and @reuben. I just played the role of the painful guy constantly asking @josh_meyer to merge.