Taras Ivashchuk

icon indicating a website link http://tarasivashchuk.com icon indicating an email [email protected]

icon company Freelancer @ Upwork icon location Cleveland icon location Machine learning engineer. Avid learner of all things, most of which are useless, occasionally meaningful, but always interesting.

Results 7 comments of Taras Ivashchuk

Change extension logo to match theme of other Python extensions

Awesome – I’ll try to get it done this weekend! From: Nils Werner Reply-To: NilsJPWerner/autoDocstring Date: Tuesday, July 21, 2020 at 12:42 AM To: NilsJPWerner/autoDocstring Cc: Taras Ivashchuk , Author...

Add TPE Optimizer

I might look at implementing this over the weekend. No promises or anything, but I'm definitely intrigued and have my ears perked up at attention (figuratively, obviously 😅). If anyone...

Add TPE Optimizer

> @JonnoFTW We don't currently have plans to implement this algorithm here but it's something we are considering for the future > > If anyone is interested in implementing this...

Is this only works for Feed Forward?

This will work for Model object (keras.models.Model or tf.keras.models.Model) as long as the optimizer function used when compiling the model has a "learning_rate" parameter. Actually, I just checked the code...

Why does this lr_finder use training loss instead of validation loss?

I might take a look at this today if I have some free time and submit the pull request. That is unless you have already started and wanted to finish...

Why does this lr_finder use training loss instead of validation loss?

@alleno-yu Ok, I'm going to wait to hear back from @surmenok to make sure he's on board with that solution

Add explainshell docker image to repository/docs

@wscherphof Thank you so much! They should honestly update the explainshell repo with that Docker image since the one there doesn't work because of Python 2 being phased out and...