Tensorflow 1.x to 2.x

I changed the only function from Tensorflow 1.x of TempoGAN that I mentioned in this post, from

tf.contrib.layers.batch_norm()

to

tf.compat.v1.layers.batch_normalization()

and, of course, the pre-trained weights are useless now that I changed the net structure. So, I need to retrain it, but there is no script to do it. I can do one myself and be very careful when choosing the parameters. Or, I use Google Colab to run the original net for me.

You may have noticed that Google Colab does not support Tensorflow 1.x anymore, right? But no worries. I've found a way to overcome this with miniconda here.

I'm back

Hello. It's been a a while. Not yet back to normal, but as normal as it can be.

I'm here to tell about an error I got while trying to run the TempoGAN on a brand new server. The error happens when "session.run" is called, and it gives:

Internal: Blas SGEMM launch failed : m=216000, n=32, k=4

If you search on the internet, everyone will tell this is due to lack of memory in the GPU. Ok, this net is quite large but... I have 48GB available to me! This net can't be that greedy.

So, what did I found? Yes, it needs more memory in the graphics card... BECAUSE IT IS NOT ALLOCATING ANY!  The code is from 2018, the GPU architecture is modern, and cuBLAS from CUDA 10 does not know how to do its job.

I'm sorry, but you and I will have to upgrade the code to Tensorflow 2.X.

Good luck for us. 

Trying to return to normal

Hello. 

I am having troubles with 3 estate inventory deeds and an eviction action, which are taking a lot of my time. But I hope this year all of them will be solved. Until then, I need to raise money for all the taxes, fine, interests and court costs related to it. So I am really focused on my work, and that's why there were no updates here.

But the first thing I'll do is to post the code of the simple Toy Model net to learn the traingle area,

See you soon.

Troubleshoot in Visual Studio 2013 Community

A few days ago I was receiving a message from Visual Studio, telling that my license needed to be updated. Nonsense, I thoutgh. How can a free program have a license to expire? Then, after 30 days, the program was blocked. I tried to sign in again, update my license, but all I got was: 

The underlying connection was closed: An unexpected error occurred on a send.

I followed every single sugestion to solve this, but this error was persistent. 

You know what was it?

I changed my internet provider last month, and I experienced some troubles to get a good connection, despite the high download rates. I returned to my previous internet provider, connected to the VPN of my job, set Firefox as my default browser (I was using Edge), delete the user data with the command "./devenv.exe /resetuserdata" (devenv.exe is in "C:\Program Files (x86)\Microsoft Visual Studio 12.0\Common7\IDE") and I activated the localization system in Windows. Finally the login window showed up, VS 2013 openned and asked me to uptade the license and it was done.

I lost 3 days of work because of this. I hope you don't need to.

Link to practice reading in Japanese

Hello again. 

This time I'm here to share a link with several short books, organized by levels, and with audio (most of them).

Free easy japanese books

This link is also saved in my Japanese page.

Have fun!

Change of plans

In the last post I said I would update the tutorial of the deep learning API. But an urgent matter came first: learn to use SHAP. The subject will be a Toy Model for predicting the area of a 2D triangle based on its points.

The tutorial is not ready yet, but you can check it every week for new content, and the code is not open source yet.

When there is more updates, I'll let you know.

See ya.

Problems with PyTorch in Conda

So... I made a tutorial for using the Deep Lagrangian Fluids, but the training gets stuck in what I suppose it is a deadlock. However, the training works fine with Tensorflow. I know I said it was impossible to install the version I needed via conda (still is), but via pip, it is possible.

I'll post the tutorial update ASAP. There are some differences in the steps. I'm thinking about how to organize them.