Ferran Pérez Gamonal

Hello @martinv , I am currently doing my MsC thesis in Optical Flow interpolation and I've taking a look at testing unsupervised learning for OF estimation too. That is why...

Hello all, Just as @kyamagu, I run into this problem after migrating from TensorFlow 1 to the latest 2.9.1. In my case, the information is properly reported per batch in...

Hello! I really don't know. I guess it depends on how they define the optional symbols to be included in the `dll` for these versions (probably with the file `patches/def_file_filter.py.tpl`)....

Hello @cocoyen1995 I'm very sorry, I didn't get your message. I'm glad you managed to compile it (it's not an easy task!). I'm currently trying to compile Tensorflow 2.6.0 for...

Hi again, I've successfully compiled TF 2.6.0 with the following configuration: - Python 3.9.6 - CUDA 11.2 - cuDNN 8.1 - MSVC 2019 - MSYS2 v6.0.0 (20210725) I have updated...

Hello, I am running into the same problem. Have you found a solution? As I am working in a cluster, I have found that I have to wait a lot...

I tried to disable all transformation done regarding colour (*dataset_configs.py* from 'image_b' downwards) to no avail. For now I use Data augmentation on the CPU successfully but it requires a...

Hello, Months ago I compiled successfully the custom ops in a machine running Ubuntu 18.04LTS, CUDA 10 and Tensorflow-gpu 1.13.1. Nevertheless, a colleague in the research group has granted me...

Final update: after fighting with it for quite a few days and with help with my university's IT staff, I got it solved. A soft link for cuda.h was the...

Hello @seni04 the technical stuff told me they had fixed by creating a soft link between the actual cuda version on the PC and the "standard" path where it is...