I'm following this https://software.intel.com/en-us/articles/tensorflow-optimizations-on-mo
I am interesting to know if there is any easy way to optimize TensorFlow performance on Intel Atom CPU w/o Nvidia GPU installed.
Hi, I'm a mechanical engineering student but I came across about an idea regarding using neural network as the driver or part of the driver for intel iGPUs itself to drive intel HD graphics compone
I have installed tensorflow on my Xeon Phi (Knights Landing with 288 logical cores) as per these links:
I am having issues with operating cluster. I thought it would be better if someone could tell me how to train my cnn (train.py) from the github repository
I have the ImageNet data and want to test Intel Caffe on it. I am reading lot of tutorials, however I am getting confused how exactly is this raw data used.
Currently, I'm developing a medical diagnosis engine (https://devmesh.intel.com/projects/machine-diagnosis).
I only see 4 weeks of material for the two ML classes. Am I missing something, or have the subsequent weeks just not been released yet?
When i run this program of CNN on my laptop epoch is around 5 seconds, but when i run the following on cluster ETA to compute eone epoch is around 60- 80 seconds.