Ah, that’s understandable, although I’m worried about the internet already being overloaded. We will share the slides and video afterwards for you to catch the extra details
@renjithmadhavan OpenCV is commonly used for computer vision, although it can definitely be a pain to configure
With the high level APIs now in Tensorflow, what is going to be the difference b/w Keras API and TensorFlow API?
Would we have an example on how to solve gradient saturation with the tensorflow tools ?
I also read that tensorflow officially supports keras. So what is the difference between keras and the high level api in TF ?
OpenCV is commonly used, although you might find a lot of overlap with scikit-image and scipy.ndimage (which are both simple conda installs).
about productionalizing deep learning application:
- is there an idea for using deep learning on AWS lambda
btw: I would like to work on that as an project
does precompiling mean, that we will write tensorflow code/test it and when we train a big model, than we precompile the code and train our model?
All videos from TF Summit here: https://www.youtube.com/playlist?list=PLOU2XLYxmsIKGc_NBoIhTn2Qhraji53cv
What is the relationship between TF and Pytorch
Can we use TF and Torch together, like some part of code in one rest in other?
Doesnt the batch size also depend heavily on the video ram ?
Or does just upgrading RAM allow bigger batch sizes?
He’s talking about GPU RAM.
For keras with TF, this is helpful for larger batch sizes if you have multiple GPUs (splits batch across your GPUs for easy data parallelization):
I can confirm NVMe drives are awesome. Just got a Samsung Evo 960. In conjunction with bcolz it is really amazing.
I got this idea from part 1 … that deep learning can be used for any machine learning problem( including non-image data sets ) with very good results. Is this a true statement? Does this mean traditional ML methods such as decision tree, linear regression need not be used . Is there a problem where you think deep learning may not be a good idea ?
I’m currently using a Google Cloud Engine instance. It’s not bad. Close to the same price as AWS, but they use Titan X Pascal GPUs.
Good question @renjithmadhavan ! We will be using deep learning on structured, time-series data in a later session
Edit: I meant class session in this course
Its annoying to setup, but its nice though
Where to find the current research papers?