Lesson 8 in-class


(Rachel Thomas) #41

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


(Rachel Thomas) #42

@renjithmadhavan OpenCV is commonly used for computer vision, although it can definitely be a pain to configure


(Hamel Husain) #43

With the high level APIs now in Tensorflow, what is going to be the difference b/w Keras API and TensorFlow API?


(Kouassi Konan Jean-Claude) #44

Would we have an example on how to solve gradient saturation with the tensorflow tools ?


#45

I also read that tensorflow officially supports keras. So what is the difference between keras and the high level api in TF ?


(David Gutman) #46

OpenCV is commonly used, although you might find a lot of overlap with scikit-image and scipy.ndimage (which are both simple conda installs).


(Benedikt S) #47

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 :slight_smile:


(Benedikt S) #48

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?


(Alex Izvorski) #49

All videos from TF Summit here: https://www.youtube.com/playlist?list=PLOU2XLYxmsIKGc_NBoIhTn2Qhraji53cv


#50

What is the relationship between TF and Pytorch


(Kishore P. V.) #51

Can we use TF and Torch together, like some part of code in one rest in other?


#52

Doesnt the batch size also depend heavily on the video ram ?
Or does just upgrading RAM allow bigger batch sizes?


(David Gutman) #53

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):


(Constantin) #54

I can confirm NVMe drives are awesome. Just got a Samsung Evo 960. In conjunction with bcolz it is really amazing.


(RENJITH MADHAVAN) #55

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 ?


(Rachel Thomas) #56

@iNLyze We will be talking about bcolz later in the course :slight_smile:


(James Puderer) #57

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.


(Rachel Thomas) #58

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


(Samuel Ekpe) #59

Its annoying to setup, but its nice though


(sai kiran) #60

Where to find the current research papers?