TensorFlow – Consise Examples for Beginners
1–10 of 32 posts
Re: TensorFlow – Consise Examples for Beginners
#2Can we get a mod fix on the title?
Re: TensorFlow – Consise Examples for Beginners
#3I find it so aggravating that nearly every last ML framework documents their CNN libraries in terms of canned MNIST datasets imported from the library in a preprocessed form.
It's always left as a useless exercise for the reader to divine how to generate such a dataset from his/her own data.
Examples should be way more general. The starting point shouldn't be:
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
EDIT: Should anyone have any insight as to where I might get such a tutorial (or have the desire to write one), I know a herd of ML pre-initiates that would be grateful.
Re: TensorFlow – Consise Examples for Beginners
#4curated list of dedicated resources: https://github.com/jtoy/awesome-tensorflow
Re: TensorFlow – Consise Examples for Beginners
#5Great examples! I find it more accessible for me than the official tutorial.
Re: TensorFlow – Consise Examples for Beginners
#6I am looking for a TensorFlow resource that shows how to classify images of a certain kind. For example: given 100 images, find the ones that might contain a soccer ball. I haven't come across such a learning resource with TensorFlow. Has anyone else?
Re: TensorFlow – Consise Examples for Beginners
#7Anyone know of any benchmarks on tensorflow that provide a baseline estimate of the expected performance for some off-the-shelf hardware(s)?
Re: TensorFlow – Consise Examples for Beginners
#8This is missing a FizzBuzz example.
Re: TensorFlow – Consise Examples for Beginners
#9Thanks for this! I recently ported something over from Theano to TensorFlow (I wrote it up at [1]) and I have to admit I generally enjoyed the experience a great deal, even if the single-GPU performance wasn't good enough to make me switch. The TFLearn library (especially [2]) looks very compelling for prototyping however, some I'm very excited to see how the project develops.
[1] https://medium.com/@sentimentron/faceoff-theano-vs-tensorflo...
[2] https://github.com/tflearn/tflearn/blob/master/examples/nlp/...
Re: TensorFlow – Consise Examples for Beginners
#10I find it so aggravating that nearly every last ML framework documents their CNN libraries in terms of canned MNIST datasets imported from the library in a preprocessed form. It's always left as a useless exercise for the reader to divine how to generate such a dataset from his/her own data. Examples should be way more general. The starting point shouldn't be: from tensorflow.examples.tutorials.mnist import input_dat…
+1
That and the fact that way too many ML examples/tutorials take a very academic/theoretical stance where they are making the model purely for the sake or it, and the tutorial basically ends with a statement like "Our loss is 0.0034!" which I am sure is great if you are a data scientist, but for people just getting started (e.g. me) it is not helpful since I want to know how I can do real-world stuff with ML, not just intellectual-masturbation/maths-for-the-sake-of-maths etc.
I would love to see some more "real world" examples that go from "data files in a directory" to not only a CNN, but also an actual "..and here is how we actually use our model in a real-life web application to do something useful: "