Introduction to Deep Learning with Python
Why Stack Overflow recommends it
Stack Overflow users link it as a hands-on Theano tutorial, both to help others with neural network code and as the source people follow when their own implementations break.
Recommended by 1 people across 1 different months, 2015 to 2016.
What it is
A 2014 conference talk by Alec Radford of indico Data Solutions on deep learning in Python using the Theano library. It covers high performance computing, recurrent neural nets for natural language processing, and large-scale learning on GPUs, with companion slides and a GitHub tutorial repo.
What people said
Recommends Aabglov · 2015-09 · Stack Overflow · on “Impute multiple missing values in a feature-vector”
Glad it helped. If you get stuck with the Neural Network stuff or general Theano coding this video is a really good: [this video] All the code from it is on github. I reference it all the time: [LINK]
Cites anthonybell · 2015-02 · Stack Overflow · on “Theano - logistic regression example weight vector becomes NaN?”
I am doing a tutorial (code here [LINK] ) and video here [this video] (13:00 minutes in). My only change is using the mnist training set from a different location (creating a one-hot encoding) but it is not working. I literally copy-pasted all the code (except for the mnist loading) in this example. Here is the code: import theano from theano import tensor as T import numpy as np from sklearn.datasets import fetch_mldata mnist = fetch_mldata("MNIST Original") trX, teX, trY_digit, teY_digit = train_test_split(mnist.data, mnist.target, test_size=.4) #Get one-hot encoding enc = OneHotEncoder() enc.fit([[n] for n in range(10)]) trY, teY = sparse_to_floatX(enc.transform(trY_digit[:,newaxis])), sparse_
Cites bjotta · 2016-03 · Stack Overflow · on “Theano: expected 2, got 1 with shape (128,).')”
Im trying to make a neural network. I have followed the video from [this video] I have loaded the adult.data training set. I am now on my way of training and i have these lines where the code fails. while(epocs<5): i = 0 for start, end in zip(range(0, len(trX), 128), range(128, len(trX), 128)): print(trX.shape) tr = trX[start:end] print(tr.shape[0]) print(tr.shape[1]) self.cost = train(tr.reshape(tr.shape[0],tr.shape[1]), trY[start:end]) epocs+=1 I am strugling with an error message which is: n.training() File "C:\Users\Bjornars\PycharmProjects\cogs-118a\Project\NN\Network.py", line 101, in training self.cost = train(tr.reshape(128,106), trY[start:end]) File "C:\Anaconda3\lib\site-packages\theano