NOTE: For users interested in multi-GPU, we recommend looking at the newer cifar10_estimator example instead.
CIFAR-10 is a common benchmark in machine learning for image recognition.
http://www.cs.toronto.edu/~kriz/cifar.html
Code in this directory demonstrates how to use TensorFlow to train and evaluate a convolutional neural network (CNN) on both CPU and GPU. We also demonstrate how to train a CNN over multiple GPUs.
Detailed instructions on how to get started available at:
http://tensorflow.org/tutorials/deep_cnn/
changed in cifar1.py local3 and local4 from fully-connected to locally-connected
output is changed to probability using tf.nn.softmax