andrewschreiber

    # Backprop to get gradient
    label_one_hot = labels[i]
    dy = np.array(label_one_hot)
    for l in range(len(network.layers)-1, -1, -1):
        dout = network.layers[l].backward(dy)
        dy = dout

andrewschreiber

# Create a saliency map for each data point
for i, image in enumerate(data):
    # Forward pass on image
    # Note: the activations from this are saved on each layer
    output = image
    for l in range(len(network.layers)):
        output = network.layers[l].forward(output)

    # Backprop to get gradient
    label_one_hot = labels[i]

andrewschreiber

# Create a saliency map for each data point
for i, image in enumerate(data):
    # Forward pass on image
    # Note: the activations are saved on each layer
    output = image
    for l in range(len(network.layers)):
        output = network.layers[l].forward(output)

    # Backprop to get gradient
    label_one_hot = labels[i]

andrewschreiber

Open jupyter with

$ xvfb-run -s "-screen 0 1400x900x24" jupyter notebook

In Jupyter

import matplotlib.pyplot as plt
%matplotlib inline

After each step

def show_state(env, step=0):

andrewschreiber

#!/bin/sh
# See video https://www.youtube.com/watch?v=7PO27i2lEOs

set -e


command_exists () {
    type "$1" &> /dev/null ;
}