import tensorflow as tf from tensorflow.contrib.layers import flatten import cv2 import numpy as np def LeNet(x): # Hyperparameters mu = 0 sigma = 0.1 # SOLUTION: Layer 1: Convolutional. Input = 32x32x1. Output = 28x28x6. conv1_W = tf.Variable(tf.truncated_normal(shape=(5, 5, 1, 6), mean=mu, stddev=sigma)) conv1_b = tf.Variable(tf.zeros(6)) conv1 = tf.nn.conv2d(x, conv1_W, strides=[1, 1, 1, 1], padding='VALID') + conv1_b # SOLUTION: Activation. conv1 = tf.nn.relu(conv1) # SOLUTION: Pooling. Input = 28x28x6. Output = 14x14x6. conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID') # SOLUTION: Layer 2: Convolutional. Output = 10x10x16. conv2_W = tf.Variable(tf.truncated_normal(shape=(5, 5, 6, 16), mean=mu, stddev=sigma)) conv2_b = tf.Variable(tf.zeros(16)) conv2 = tf.nn.conv2d(conv1, conv2_W, strides=[1, 1, 1, 1], padding='VALID') + conv2_b # SOLUTION: Activation. conv2 = tf.nn.relu(conv2) # SOLUTION: Pooling. Input = 10x10x16. Output = 5x5x16. conv2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID') # SOLUTION: Flatten. Input = 5x5x16. Output = 400. fc0 = flatten(conv2) # SOLUTION: Layer 3: Fully Connected. Input = 400. Output = 200. fc1_W = tf.Variable(tf.truncated_normal(shape=(400, 200), mean=mu, stddev=sigma)) fc1_b = tf.Variable(tf.zeros(200)) fc1 = tf.matmul(fc0, fc1_W) + fc1_b # SOLUTION: Activation. fc1 = tf.nn.relu(fc1) # SOLUTION: Layer 4: Fully Connected. Input = 200. Output = 200. fc2_W = tf.Variable(tf.truncated_normal(shape=(200, 200), mean=mu, stddev=sigma)) fc2_b = tf.Variable(tf.zeros(200)) fc2 = tf.matmul(fc1, fc2_W) + fc2_b # SOLUTION: Activation. fc2 = tf.nn.relu(fc2) # SOLUTION: Layer 5: Fully Connected. Input = 200. Output = 147. fc3_W = tf.Variable(tf.truncated_normal(shape=(200, 147), mean=mu, stddev=sigma)) fc3_b = tf.Variable(tf.zeros(147)) logits = tf.matmul(fc2, fc3_W) + fc3_b return logits # Create placeholders for training data, # x is a placeholder for a batch of input images. y is a placeholder for a batch of output labels. x = tf.placeholder(tf.float32, (None, 32, 32, 1)) logits = LeNet(x) saver = tf.train.Saver() # load checkpoint and make prediction with tf.Session() as sess: # read one input image from disk im = cv2.imread('test3.jpg') im = cv2.cvtColor(im, cv2.COLOR_RGB2GRAY) im = cv2.resize(im, (32, 32), interpolation=cv2.INTER_NEAREST) im = 255 - im # for jpeg white is 255 black is 0, we revert so that white is 0 and black is 255 im = np.divide(im.astype(np.float32), 255) # expand dims for input image im = np.expand_dims(im, axis=-1) im = np.expand_dims(im, axis=0) # restore training session and make prediction saver.restore(sess, tf.train.latest_checkpoint('.')) prediction = sess.run(logits, feed_dict={x: im}) # sorted indices sorted_index = np.argsort(-prediction) print sorted_index

## Friday, 14 July 2017

### Making predictions from images with models trained with the TensorFlow LeNet tutorial

Suppose we have trained a model with the TensorFlow LeNet tutorial, as outlined in this post. The following codes would allow you to read an image from disk, and make predictions with the trained LeNet model:

Subscribe to:
Posts (Atom)