I am attempting to train a CNN model following along with a tutorial, using the exact code specified and am receiving an error. Below is the code I am using.
# Common imports
from __future__ import division, print_function, unicode_literals
import numpy as np
import os
import numpy as np
from sklearn.datasets import load_sample_image
from io import open
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
# to make this notebook's output stable across runs
def reset_graph(seed=42):
tf.reset_default_graph()
tf.set_random_seed(seed)
np.random.seed(seed)
# To plot pretty figures
%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12
# Where to save the figures
PROJECT_ROOT_DIR = "."
CHAPTER_ID = "cnn"
def save_fig(fig_id, tight_layout=True):
path = os.path.join(PROJECT_ROOT_DIR, "images", CHAPTER_ID, fig_id + ".png")
print("Saving figure", fig_id)
if tight_layout:
plt.tight_layout()
plt.savefig(path, format='png', dpi=300)
#A couple utility functions to plot grayscale and RGB images:
def plot_image(image):
plt.imshow(image, cmap="gray", interpolation="nearest")
plt.axis("off")
def plot_color_image(image):
plt.imshow(image.astype(np.uint8),interpolation="nearest")
plt.axis("off")
#Convolutional Layer
china = load_sample_image("china.jpg")
flower = load_sample_image("flower.jpg")
image = china[150:220, 130:250]
height, width, channels = image.shape
image_grayscale = image.mean(axis=2).astype(np.float32)
images = image_grayscale.reshape(1, height, width, 1)
fmap = np.zeros(shape=(7, 7, 1, 2), dtype=np.float32)
fmap[:, 3, 0, 0] = 1
fmap[3, :, 0, 1] = 1
plot_image(fmap[:, :, 0, 0])
plt.show()
plot_image(fmap[:, :, 0, 1])
plt.show()
reset_graph()
X = tf.placeholder(tf.float32, shape=(None, height, width, 1))
feature_maps = tf.constant(fmap)
convolution = tf.nn.conv2d(X, feature_maps, strides=[1,1,1,1], padding="SAME")
with tf.Session() as sess:
output = convolution.eval(feed_dict={X: images})
plot_image(images[0, :, :, 0])
save_fig("china_original", tight_layout=False)
plt.show()
plot_image(output[0, :, :, 0])
save_fig("china_vertical", tight_layout=False)
plt.show()
plot_image(output[0, :, :, 1])
save_fig("china_horizontal", tight_layout=False)
plt.show()
# Simple Example
# Load sample images
china = load_sample_image("china.jpg")
flower = load_sample_image("flower.jpg")
dataset = np.array([china, flower], dtype=np.float32)
batch_size, height, width, channels = dataset.shape
# Create 2 filters
filters = np.zeros(shape=(7, 7, channels, 2), dtype=np.float32)
filters[:, 3, :, 0] = 1 # vertical line
filters[3, :, :, 1] = 1 # horizontal line
# Create a graph with input X plus a convolutional layer applying the 2 filters
X = tf.placeholder(tf.float32, shape=(None, height, width, channels))
convolution = tf.nn.conv2d(X, filters, strides=[1,2,2,1], padding="SAME")
with tf.Session() as sess:
output = sess.run(convolution, feed_dict={X: dataset})
plt.imshow(output[0, :, :, 1], cmap="gray") # plot 1st image's 2nd feature map
plt.show()
for image_index in (0, 1):
for feature_map_index in (0, 1):
plot_image(output[image_index, :, :, feature_map_index])
plt.show()
reset_graph()
X = tf.placeholder(shape=(None, height, width, channels), dtype=tf.float32)
conv = tf.layers.conv2d(X, filters=2, kernel_size=7, strides=[2,2],
padding="SAME")
init = tf.global_variables_initializer()
with tf.Session() as sess:
init.run()
output = sess.run(conv, feed_dict={X: dataset})
plt.imshow(output[0, :, :, 1], cmap="gray") # plot 1st image's 2nd feature map
plt.show()
reset_graph()
filter_primes = np.array([2., 3., 5., 7., 11., 13.], dtype=np.float32)
x = tf.constant(np.arange(1, 13+1, dtype=np.float32).reshape([1, 1, 13, 1]))
filters = tf.constant(filter_primes.reshape(1, 6, 1, 1))
valid_conv = tf.nn.conv2d(x, filters, strides=[1, 1, 5, 1], padding='VALID')
same_conv = tf.nn.conv2d(x, filters, strides=[1, 1, 5, 1], padding='SAME')
with tf.Session() as sess:
print("VALID:\n", valid_conv.eval())
print("SAME:\n", same_conv.eval())
print("VALID:")
print(np.array([1,2,3,4,5,6]).T.dot(filter_primes))
print(np.array([6,7,8,9,10,11]).T.dot(filter_primes))
print("SAME:")
print(np.array([0,1,2,3,4,5]).T.dot(filter_primes))
print(np.array([5,6,7,8,9,10]).T.dot(filter_primes))
print(np.array([10,11,12,13,0,0]).T.dot(filter_primes))
batch_size, height, width, channels = dataset.shape
filters = np.zeros(shape=(7, 7, channels, 2), dtype=np.float32)
filters[:, 3, :, 0] = 1 # vertical line
filters[3, :, :, 1] = 1 # horizontal line
X = tf.placeholder(tf.float32, shape=(None, height, width, channels))
max_pool = tf.nn.max_pool(X, ksize=[1,2,2,1], strides=[1,2,2,1],padding="VALID")
with tf.Session() as sess:
output = sess.run(max_pool, feed_dict={X: dataset})
plt.imshow(output[0].astype(np.uint8)) # plot the output for the 1st image
plt.show()
plot_color_image(dataset[0])
save_fig("china_original")
plt.show()
plot_color_image(output[0])
save_fig("china_max_pool")
plt.show()
width = 28
channels = 1
n_inputs = height * width
conv1_fmaps = 32
conv1_ksize = 3
conv1_stride = 1
conv1_pad = "SAME"
conv2_fmaps = 64
conv2_ksize = 3
conv2_stride = 2
conv2_pad = "SAME"
pool3_fmaps = conv2_fmaps
n_fc1 = 64
n_outputs = 10
reset_graph()
with tf.name_scope("inputs"):
X = tf.placeholder(tf.float32, shape=[None, n_inputs], name="X")
X_reshaped = tf.reshape(X, shape=[-1, height, width, channels])
y = tf.placeholder(tf.int32, shape=[None], name="y")
conv1 = tf.layers.conv2d(X_reshaped, filters=conv1_fmaps, kernel_size=conv1_ksize,
strides=conv1_stride, padding=conv1_pad,
activation=tf.nn.relu, name="conv1")
conv2 = tf.layers.conv2d(conv1, filters=conv2_fmaps, kernel_size=conv2_ksize,
strides=conv2_stride, padding=conv2_pad,
activation=tf.nn.relu, name="conv2")
with tf.name_scope("pool3"):
pool3 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="VALID")
pool3_flat = tf.reshape(pool3, shape=[-1, pool3_fmaps * 7 * 7])
with tf.name_scope("fc1"):
fc1 = tf.layers.dense(pool3_flat, n_fc1, activation=tf.nn.relu, name="fc1")
with tf.name_scope("output"):
logits = tf.layers.dense(fc1, n_outputs, name="output")
Y_proba = tf.nn.softmax(logits, name="Y_proba")
with tf.name_scope("train"):
xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=y)
loss = tf.reduce_mean(xentropy)
optimizer = tf.train.AdamOptimizer()
training_op = optimizer.minimize(loss)
with tf.name_scope("eval"):
correct = tf.nn.in_top_k(logits, y, 1)
accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))
with tf.name_scope("init_and_save"):
init = tf.global_variables_initializer()
saver = tf.train.Saver()
(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()
X_train = X_train.astype(np.float32).reshape(-1, 28*28) / 255.0
X_test = X_test.astype(np.float32).reshape(-1, 28*28) / 255.0
y_train = y_train.astype(np.int32)
y_test = y_test.astype(np.int32)
X_valid, X_train = X_train[:5000], X_train[5000:]
y_valid, y_train = y_train[:5000], y_train[5000:]
def shuffle_batch(X, y, batch_size):
rnd_idx = np.random.permutation(len(X))
n_batches = len(X) // batch_size
for batch_idx in np.array_split(rnd_idx, n_batches):
X_batch, y_batch = X[batch_idx], y[batch_idx]
yield X_batch, y_batch
n_epochs = 10
batch_size = 100
with tf.Session() as sess:
init.run()
for epoch in range(n_epochs):
for X_batch, y_batch in shuffle_batch(X_train, y_train, batch_size):
sess.run(training_op, feed_dict={X: X_batch, y: y_batch})
acc_batch = accuracy.eval(feed_dict={X: X_batch, y: y_batch})
acc_test = accuracy.eval(feed_dict={X: X_test, y: y_test})
print(epoch, "Last batch accuracy:", acc_batch, "Test accuracy:", acc_test)
save_path = saver.save(sess, "./my_mnist_model")
Everything runs fine until the very last section (with tf.Session() as sess:) where I receive the following error:
ValueError: Cannot feed value of shape (100, 784) for Tensor 'inputs/X:0', which has shape '(?, 1960)'
I have been reading the following related threads on Stack Overflow, most of which seem to have no resolution.
ValueError: Cannot feed value of shape (784,) for Tensor 'x:0', which has shape '(?, 784)'
ValueError: Cannot feed value of shape
Sketch_RNN , ValueError: Cannot feed value of shape
Edit: I included some code that I thought was for a separate module, but was defining some of my parameters, namely height.
