How do I optimize Tensorflow CNN?

Question

I'm very new to Tensorflow, so I apologize if my question comes off as ignorant.

I have a very simple CNN Tensorflow that takes images and outputs another image. With just a batchsize of 5, it takes minutes to run between epochs and often crashes after 5 epochs.(I'm using python 3.6.5 on my mac with 16 gbs of RAM)

This is a snippet of my program

learning_rate = 0.01
inputs_ = tf.placeholder(tf.float32, (None, 224, 224, 3), name='inputs')
targets_ = tf.placeholder(tf.float32, (None, 224, 224, 1), name='targets')
### Encoder
conv1 = tf.layers.conv2d(inputs=inputs_, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 224x224x32
maxpool1 = tf.layers.max_pooling2d(conv1, pool_size=(2,2), strides=(2,2), padding='same')
# Now 112x112x32

conv2 = tf.layers.conv2d(inputs=maxpool1, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 112x112x32
maxpool2 = tf.layers.max_pooling2d(conv2, pool_size=(2,2), strides=(2,2), padding='same')
# Now 56x56x32

conv3 = tf.layers.conv2d(inputs=maxpool2, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 56x56x32
maxpool3 = tf.layers.max_pooling2d(conv3, pool_size=(2,2), strides=(2,2), padding='same')
# Now 28x28x32

conv4 = tf.layers.conv2d(inputs=maxpool3, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 28x28x32
maxpool4 = tf.layers.max_pooling2d(conv4, pool_size=(2,2), strides=(2,2), padding='same')
# Now 14x14x32
conv5 = tf.layers.conv2d(inputs=maxpool4, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 14x14x32
maxpool5 = tf.layers.max_pooling2d(conv5, pool_size=(2,2), strides=(2,2), padding='same')
# Now 7x7x32
conv6 = tf.layers.conv2d(inputs=maxpool5, filters=16, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 7x7x16
encoded = tf.layers.max_pooling2d(conv6, pool_size=(2,2), strides=(2,2), padding='same')
# Now 4x4x16

### Decoder
upsample1 = tf.image.resize_images(encoded, size=(7,7), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
# Now 7x7x16
conv7 = tf.layers.conv2d(inputs=upsample1, filters=16, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 7x7x16
upsample2 = tf.image.resize_images(conv7, size=(14,14), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
# Now 14x14x16
conv8 = tf.layers.conv2d(inputs=upsample2, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 14x14x32
upsample3 = tf.image.resize_images(conv8, size=(28,28), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
# Now 28x28x32
conv9 = tf.layers.conv2d(inputs=upsample3, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 28x28x32

upsample4 = tf.image.resize_images(conv9, size=(56,56), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
# Now 56x56x32
conv10 = tf.layers.conv2d(inputs=upsample3, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 56x56x32

upsample5 = tf.image.resize_images(conv10, size=(112,112), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
# Now 112x112x32
conv11 = tf.layers.conv2d(inputs=upsample5, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 112x112x32

upsample6 = tf.image.resize_images(conv11, size=(224,224), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
# Now 224x224x32
conv12 = tf.layers.conv2d(inputs=upsample6, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# Now 224x224x32

logits = tf.layers.conv2d(inputs=conv12, filters=1, kernel_size=(3,3), padding='same', activation=None)
#Now 224x224x1
# Pass logits through sigmoid and calculate the cross-entropy loss
loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=targets_, logits=logits)

# Get cost and define the optimizer
cost = tf.reduce_mean(loss)
opt = tf.train.AdamOptimizer(learning_rate).minimize(cost)

imagelist = ... #array of all images with 3 channels
imagelabellist = ... #array of all images with 1 channel
epochs = 15

for e in range(epochs):
            imgs_large = imagelist
            imgs_target_large = imagelabellist
            shaped_imgs = tf.image.resize_images(imgs_large, [224, 224])
            shaped_imgs_target = tf.image.resize_images(imgs_target_large, [224, 224])
            # Get images from the batch
            imgs = sess.run(shaped_imgs)
            imgs_target = sess.run(shaped_imgs_target)
            batch_cost, _ = sess.run([cost, opt], feed_dict={inputs_: imgs, targets_: imgs_target})

This is the output of the CNN

epoch: #1
0 minutes between epoch
epoch: #2
3 minutes between epoch
epoch: #3
3 minutes between epoch
epoch: #4
12 minutes between epoch
epoch: #5

...

I'm open to any suggestions on how to fix this issue. Thank you.

Answer 1

tf.image.resize_images is a graph op, so you're appending more nodes to the graph (that explains the increasing run time). Before your training loop add sess.graph.finalize() if nodes are being added it will throw an error to check this.

If you move resize_images outside of the loop, that should fixed the issue.