Convolutional Neural Net using TensorFlow on Happy/Sad image dataset

conv_net.py

import tensorflow as tf
import os
import zipfile

DESIRED_ACCURACY = 0.999

!wget --no-check-certificate \
    "https://storage.googleapis.com/laurencemoroney-blog.appspot.com/happy-or-sad.zip" \
    -O "/tmp/happy-or-sad.zip"

zip_ref = zipfile.ZipFile("/tmp/happy-or-sad.zip", 'r')
zip_ref.extractall("/tmp/h-or-s")
zip_ref.close()

class myCallback(tf.keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs={}):
    if(logs.get('acc')>DESIRED_ACCURACY):
      print("\nReached 99.9% accuracy so cancelling training!")
      self.model.stop_training = True

callbacks = myCallback()


model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(16, (3,3), activation='relu', input_shape=(150, 150, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(32, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Conv2D(32, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

from tensorflow.keras.optimizers import RMSprop

model.compile(loss='binary_crossentropy',
              optimizer=RMSprop(lr=0.001),
              metrics=['acc'])

from tensorflow.keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(rescale=1/255)

train_generator = train_datagen.flow_from_directory(
        "/tmp/h-or-s",  
        target_size=(150, 150), 
        batch_size=10,
        class_mode='binary')

# Expected output: 'Found 80 images belonging to 2 classes'

history = model.fit_generator(
      train_generator,
      steps_per_epoch=2,  
      epochs=15,
      verbose=1,
      callbacks=[callbacks])

Does this overfit?

I have not been been able to get wget to work to download the images. I get "/bin/sh: 1: wget: not found" on executing the wget command. I have pip installed it and I can see wget 3.2 installed in the python3.6 folder. I import wget but still can't get it to work on jupyter. Wget works fine on Google collab.

there are 80 images in batches of 10 so 8 steps_per_epoch
history = model.fit_generator(
train_generator,
steps_per_epoch=8,
epochs=15,
verbose=1,
callbacks=[callbacks])

I have not been been able to get wget to work to download the images. I get "/bin/sh: 1: wget: not found" on executing the wget command. I have pip installed it and I can see wget 3.2 installed in the python3.6 folder. I import wget but still can't get it to work on jupyter. Wget works fine on Google collab.

I have a solution for this. Please go to the below link and directly download the happy/sad zip file onto your local computer.

Link - https://storage.googleapis.com/laurencemoroney-blog.appspot.com/happy-or-sad.zip

After that, you can make changes to your code as below:

path = r'Desktop\happy-or-sad.zip'
zip_ref = zipfile.ZipFile(path, 'r')
zip_ref.extractall("/tmp/h-or-s")
zip_ref.close()

Since I've saved the file on my Desktop, I've mentioned that folder. Rest of the code will remain the same.
Hope this helps. :)

Definitely overfits. Accuracy approx. 1.