import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential

import pathlib
dataset_url = "https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz"
data_dir = tf.keras.utils.get_file('flower_photos', origin=dataset_url, untar=True)
data_dir = pathlib.Path(data_dir)

image_count = len(list(data_dir.glob('*/*.jpg')))
print(image_count)
roses = list(data_dir.glob('roses/*'))
PIL.Image.open(str(roses[2]))

3670

batch_size = 32
img_height = 180
img_width = 180

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split = 0.2,
    subset = "training",
    seed = 123,
    image_size = (img_height, img_width),
    batch_size = batch_size
)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split = 0.2,
    subset = "validation",
    seed = 123,
    image_size = (img_height, img_width),
    batch_size = batch_size
)

class_names = train_ds.class_names
print(class_names)

Found 3670 files belonging to 5 classes.
Using 2936 files for training.
Found 3670 files belonging to 5 classes.
Using 734 files for validation.
['daisy', 'dandelion', 'roses', 'sunflowers', 'tulips']

AUTOTUNE = tf.data.experimental.AUTOTUNE

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

data_augmentation = keras.Sequential(
  [
    layers.experimental.preprocessing.RandomFlip("horizontal", 
                                                 input_shape=(img_height, 
                                                              img_width,
                                                              3)),
    layers.experimental.preprocessing.RandomRotation(0.1),
    layers.experimental.preprocessing.RandomZoom(0.1),
  ]
)

num_classes = 5

model = Sequential([
  data_augmentation,
  layers.experimental.preprocessing.Rescaling(1./255),
  layers.Conv2D(16, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(32, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Conv2D(64, 3, padding='same', activation='relu'),
  layers.MaxPooling2D(),
  layers.Dropout(0.2),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes)
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

model.summary()

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
sequential (Sequential)      (None, 180, 180, 3)       0         
_________________________________________________________________
rescaling (Rescaling)        (None, 180, 180, 3)       0         
_________________________________________________________________
conv2d (Conv2D)              (None, 180, 180, 16)      448       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 90, 90, 16)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 90, 90, 32)        4640      
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 45, 45, 32)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 45, 45, 64)        18496     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 22, 22, 64)        0         
_________________________________________________________________
dropout (Dropout)            (None, 22, 22, 64)        0         
_________________________________________________________________
flatten (Flatten)            (None, 30976)             0         
_________________________________________________________________
dense (Dense)                (None, 128)               3965056   
_________________________________________________________________
dense_1 (Dense)              (None, 5)                 645       
=================================================================
Total params: 3,989,285
Trainable params: 3,989,285
Non-trainable params: 0
_________________________________________________________________

#this step may take a minute
epochs = 10
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

Epoch 1/10
92/92 [==============================] - 52s 567ms/step - loss: 1.2822 - accuracy: 0.4496 - val_loss: 1.0467 - val_accuracy: 0.5940
Epoch 2/10
92/92 [==============================] - 45s 487ms/step - loss: 1.0299 - accuracy: 0.5906 - val_loss: 0.9622 - val_accuracy: 0.6213
Epoch 3/10
92/92 [==============================] - 45s 487ms/step - loss: 0.9288 - accuracy: 0.6349 - val_loss: 0.9489 - val_accuracy: 0.6362
Epoch 4/10
92/92 [==============================] - 50s 548ms/step - loss: 0.8767 - accuracy: 0.6591 - val_loss: 0.8652 - val_accuracy: 0.6744
Epoch 5/10
92/92 [==============================] - 51s 555ms/step - loss: 0.8144 - accuracy: 0.6884 - val_loss: 1.0062 - val_accuracy: 0.6226
Epoch 6/10
92/92 [==============================] - 52s 567ms/step - loss: 0.7877 - accuracy: 0.7003 - val_loss: 0.8033 - val_accuracy: 0.6717
Epoch 7/10
92/92 [==============================] - 48s 527ms/step - loss: 0.7634 - accuracy: 0.7091 - val_loss: 0.8038 - val_accuracy: 0.6812
Epoch 8/10
92/92 [==============================] - 48s 517ms/step - loss: 0.7093 - accuracy: 0.7221 - val_loss: 0.7143 - val_accuracy: 0.7234
Epoch 9/10
92/92 [==============================] - 48s 524ms/step - loss: 0.6858 - accuracy: 0.7337 - val_loss: 0.7324 - val_accuracy: 0.7112
Epoch 10/10
92/92 [==============================] - 50s 545ms/step - loss: 0.6826 - accuracy: 0.7466 - val_loss: 0.6870 - val_accuracy: 0.7343

acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(epochs)

plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()