图像分类-识别花朵
云间之龙
  2021-07-05 20:46:12 2021-07-05 20:46  

图像分类-花朵识别

使用TensorFlow官网的image classification 实例

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
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/*'))

# Create a dataset
batch_size = 32
img_height = 180
img_width = 180

# It's good practice to use a validation split when developing your model. Let's use 80% of the images for training, and 20% for validation.
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)

# You can find the class names in the class_names attribute on these datasets. These correspond to the directory names in alphabetical order.
class_names = train_ds.class_names
print(class_names)


# Visualize the data
plt.figure(figsize=(10, 10))
for images, labels in train_ds.take(1):
  for i in range(9):
    ax = plt.subplot(3, 3, i + 1)
    plt.imshow(images[i].numpy().astype("uint8"))
    plt.title(class_names[labels[i]])
    plt.axis("off")

for image_batch, labels_batch in train_ds:
  print(image_batch.shape)
  print(labels_batch.shape)
  break

AUTOTUNE = tf.data.AUTOTUNE

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

normalization_layer = layers.experimental.preprocessing.Rescaling(1./255)

normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
image_batch, labels_batch = next(iter(normalized_ds))
first_image = image_batch[0]
# Notice the pixels values are now in `[0,1]`.
print(np.min(first_image), np.max(first_image))


# Create the model

num_classes = 5

model = Sequential([
  layers.experimental.preprocessing.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
  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.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes)
])

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


# Model summary
model.summary()


epochs=10
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

# Visualize training results
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()



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

plt.figure(figsize=(10, 10))
for images, _ in train_ds.take(1):
  for i in range(9):
    augmented_images = data_augmentation(images)
    ax = plt.subplot(3, 3, i + 1)
    plt.imshow(augmented_images[0].numpy().astype("uint8"))
    plt.axis("off")




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()

epochs = 15
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

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()


# sunflower_url = "https://storage.googleapis.com/download.tensorflow.org/example_images/592px-Red_sunflower.jpg"
# sunflower_path = tf.keras.utils.get_file('Red_sunflower', origin=sunflower_url)

# img = keras.preprocessing.image.load_img(
#     sunflower_path, target_size=(img_height, img_width)
# )
# img_array = keras.preprocessing.image.img_to_array(img)
# img_array = tf.expand_dims(img_array, 0) # Create a batch

# predictions = model.predict(img_array)
# score = tf.nn.softmax(predictions[0])

# print(
#     "This image most likely belongs to {} with a {:.2f} percent confidence."
#     .format(class_names[np.argmax(score)], 100 * np.max(score))
# )
1
2
3
4
5
6
7
8
Downloading data from https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz
228818944/228813984 [==============================] - 1s 0us/step
3670
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']

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
(32, 180, 180, 3)
(32,)
0.0 0.9994554

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
rescaling_1 (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         
_________________________________________________________________
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
_________________________________________________________________

Epoch 1/10
92/92 [==============================] - 35s 35ms/step - loss: 1.2843 - accuracy: 0.4567 - val_loss: 1.0978 - val_accuracy: 0.5327
Epoch 2/10
92/92 [==============================] - 2s 21ms/step - loss: 0.9808 - accuracy: 0.6151 - val_loss: 0.9376 - val_accuracy: 0.6199
Epoch 3/10
92/92 [==============================] - 2s 20ms/step - loss: 0.7793 - accuracy: 0.6941 - val_loss: 0.9825 - val_accuracy: 0.6213
Epoch 4/10
92/92 [==============================] - 2s 20ms/step - loss: 0.5839 - accuracy: 0.7796 - val_loss: 0.9078 - val_accuracy: 0.6526
Epoch 5/10
92/92 [==============================] - 2s 20ms/step - loss: 0.3918 - accuracy: 0.8556 - val_loss: 0.9262 - val_accuracy: 0.6553
Epoch 6/10
92/92 [==============================] - 2s 20ms/step - loss: 0.2278 - accuracy: 0.9220 - val_loss: 1.1121 - val_accuracy: 0.6431
Epoch 7/10
92/92 [==============================] - 2s 20ms/step - loss: 0.1672 - accuracy: 0.9475 - val_loss: 1.3076 - val_accuracy: 0.6362
Epoch 8/10
92/92 [==============================] - 2s 20ms/step - loss: 0.0641 - accuracy: 0.9837 - val_loss: 1.4835 - val_accuracy: 0.6458
Epoch 9/10
92/92 [==============================] - 2s 20ms/step - loss: 0.0231 - accuracy: 0.9939 - val_loss: 1.6968 - val_accuracy: 0.6635
Epoch 10/10
92/92 [==============================] - 2s 20ms/step - loss: 0.0162 - accuracy: 0.9986 - val_loss: 1.7977 - val_accuracy: 0.6635

过度拟合通常发生在有少量训练示例的情况下。数据增强采用的方法是从现有示例中生成额外的训练数据，方法是使用随机变换对它们进行增强，从而生成外观可信的图像。这有助于将模型暴露于数据的更多方面，并更好地概括。

您将使用tf.keras.layers.experimental.preprocessing中的层来实现数据扩充。这些可以像其他层一样包含在模型中，并在GPU上运行。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66

Model: "sequential_2"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
sequential_1 (Sequential)    (None, 180, 180, 3)       0         
_________________________________________________________________
rescaling_2 (Rescaling)      (None, 180, 180, 3)       0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 180, 180, 16)      448       
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 90, 90, 16)        0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 90, 90, 32)        4640      
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 45, 45, 32)        0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 45, 45, 64)        18496     
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 22, 22, 64)        0         
_________________________________________________________________
dropout (Dropout)            (None, 22, 22, 64)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 30976)             0         
_________________________________________________________________
dense_2 (Dense)              (None, 128)               3965056   
_________________________________________________________________
dense_3 (Dense)              (None, 5)                 645       
=================================================================
Total params: 3,989,285
Trainable params: 3,989,285
Non-trainable params: 0
_________________________________________________________________


Epoch 1/15
92/92 [==============================] - 3s 26ms/step - loss: 1.3763 - accuracy: 0.4135 - val_loss: 1.0668 - val_accuracy: 0.5409
Epoch 2/15
92/92 [==============================] - 2s 24ms/step - loss: 1.0724 - accuracy: 0.5576 - val_loss: 1.1257 - val_accuracy: 0.5613
Epoch 3/15
92/92 [==============================] - 2s 24ms/step - loss: 0.9417 - accuracy: 0.6345 - val_loss: 1.0127 - val_accuracy: 0.6226
Epoch 4/15
92/92 [==============================] - 2s 24ms/step - loss: 0.8745 - accuracy: 0.6587 - val_loss: 0.9076 - val_accuracy: 0.6417
Epoch 5/15
92/92 [==============================] - 2s 24ms/step - loss: 0.8245 - accuracy: 0.6897 - val_loss: 0.8622 - val_accuracy: 0.6717
Epoch 6/15
92/92 [==============================] - 2s 24ms/step - loss: 0.7905 - accuracy: 0.6928 - val_loss: 0.8115 - val_accuracy: 0.6880
Epoch 7/15
92/92 [==============================] - 2s 24ms/step - loss: 0.7479 - accuracy: 0.7156 - val_loss: 0.7976 - val_accuracy: 0.6839
Epoch 8/15
92/92 [==============================] - 2s 24ms/step - loss: 0.7455 - accuracy: 0.7197 - val_loss: 0.7919 - val_accuracy: 0.6880
Epoch 9/15
92/92 [==============================] - 2s 25ms/step - loss: 0.6901 - accuracy: 0.7330 - val_loss: 0.7831 - val_accuracy: 0.7057
Epoch 10/15
92/92 [==============================] - 2s 24ms/step - loss: 0.6729 - accuracy: 0.7422 - val_loss: 0.9560 - val_accuracy: 0.6444
Epoch 11/15
92/92 [==============================] - 2s 24ms/step - loss: 0.6511 - accuracy: 0.7493 - val_loss: 0.7521 - val_accuracy: 0.6989
Epoch 12/15
92/92 [==============================] - 2s 24ms/step - loss: 0.6225 - accuracy: 0.7667 - val_loss: 0.7420 - val_accuracy: 0.7125
Epoch 13/15
92/92 [==============================] - 2s 25ms/step - loss: 0.5907 - accuracy: 0.7769 - val_loss: 0.7644 - val_accuracy: 0.6962
Epoch 14/15
92/92 [==============================] - 2s 24ms/step - loss: 0.5704 - accuracy: 0.7847 - val_loss: 0.7330 - val_accuracy: 0.7343
Epoch 15/15
92/92 [==============================] - 2s 25ms/step - loss: 0.5624 - accuracy: 0.7902 - val_loss: 0.7804 - val_accuracy: 0.7003