第T7周:咖啡豆识别

  • 文为「365天深度学习训练营」内部文章
  • 参考本文所写文章,请在文章开头带上「 声明」

1.设置GPU

import tensorflow as tf

gpus = tf.config.list_physical_devices("GPU")

if gpus:
    tf.config.experimental.set_memory_growth(gpus[0], True)  #设置GPU显存用量按需使用
    tf.config.set_visible_devices([gpus[0]],"GPU")
from tensorflow       import keras
from tensorflow.keras import layers,models
import numpy             as np
import matplotlib.pyplot as plt
import os,PIL,pathlib

data_dir = "E:/T3/kafeidao"
data_dir = pathlib.Path(data_dir)
image_count = len(list(data_dir.glob('*/*.png')))

print("图片总数为:",image_count)
图片总数为: 1200
batch_size = 32
img_height = 224
img_width = 224
"""
关于image_dataset_from_directory()的详细介绍可以参考文章:https://mtyjkh.blog.csdn.net/article/details/117018789
"""
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)
Found 1200 files belonging to 4 classes.
Using 960 files for training.
"""
关于image_dataset_from_directory()的详细介绍可以参考文章:https://mtyjkh.blog.csdn.net/article/details/117018789
"""
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)
Found 1200 files belonging to 4 classes.
Using 240 files for validation.
class_names = train_ds.class_names
print(class_names)
['Dark', 'Green', 'Light', 'Medium']
plt.figure(figsize=(10, 4))  # 图形的宽为10高为5

for images, labels in train_ds.take(1):
    for i in range(10):
        
        ax = plt.subplot(2, 5, i + 1)  

        plt.imshow(images[i].numpy().astype("uint8"))
        plt.title(class_names[labels[i]])
        
        plt.axis("off")

第T7周:咖啡豆识别_第1张图片

for image_batch, labels_batch in train_ds:
    print(image_batch.shape)
    print(labels_batch.shape)
    break
(32, 224, 224, 3)
(32,
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)

train_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
val_ds   = val_ds.map(lambda x, y: (normalization_layer(x), y))
image_batch, labels_batch = next(iter(val_ds))
first_image = image_batch[0]

# 查看归一化后的数据
print(np.min(first_image), np.max(first_image))
0.0 1.0
from tensorflow.keras import layers, models, Input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropout

def VGG16(nb_classes, input_shape):
    input_tensor = Input(shape=input_shape)
    # 1st block
    x = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv1')(input_tensor)
    x = Conv2D(64, (3,3), activation='relu', padding='same',name='block1_conv2')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block1_pool')(x)
    # 2nd block
    x = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv1')(x)
    x = Conv2D(128, (3,3), activation='relu', padding='same',name='block2_conv2')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block2_pool')(x)
    # 3rd block
    x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv1')(x)
    x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv2')(x)
    x = Conv2D(256, (3,3), activation='relu', padding='same',name='block3_conv3')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block3_pool')(x)
    # 4th block
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv1')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv2')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block4_conv3')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block4_pool')(x)
    # 5th block
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv1')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv2')(x)
    x = Conv2D(512, (3,3), activation='relu', padding='same',name='block5_conv3')(x)
    x = MaxPooling2D((2,2), strides=(2,2), name = 'block5_pool')(x)
    # full connection
    x = Flatten()(x)
    x = Dense(4096, activation='relu',  name='fc1')(x)
    x = Dense(4096, activation='relu', name='fc2')(x)
    output_tensor = Dense(nb_classes, activation='softmax', name='predictions')(x)

    model = Model(input_tensor, output_tensor)
    return model

model=VGG16(len(class_names), (img_width, img_height, 3))
model.summary()
odel: "model"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 input_1 (InputLayer)        [(None, 224, 224, 3)]     0         
                                                                 
 block1_conv1 (Conv2D)       (None, 224, 224, 64)      1792      
                                                                 
 block1_conv2 (Conv2D)       (None, 224, 224, 64)      36928     
                                                                 
 block1_pool (MaxPooling2D)  (None, 112, 112, 64)      0         
                                                                 
 block2_conv1 (Conv2D)       (None, 112, 112, 128)     73856     
                                                                 
 block2_conv2 (Conv2D)       (None, 112, 112, 128)     147584    
                                                                 
 block2_pool (MaxPooling2D)  (None, 56, 56, 128)       0         
                                                                 
 block3_conv1 (Conv2D)       (None, 56, 56, 256)       295168    
                                                                 
 block3_conv2 (Conv2D)       (None, 56, 56, 256)       590080    
                                                                 
 block3_conv3 (Conv2D)       (None, 56, 56, 256)       590080    
                                                                 
 block3_pool (MaxPooling2D)  (None, 28, 28, 256)       0         
                                                                 
 block4_conv1 (Conv2D)       (None, 28, 28, 512)       1180160   
                                                                 
 block4_conv2 (Conv2D)       (None, 28, 28, 512)       2359808   
                                                                 
 block4_conv3 (Conv2D)       (None, 28, 28, 512)       2359808   
                                                                 
 block4_pool (MaxPooling2D)  (None, 14, 14, 512)       0         
                                                                 
 block5_conv1 (Conv2D)       (None, 14, 14, 512)       2359808   
                                                                 
 block5_conv2 (Conv2D)       (None, 14, 14, 512)       2359808   
                                                                 
 block5_conv3 (Conv2D)       (None, 14, 14, 512)       2359808   
                                                                 
 block5_pool (MaxPooling2D)  (None, 7, 7, 512)         0         
                                                                 
 flatten (Flatten)           (None, 25088)             0         
                                                                 
 fc1 (Dense)                 (None, 4096)              102764544 
                                                                 
 fc2 (Dense)                 (None, 4096)              16781312  
                                                                 
 predictions (Dense)         (None, 4)                 16388     
                                                                 
=================================================================
Total params: 134276932 (512.23 MB)
Trainable params: 134276932 (512.23 MB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________
# 设置初始学习率
initial_learning_rate = 1e-4

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
        initial_learning_rate, 
        decay_steps=30,      # 敲黑板!!!这里是指 steps,不是指epochs
        decay_rate=0.92,     # lr经过一次衰减就会变成 decay_rate*lr
        staircase=True)

# 设置优化器
opt = tf.keras.optimizers.Adam(learning_rate=initial_learning_rate)

model.compile(optimizer=opt,
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['accuracy'])
epochs = 20

history = model.fit(
    train_ds,
    validation_data=val_ds,
    epochs=epochs
)
poch 1/20
WARNING:tensorflow:From D:\dl\envs\pytorch_gpu\lib\site-packages\keras\src\utils\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.

WARNING:tensorflow:From D:\dl\envs\pytorch_gpu\lib\site-packages\keras\src\engine\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.

30/30 [==============================] - 114s 4s/step - loss: 1.3847 - accuracy: 0.2427 - val_loss: 1.3976 - val_accuracy: 0.2125
Epoch 2/20
30/30 [==============================] - 124s 4s/step - loss: 1.1982 - accuracy: 0.4021 - val_loss: 1.1049 - val_accuracy: 0.3542
Epoch 3/20
30/30 [==============================] - 123s 4s/step - loss: 0.8367 - accuracy: 0.5354 - val_loss: 0.7545 - val_accuracy: 0.5917
Epoch 4/20
30/30 [==============================] - 121s 4s/step - loss: 0.6268 - accuracy: 0.6583 - val_loss: 0.5559 - val_accuracy: 0.5958
Epoch 5/20
30/30 [==============================] - 121s 4s/step - loss: 0.4366 - accuracy: 0.7854 - val_loss: 0.6017 - val_accuracy: 0.6333
Epoch 6/20
30/30 [==============================] - 122s 4s/step - loss: 0.2857 - accuracy: 0.8854 - val_loss: 0.2449 - val_accuracy: 0.9000
Epoch 7/20
30/30 [==============================] - 123s 4s/step - loss: 0.2309 - accuracy: 0.9250 - val_loss: 0.5561 - val_accuracy: 0.8708
Epoch 8/20
30/30 [==============================] - 126s 4s/step - loss: 0.1277 - accuracy: 0.9542 - val_loss: 0.2514 - val_accuracy: 0.8958
Epoch 9/20
30/30 [==============================] - 122s 4s/step - loss: 0.0856 - accuracy: 0.9719 - val_loss: 0.0807 - val_accuracy: 0.9792
Epoch 10/20
30/30 [==============================] - 121s 4s/step - loss: 0.0637 - accuracy: 0.9823 - val_loss: 0.2138 - val_accuracy: 0.9417
Epoch 11/20
30/30 [==============================] - 122s 4s/step - loss: 0.0589 - accuracy: 0.9792 - val_loss: 0.1214 - val_accuracy: 0.9375
Epoch 12/20
30/30 [==============================] - 121s 4s/step - loss: 0.0522 - accuracy: 0.9823 - val_loss: 0.1414 - val_accuracy: 0.9417
Epoch 13/20
30/30 [==============================] - 122s 4s/step - loss: 0.0503 - accuracy: 0.9833 - val_loss: 0.0634 - val_accuracy: 0.9750
Epoch 14/20
30/30 [==============================] - 121s 4s/step - loss: 0.0924 - accuracy: 0.9698 - val_loss: 0.0720 - val_accuracy: 0.9875
Epoch 15/20
30/30 [==============================] - 122s 4s/step - loss: 0.0294 - accuracy: 0.9885 - val_loss: 0.1154 - val_accuracy: 0.9750
Epoch 16/20
30/30 [==============================] - 123s 4s/step - loss: 0.0326 - accuracy: 0.9917 - val_loss: 0.0866 - val_accuracy: 0.9750
Epoch 17/20
30/30 [==============================] - 122s 4s/step - loss: 0.0520 - accuracy: 0.9854 - val_loss: 0.0899 - val_accuracy: 0.9792
Epoch 18/20
30/30 [==============================] - 124s 4s/step - loss: 0.0517 - accuracy: 0.9844 - val_loss: 0.0580 - val_accuracy: 0.9750
Epoch 19/20
30/30 [==============================] - 122s 4s/step - loss: 0.0280 - accuracy: 0.9875 - val_loss: 0.0817 - val_accuracy: 0.9833
Epoch 20/20
30/30 [==============================] - 122s 4s/step - loss: 0.0299 - accuracy: 0.9906 - val_loss: 0.0590 - val_accuracy: 0.9875
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=(12, 4))
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()

第T7周:咖啡豆识别_第2张图片

你可能感兴趣的:(python)