import tensorflow as tf
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import pathlib
数据读取及预处理
data_dir = "./2_class"
data_root = pathlib.Path(data_dir)
for item in data_root.iterdir():
print(item)
all_image_path = list(data_root.glob("*/*"))
len(all_image_path)
all_image_path[:3]
all_image_path = [str(path) for path in all_image_path]
all_image_path[10:12]
import random
random.shuffle(all_image_path)
all_image_path[10:12]
image_count = len(all_image_path)
image_count
label_names = sorted (item.name for item in data_root.glob("*/"))
label_names
label_to_index = dict((name,index) for index,name in enumerate(label_names))
label_to_index
all_image_path[:3]
pathlib.Path("2_class\\lake\\lake_405.jpg").parent.name
all_image_label = [label_to_index[pathlib.Path(p).parent.name]for p in all_image_path]
all_image_label[:5]
all_image_path[:5]
import IPython.display as display
index_to_label = dict((v,k) for k,v in label_to_index.items())
index_to_label
读取和解码图片
for n in range(3):
image_index = random.choice(range(len(all_image_path)))
display.display(display.Image(all_image_path[image_index]))
print(index_to_label[all_image_label[image_index]])
print()
img_path = all_image_path[0]
img_path
img_raw = tf.io.read_file(img_path)
img_raw
img_tensor = tf.image.decode_image(img_raw)
img_tensor.shape
img_tensor
img_tensor = tf.cast(img_tensor,tf.float32)
img_tensor
img_tensor = img_tensor/255
定义函数对图片进行处理
def load_preprosess_image(img_paht):
img_raw = tf.io.read_file(img_path)
img_tensor = tf.image.decode_jpeg(img_raw,channels=3)
img_tensor = tf.image.resize(img_tensor,[256,256])
img_tensor = tf.cast(img_tensor,tf.float32)
img = img_tensor/255
return img
使用tf.data 构建图片输入管道
path_ds = tf.data.Dataset.from_tensor_slices(all_image_path)
image_dataset = path_ds.map(load_preprosess_image)
label_dataset = tf.data.Dataset.from_tensor_slices(all_image_label)
dataset = tf.data.Dataset.zip((image_dataset,label_dataset))
test_count = int(image_count*0.2)
train_count = image_count-test_count
train_dataset = dataset.skip(test_count)
test_dataset = dataset.take(test_count)
BATCH_SIZE = 32
train_dataset = train_dataset.shuffle(buffer_size=train_count).batch(BATCH_SIZE)
test_dataset = test_dataset.batch(BATCH_SIZE)
建立模型
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(64,(3,3),input_shape=(256,256,3)))
model.add(tf.keras.layers.BatchNormalization())
model.add(tf.keras.layers.Activation("relu"))
model.add(tf.keras.layers.Conv2D(64,(3,3)))
model.add(tf.keras.layers.BatchNormalization())
model.add(tf.keras.layers.Activation("relu"))
model.add(tf.keras.layers.MaxPooling2D())
model.add(tf.keras.layers.Conv2D(128,(3,3)))
model.add(tf.keras.layers.BatchNormalization())
model.add(tf.keras.layers.Activation("relu"))
model.add(tf.keras.layers.MaxPooling2D())
model.add(tf.keras.layers.Conv2D(256,(3,3)))
model.add(tf.keras.layers.BatchNormalization())
model.add(tf.keras.layers.Activation("relu"))
model.add(tf.keras.layers.MaxPooling2D())
model.add(tf.keras.layers.Conv2D(512,(3,3)))
model.add(tf.keras.layers.BatchNormalization())
model.add(tf.keras.layers.Activation("relu"))
model.add(tf.keras.layers.MaxPooling2D())
model.add(tf.keras.layers.Conv2D(1024,(3,3)))
model.add(tf.keras.layers.BatchNormalization())
model.add(tf.keras.layers.Activation("relu"))
model.add(tf.keras.layers.GlobalAveragePooling2D())
model.add(tf.keras.layers.Dense(1024))
model.add(tf.keras.layers.BatchNormalization())
model.add(tf.keras.layers.Activation("relu"))
model.add(tf.keras.layers.Dense(256))
model.add(tf.keras.layers.BatchNormalization())
model.add(tf.keras.layers.Activation("relu"))
model.add(tf.keras.layers.Dense(1,activation="sigmoid"))
model.summary()
model.compile(optimizer="adam",
loss="binary_crossentropy",
metrics=["acc"])
steps_per_epoch = train_count//BATCH_SIZE
validation_steps = test_count//BATCH_SIZE
history = model.fit(train_dataset,epochs=30,
steps_per_epoch=steps_per_epoch,
validation_data=test_dataset,
validation_steps=validation_steps)