3.4 手势识别
问题描述
识别一个人出的是剪刀，石头还是布。
数据预处理
图片下载
!wget --no-check-certificate \
https://storage.googleapis.com/laurencemoroney-blog.appspot.com/rps.zip \
-O /tmp/rps.zip
!wget --no-check-certificate \
https://storage.googleapis.com/laurencemoroney-blog.appspot.com/rps-test-set.zip \
-O /tmp/rps-test-set.zip解压
import os
import zipfile
local_zip = '/tmp/rps.zip'
zip_ref = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('/tmp/')
zip_ref.close()
local_zip = '/tmp/rps-test-set.zip'
zip_ref = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('/tmp/')
zip_ref.close()rock_dir = os.path.join('/tmp/rps/rock')
paper_dir = os.path.join('/tmp/rps/paper')
scissors_dir = os.path.join('/tmp/rps/scissors')
print('total training rock images:', len(os.listdir(rock_dir)))
print('total training paper images:', len(os.listdir(paper_dir)))
print('total training scissors images:', len(os.listdir(scissors_dir)))
rock_files = os.listdir(rock_dir)
print(rock_files[:10])
paper_files = os.listdir(paper_dir)
print(paper_files[:10])
scissors_files = os.listdir(scissors_dir)
print(scissors_files[:10])
total training rock images: 840
total training paper images: 840
total training scissors images: 840
['rock07-k03-096.png', 'rock03-059.png', 'rock03-058.png', 'rock01-098.png', 'rock05ck01-034.png', 'rock07-k03-056.png', 'rock03-024.png', 'rock06ck02-051.png', 'rock06ck02-080.png', 'rock03-092.png']
['paper03-061.png', 'paper06-071.png', 'paper02-098.png', 'paper06-006.png', 'paper01-065.png', 'paper01-118.png', 'paper02-000.png', 'paper05-043.png', 'paper04-054.png', 'paper04-109.png']
['scissors03-041.png', 'scissors02-000.png', 'testscissors03-039.png', 'scissors02-036.png', 'scissors04-006.png', 'scissors04-010.png', 'testscissors01-012.png', 'scissors01-098.png', 'scissors04-077.png', 'scissors04-112.png']查看一下素材(各两张)
%matplotlib inline
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
pic_index = 2
next_rock = [os.path.join(rock_dir, fname)
for fname in rock_files[pic_index-2:pic_index]]
next_paper = [os.path.join(paper_dir, fname)
for fname in paper_files[pic_index-2:pic_index]]
next_scissors = [os.path.join(scissors_dir, fname)
for fname in scissors_files[pic_index-2:pic_index]]
for i, img_path in enumerate(next_rock+next_paper+next_scissors):
#print(img_path)
img = mpimg.imread(img_path)
plt.imshow(img)
plt.axis('Off')
plt.show()
预处理
import tensorflow as tf
import keras_preprocessing
from keras_preprocessing import image
from keras_preprocessing.image import ImageDataGenerator
TRAINING_DIR = "/tmp/rps/"
training_datagen = ImageDataGenerator(
rescale = 1./255,
rotation_range=40,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True,
fill_mode='nearest')
VALIDATION_DIR = "/tmp/rps-test-set/"
validation_datagen = ImageDataGenerator(rescale = 1./255)
train_generator = training_datagen.flow_from_directory(
TRAINING_DIR,
target_size=(150,150),
class_mode='categorical'
)
validation_generator = validation_datagen.flow_from_directory(
VALIDATION_DIR,
target_size=(150,150),
class_mode='categorical'
)模型定义及训练
model = tf.keras.models.Sequential([
# Note the input shape is the desired size of the image 150x150 with 3 bytes color
# This is the first convolution
tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(150, 150, 3)),
tf.keras.layers.MaxPooling2D(2, 2),
# The second convolution
tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
# The third convolution
tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
# The fourth convolution
tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
# Flatten the results to feed into a DNN
tf.keras.layers.Flatten(),
tf.keras.layers.Dropout(0.5),
# 512 neuron hidden layer
tf.keras.layers.Dense(512, activation='relu'),
tf.keras.layers.Dense(3, activation='softmax')
])
model.compile(loss = 'categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
history = model.fit_generator(train_generator, epochs=5, validation_data = validation_generator, verbose = 1)
model.save("rps.h5")Epoch 1/5
79/79 [==============================] - 84s 1s/step - loss: 1.1976 - accuracy: 0.3738 - val_loss: 0.9343 - val_accuracy: 0.5780
Epoch 2/5
79/79 [==============================] - 84s 1s/step - loss: 0.9056 - accuracy: 0.5813 - val_loss: 0.3923 - val_accuracy: 0.8333
Epoch 3/5
79/79 [==============================] - 84s 1s/step - loss: 0.5751 - accuracy: 0.7556 - val_loss: 0.2332 - val_accuracy: 0.8898
Epoch 4/5
79/79 [==============================] - 84s 1s/step - loss: 0.3748 - accuracy: 0.8484 - val_loss: 0.0647 - val_accuracy: 0.9704
Epoch 5/5
79/79 [==============================] - 83s 1s/step - loss: 0.2706 - accuracy: 0.8948 - val_loss: 0.0668 - val_accuracy: 0.9812分析
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(len(acc))
plt.plot(epochs, acc, 'r', label='Training accuracy')
plt.plot(epochs, val_acc, 'b', label='Validation accuracy')
plt.title('Training and validation accuracy')
plt.legend(loc=0)
plt.figure()
plt.show()上传图片测试
import numpy as np
from google.colab import files
from keras.preprocessing import image
uploaded = files.upload()
for fn in uploaded.keys():
# predicting images
path = fn
img = image.load_img(path, target_size=(150, 150))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
images = np.vstack([x])
classes = model.predict(images, batch_size=10)
print(fn)
print(classes)
Comments NOTHING