CIFAR10简单实战——VGG13
自定义
import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from tensorflow import keras
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
def preprocess(x, y):
# [0~255] => [-1~1]
x = 2 * tf.cast(x, dtype=tf.float32) / 255. - 1.
y = tf.cast(y, dtype=tf.int32)
return x,y
batchsz = 128
# [50k, 32, 32, 3], [10k, 1]
(x, y), (x_val, y_val) = datasets.cifar10.load_data()
y = tf.squeeze(y)
y_val = tf.squeeze(y_val)
y = tf.one_hot(y, depth=10) # [50k, 10]
y_val = tf.one_hot(y_val, depth=10) # [10k, 10]
print('datasets:', x.shape, y.shape, x_val.shape, y_val.shape, x.min(), x.max())
train_db = tf.data.Dataset.from_tensor_slices((x,y))
train_db = train_db.map(preprocess).shuffle(10000).batch(batchsz)
test_db = tf.data.Dataset.from_tensor_slices((x_val, y_val))
test_db = test_db.map(preprocess).batch(batchsz)
sample = next(iter(train_db))
print('batch:', sample[0].shape, sample[1].shape)
class MyDense(layers.Layer):
# to replace standard layers.Dense()
def __init__(self, inp_dim, outp_dim):
super(MyDense, self).__init__()
self.kernel = self.add_variable('w', [inp_dim, outp_dim])
# self.bias = self.add_variable('b', [outp_dim])
def call(self, inputs, training=None):
x = inputs @ self.kernel
return x
class MyNetwork(keras.Model):
def __init__(self):
super(MyNetwork, self).__init__()
self.fc1 = MyDense(32*32*3, 256)
self.fc2 = MyDense(256, 128)
self.fc3 = MyDense(128, 64)
self.fc4 = MyDense(64, 32)
self.fc5 = MyDense(32, 10)
def call(self, inputs, training=None):
"""
:param inputs: [b, 32, 32, 3]
:param training:
:return:
"""
x = tf.reshape(inputs, [-1, 32*32*3])
# [b, 32*32*3] => [b, 256]
x = self.fc1(x)
x = tf.nn.relu(x)
# [b, 256] => [b, 128]
x = self.fc2(x)
x = tf.nn.relu(x)
# [b, 128] => [b, 64]
x = self.fc3(x)
x = tf.nn.relu(x)
# [b, 64] => [b, 32]
x = self.fc4(x)
x = tf.nn.relu(x)
# [b, 32] => [b, 10]
x = self.fc5(x)
return x
network = MyNetwork()
network.compile(optimizer=optimizers.Adam(lr=1e-3),
loss=tf.losses.CategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
network.fit(train_db, epochs=15, validation_data=test_db, validation_freq=1)
network.evaluate(test_db)
network.save_weights('ckpt/weights.ckpt')
del network
print('saved to ckpt/weights.ckpt')
network = MyNetwork()
network.compile(optimizer=optimizers.Adam(lr=1e-3),
loss=tf.losses.CategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
network.load_weights('ckpt/weights.ckpt')
print('loaded weights from file.')
network.evaluate(test_db)
keras.layers
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
tf.random.set_seed(1234)
conv_layers = [
# unit1
layers.Conv2D(64, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.Conv2D(64, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
# unit2
layers.Conv2D(128, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.Conv2D(128, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
# unit3
layers.Conv2D(256, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.Conv2D(256, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
# unit4
layers.Conv2D(512, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.Conv2D(512, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
# unit5
layers.Conv2D(512, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.Conv2D(512, kernel_size=[3, 3], padding='same', activation=tf.nn.relu),
layers.MaxPool2D(pool_size=[2, 2], strides=2, padding='same'),
]
def preprocess(x, y):
x = tf.cast(x, dtype=tf.float32) / 255.
y = tf.cast(y, dtype=tf.int32)
return x, y
(x, y), (x_test, y_test) = datasets.cifar100.load_data()
y = tf.squeeze(y, axis=1)
print(x.shape, y.shape, x_test.shape, y_test.shape)
train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.shuffle(1000).map(preprocess).batch(64)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_db = test_db.map(preprocess).batch(64)
sample = next(iter(train_db))
print('sample:', sample[0].shape, sample[1].shape, tf.reduce_min(sample[0]), tf.reduce_max(sample[0]))
def main():
conv_net = Sequential(conv_layers)
# conv_net.build(input_shape=[None, 32, 32, 3])
# x = tf.random.normal([4, 32, 32, 3])
# out = conv_net(x)
# print(out.shape)
fc_net = Sequential([
layers.Dense(256, activation=tf.nn.relu),
layers.Dense(128, activation=tf.nn.relu),
layers.Dense(100, activation=tf.nn.relu),
])
conv_net.build(input_shape=[None, 32, 32, 3])
fc_net.build(input_shape=[None, 512])
optimizer = optimizers.Adam(lr=1e-4)
variables = conv_net.trainable_variables + fc_net.trainable_variables
for epoch in range(3):
for step, (x, y) in enumerate(train_db):
with tf.GradientTape() as tape:
# [b, 32, 32, 3] => [b, 1, 1, 512]
out = conv_net(x)
# flatten => [b, 512]
out = tf.reshape(out, [-1, 512])
# [b, 512] => [b, 100]
logits = fc_net(out)
# [b] => [b, 100]
y_onehot = tf.one_hot(y, depth=100)
# compute loss
loss = tf.losses.categorical_crossentropy(y_onehot, logits, from_logits=True)
loss = tf.reduce_mean(loss)
grads = tape.gradient(loss, variables)
optimizer.apply_gradients(zip(grads, variables))
if step % 100 == 0:
print(epoch, step, 'loss:', loss)
total_num = 0
total_correct = 0
for x, y in test_db:
out = conv_net(x)
out = tf.reshape(out, [-1, 512])
logits = fc_net(out)
prob = tf.nn.softmax(logits, axis=1)
pred = tf.argmax(prob, axis=1)
pred = tf.cast(pred, dtype=tf.int32)
correct = tf.cast(tf.equal(pred, y), dtype=tf.int32)
correct = tf.reduce_sum(correct)
total_num = x.shape[0]
total_correct += int(correct)
acc = total_correct / total_num
print(epoch, 'acc', acc)
if __name__ == '__main__':
main()