ResNet实战

目录

* Res Block <https://www.cnblogs.com/nickchen121/p/10960206.html#res-block>
* ResNet18 <https://www.cnblogs.com/nickchen121/p/10960206.html#resnet18>
* Out of memory
<https://www.cnblogs.com/nickchen121/p/10960206.html#out-of-memory>

# Resnet.py #!/usr/bin/env python # -*- coding:utf-8 -*- import tensorflow as
tf from tensorflow import keras from tensorflow.keras import layers, Sequential
class BasicBlock(layers.Layer): def __init__(self, filter_num, stride=1):
super(BasicBlock, self).__init__() self.conv1 = layers.Conv2D(filter_num, (3,
3), strides=stride, padding='same') self.bn1 = layers.BatchNormalization()
self.relu = layers.Activation('relu') self.conv2 = layers.Conv2D(filter_num,
(3, 3), strides=1, padding='same') self.bn2 = layers.BatchNormalization() if
stride != 1: self.downsample = Sequential()
self.downsample.add(layers.Conv2D(filter_num, (1, 1), strides=stride)) else:
self.downsample = lambda x: x def call(self, inputs, training=None): #
[b,h,w,c] out = self.conv1(inputs) out = self.bn1(out) out = self.relu(out) out
= self.conv2(out) out = self.bn2(out) identity = self.downsample(inputs) output
= layers.add([out, identity]) output = tf.nn.relu(output) return out
Res Block



ResNet18


# Resnet.py #!/usr/bin/env python # -*- coding:utf-8 -*- import tensorflow as
tf from tensorflow import keras from tensorflow.keras import layers, Sequential
class BasicBlock(layers.Layer): def __init__(self, filter_num, stride=1):
super(BasicBlock, self).__init__() self.conv1 = layers.Conv2D(filter_num, (3,
3), strides=stride, padding='same') self.bn1 = layers.BatchNormalization()
self.relu = layers.Activation('relu') self.conv2 = layers.Conv2D(filter_num,
(3, 3), strides=1, padding='same') self.bn2 = layers.BatchNormalization() if
stride != 1: self.downsample = Sequential()
self.downsample.add(layers.Conv2D(filter_num, (1, 1), strides=stride)) else:
self.downsample = lambda x: x def call(self, inputs, training=None): #
[b,h,w,c] out = self.conv1(inputs) out = self.bn1(out) out = self.relu(out) out
= self.conv2(out) out = self.bn2(out) identity = self.downsample(inputs) output
= layers.add([out, identity]) output = tf.nn.relu(output) return out class
ResNet(keras.Model): def __init__(self, layer_dims, num_classes=100): #
[2,2,2,2] super(ResNet, self).__init__() # 根部 self.stem =
Sequential([layers.Conv2D(64, (3, 3), strides=(1, 1,)),
layers.BatchNormalization(), layers.Activation('relu'),
layers.MaxPool2D(pool_size=(2, 2), strides=(1, 1), padding='same') ]) #
64,128,256,512是通道数 self.layer1 = self.build_resblock(64, layer_dims[0])
self.layer2 = self.build_resblock(128, layer_dims[1], stride=2) self.layer3 =
self.build_resblock(256, layer_dims[2], stride=2) self.layer4 =
self.build_resblock(512, layer_dims[3], stride=2) # output: [b, 512, h, w]
self.avgpool = layers.GlobalAveragePooling2D() self.fc =
layers.Dense(num_classes) # 分类 def call(self, inputs, training=None): x =
self.stem(inputs) x = self.layer1(x) x = self.layer2(x) x = self.layer3(x) x =
self.layer4(x) # [b, c] x = self.avgpool(x) # [b] x = self.fc(x) return x def
build_resblock(self, filter_num, blocks, stride=1): res_blocks = Sequential() #
may down sample res_blocks.add(BasicBlock(filter_num, stride)) for _ in
range(1, blocks): res_blocks.add(BasicBlock(filter_num, stride=1)) return
res_blocks def resnet18(): return ResNet([2, 2, 2, 2]) def resnet34(): return
ResNet([3, 4, 6, 3]) # resnet18_train.py #!/usr/bin/env python # -*-
coding:utf-8 -*- import tensorflow as tf from tensorflow.keras import layers,
optimizers, datasets, Sequential import os from Resnet import resnet18
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' tf.random.set_seed(2345) def
preprocess(x, y): # [-1~1] x = tf.cast(x, dtype=tf.float32) / 255. - 0.5 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) y_test =
tf.squeeze(y_test, 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(512) test_db =
tf.data.Dataset.from_tensor_slices((x_test, y_test)) test_db =
test_db.map(preprocess).batch(512) 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(): # [b, 32, 32, 3] => [b, 1, 1, 512] model
= resnet18() model.build(input_shape=(None, 32, 32, 3)) model.summary()
optimizer = optimizers.Adam(lr=1e-3) for epoch in range(500): for step, (x, y)
in enumerate(train_db): with tf.GradientTape() as tape: # [b, 32, 32, 3] => [b,
100] logits = model(x) # [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,
model.trainable_variables) optimizer.apply_gradients(zip(grads,
model.trainable_variables)) if step % 50 == 0: print(epoch, step, 'loss:',
float(loss)) total_num = 0 total_correct = 0 for x, y in test_db: logits =
model(x) 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() (50000, 32, 32, 3) (50000,)
(10000, 32, 32, 3) (10000,) sample: (512, 32, 32, 3) (512,) tf.Tensor(-0.5,
shape=(), dtype=float32) tf.Tensor(0.5, shape=(), dtype=float32) Model:
"res_net" _________________________________________________________________
Layer (type) Output Shape Param #
================================================================= sequential
(Sequential) multiple 2048
_________________________________________________________________ sequential_1
(Sequential) multiple 148736
_________________________________________________________________ sequential_2
(Sequential) multiple 526976
_________________________________________________________________ sequential_4
(Sequential) multiple 2102528
_________________________________________________________________ sequential_6
(Sequential) multiple 8399360
_________________________________________________________________
global_average_pooling2d (Gl multiple 0
_________________________________________________________________ dense (Dense)
multiple 51300
================================================================= Total params:
11,230,948 Trainable params: 11,223,140 Non-trainable params: 7,808
_________________________________________________________________ WARNING:
Logging before flag parsing goes to stderr. W0601 16:59:57.619546 4664264128
optimizer_v2.py:928] Gradients does not exist for variables
['sequential_2/basic_block_2/sequential_3/conv2d_7/kernel:0',
'sequential_2/basic_block_2/sequential_3/conv2d_7/bias:0',
'sequential_4/basic_block_4/sequential_5/conv2d_12/kernel:0',
'sequential_4/basic_block_4/sequential_5/conv2d_12/bias:0',
'sequential_6/basic_block_6/sequential_7/conv2d_17/kernel:0',
'sequential_6/basic_block_6/sequential_7/conv2d_17/bias:0'] when minimizing the
loss. 0 0 loss: 4.60512638092041
Out of memory

*
* decrease batch size
*
* tune resnet[2,2,2,2]
*
* try Google CoLab
*
* buy new NVIDIA GPU Card

• « 上一篇：对付时间不充足的项目的一些思路
• » 下一篇：Vue新手学习笔记：vue-cli框架