Skip to content

T
Tensorflow Deep Learning

别团等shy哥发育 / Tensorflow Deep Learning
9 个月 前同步成功

通知 1
Star 1
Fork 0
T
Tensorflow Deep Learning

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

提交 c866cb78 编写于 作者: 别团等shy哥发育's avatar 别团等shy哥发育
浏览文件
操作

RegNetX架构复现--CVPR2020

上级 be51173c
隐藏空白更改
内联 并排
Showing with 420 addition and 37 deletion
图像识别/adidas and nike二分类/鞋子识别.py
浏览文件 @ c866cb78
......@@ -3,8 +3,10 @@ import tensorflow as tf
import os
import datetime
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications import MobileNet
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.models import Sequential
from tensorflow.keras import layers
from tensorflow.keras.layers import Dense, Dropout, Conv2D, MaxPool2D, Flatten
from tensorflow.keras.optimizers import Adam
# 设置GPU显存按需申请
......@@ -40,7 +42,15 @@ train_datagen = ImageDataGenerator(
)
# 验证集数据只需要归一化就可以
val_datagen = ImageDataGenerator(
rotation_range=20, # 随机旋转度数
width_shift_range=0.1, # 随机水平平移
height_shift_range=0.1, # 随机竖直平移
rescale=1 / 255, # 数据归一化
shear_range=10, # 随机错切变换
zoom_range=0.1, # 随机放大
horizontal_flip=True, # 水平翻转
brightness_range=(0.7, 1.3), # 亮度变化
fill_mode='nearest', # 填充方式
)
# 测试集数据只需要归一化就可以
test_datagen = ImageDataGenerator(
......@@ -73,27 +83,38 @@ print(train_generator.class_indices)
# # x_train,y_train=next(it)
# # y_train
# AlexNet
model = Sequential()
# 卷积层
model.add(
Conv2D(filters=96, kernel_size=(11, 11), strides=(4, 4), padding='valid', input_shape=(image_size, image_size, 3),
activation='relu'))
model.add(MaxPool2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
model.add(Conv2D(filters=256, kernel_size=(5, 5), strides=(1, 1), padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
model.add(Conv2D(filters=384, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu'))
model.add(Conv2D(filters=384, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu'))
model.add(Conv2D(filters=256, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
# 全连接层
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
# model = Sequential()
# # 卷积层
# model.add(
# Conv2D(filters=96, kernel_size=(11, 11), strides=(4, 4), padding='valid', input_shape=(image_size, image_size, 3),
# activation='relu'))
# model.add(MaxPool2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
# model.add(Conv2D(filters=256, kernel_size=(5, 5), strides=(1, 1), padding='same', activation='relu'))
# model.add(MaxPool2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
# model.add(Conv2D(filters=384, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu'))
# model.add(Conv2D(filters=384, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu'))
# model.add(Conv2D(filters=256, kernel_size=(3, 3), strides=(1, 1), padding='same', activation='relu'))
# model.add(MaxPool2D(pool_size=(3, 3), strides=(2, 2), padding='valid'))
# # 全连接层
# model.add(Flatten())
# model.add(Dense(4096, activation='relu'))
# model.add(Dropout(0.5))
# model.add(Dense(4096, activation='relu'))
# model.add(Dropout(0.5))
# model.add(Dense(num_classes, activation='softmax'))
model = MobileNet(
input_shape=(224, 224, 3), alpha=1.0, depth_multiplier=1, dropout=0.001,
include_top=False, weights='imagenet', input_tensor=None, pooling=None,
classes=num_classes
)
model = Sequential([
model,
layers.GlobalAveragePooling2D(),
Dense(num_classes, activation='softmax')
])
# 模型概要
model.summary()
# model.summary()
# plot_model(model, to_file='AlexNet—鞋子分类.png', show_shapes=True)
# 学习率调节函数，逐渐减小学习率
......@@ -108,15 +129,17 @@ def adjust_learning_rate(epoch):
else:
lr = 1e-6
return lr
# 定义优化器
adam = Adam(lr=1e-4)
# 定义学习率衰减策略
learningRateSchedular=LearningRateScheduler(adjust_learning_rate)
learningRateSchedular = LearningRateScheduler(adjust_learning_rate)
# 定义TensorBoard
# 日志保存文件夹的格式
logdir = os.path.join('logdir', datetime.datetime.now().strftime('%Y%m%d-%H%M%S'))
tensorboar_callback = tf.keras.callbacks.TensorBoard(logdir) # 定义callback
# logdir = os.path.join('logdir', datetime.datetime.now().strftime('%Y%m%d-%H%M%S'))
# tensorboar_callback = tf.keras.callbacks.TensorBoard(logdir) # 定义callback
# 定义优化器，loss function，训练过程中计算准确率
model.compile(optimizer=adam, loss='categorical_crossentropy', metrics=['accuracy'])
......@@ -124,7 +147,7 @@ model.compile(optimizer=adam, loss='categorical_crossentropy', metrics=['accurac
history = model.fit(x=train_generator,
epochs=epochs,
validation_data=val_generator,
callbacks=[tensorboar_callback,learningRateSchedular])
callbacks=[learningRateSchedular])
# 显示训练集和验证集的acc和loss曲线
acc = history.history['accuracy']
......@@ -145,23 +168,15 @@ plt.title('Training and Validation Loss')
plt.legend()
plt.show()
# 模型预测
# adidass_(28).jpg Image_190.jpg
test_img=tf.keras.preprocessing.image.load_img('adidass_(28).jpg ',target_size=(image_size,image_size))
test_img = tf.keras.preprocessing.image.load_img('adidass_(28).jpg ', target_size=(image_size, image_size))
print(test_img)
test_img=tf.keras.preprocessing.image.img_to_array(test_img) # 类型变换
test_img = tf.keras.preprocessing.image.img_to_array(test_img) # 类型变换
print(test_img.shape)
test_img=tf.expand_dims(test_img,0) # 扩充一维
test_img = tf.expand_dims(test_img, 0) # 扩充一维
print(test_img.shape)
preds=model.predict(test_img) # 预测
preds = model.predict(test_img) # 预测
print(preds.shape)
print('预测结果:',preds)
print('预测结果:', preds)
经典网络/RegNet--CVPR2020/RegNet.py 0 → 100644
浏览文件 @ c866cb78
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras.models import Model
MODEL_CONFIGS = {
"x002": {
"depths": [1, 1, 4, 7],
"widths": [24, 56, 152, 368],
"group_width": 8,
"default_size": 224,
"block_type": "X"
},
"x004": {
"depths": [1, 2, 7, 12],
"widths": [32, 64, 160, 384],
"group_width": 16,
"default_size": 224,
"block_type": "X"
},
"x006": {
"depths": [1, 3, 5, 7],
"widths": [48, 96, 240, 528],
"group_width": 24,
"default_size": 224,
"block_type": "X"
},
"x008": {
"depths": [1, 3, 7, 5],
"widths": [64, 128, 288, 672],
"group_width": 16,
"default_size": 224,
"block_type": "X"
},
"x016": {
"depths": [2, 4, 10, 2],
"widths": [72, 168, 408, 912],
"group_width": 24,
"default_size": 224,
"block_type": "X"
},
"x032": {
"depths": [2, 6, 15, 2],
"widths": [96, 192, 432, 1008],
"group_width": 48,
"default_size": 224,
"block_type": "X"
},
"x040": {
"depths": [2, 5, 14, 2],
"widths": [80, 240, 560, 1360],
"group_width": 40,
"default_size": 224,
"block_type": "X"
},
"x064": {
"depths": [2, 4, 10, 1],
"widths": [168, 392, 784, 1624],
"group_width": 56,
"default_size": 224,
"block_type": "X"
},
"x080": {
"depths": [2, 5, 15, 1],
"widths": [80, 240, 720, 1920],
"group_width": 120,
"default_size": 224,
"block_type": "X"
},
"x120": {
"depths": [2, 5, 11, 1],
"widths": [224, 448, 896, 2240],
"group_width": 112,
"default_size": 224,
"block_type": "X"
},
"x160": {
"depths": [2, 6, 13, 1],
"widths": [256, 512, 896, 2048],
"group_width": 128,
"default_size": 224,
"block_type": "X"
},
"x320": {
"depths": [2, 7, 13, 1],
"widths": [336, 672, 1344, 2520],
"group_width": 168,
"default_size": 224,
"block_type": "X"
},
"y002": {
"depths": [1, 1, 4, 7],
"widths": [24, 56, 152, 368],
"group_width": 8,
"default_size": 224,
"block_type": "Y"
},
"y004": {
"depths": [1, 3, 6, 6],
"widths": [48, 104, 208, 440],
"group_width": 8,
"default_size": 224,
"block_type": "Y"
},
"y006": {
"depths": [1, 3, 7, 4],
"widths": [48, 112, 256, 608],
"group_width": 16,
"default_size": 224,
"block_type": "Y"
},
"y008": {
"depths": [1, 3, 8, 2],
"widths": [64, 128, 320, 768],
"group_width": 16,
"default_size": 224,
"block_type": "Y"
},
"y016": {
"depths": [2, 6, 17, 2],
"widths": [48, 120, 336, 888],
"group_width": 24,
"default_size": 224,
"block_type": "Y"
},
"y032": {
"depths": [2, 5, 13, 1],
"widths": [72, 216, 576, 1512],
"group_width": 24,
"default_size": 224,
"block_type": "Y"
},
"y040": {
"depths": [2, 6, 12, 2],
"widths": [128, 192, 512, 1088],
"group_width": 64,
"default_size": 224,
"block_type": "Y"
},
"y064": {
"depths": [2, 7, 14, 2],
"widths": [144, 288, 576, 1296],
"group_width": 72,
"default_size": 224,
"block_type": "Y"
},
"y080": {
"depths": [2, 4, 10, 1],
"widths": [168, 448, 896, 2016],
"group_width": 56,
"default_size": 224,
"block_type": "Y"
},
"y120": {
"depths": [2, 5, 11, 1],
"widths": [224, 448, 896, 2240],
"group_width": 112,
"default_size": 224,
"block_type": "Y"
},
"y160": {
"depths": [2, 4, 11, 1],
"widths": [224, 448, 1232, 3024],
"group_width": 112,
"default_size": 224,
"block_type": "Y"
},
"y320": {
"depths": [2, 5, 12, 1],
"widths": [232, 696, 1392, 3712],
"group_width": 232,
"default_size": 224,
"block_type": "Y"
},
}
# 将输入重新缩放并归一化为[0,1]和ImageNet均值和std
def PreStem(x, name=None):
x = layers.experimental.preprocessing.Rescaling(1. / 255.)(x)
return x
# 论文中的stem(stride=2 3x3卷积+w0 = 32 output channels）
def Stem(x, name=None):
x = layers.Conv2D(32,
(3, 3),
strides=2,
use_bias=False,
padding='same',
kernel_initializer='he_normal',
name=name + '_stem_conv')(x)
x = layers.BatchNormalization(
momentum=0.9, epsilon=1e-5, name=name + "_stem_bn")(x)
x = layers.ReLU(name=name + '_stem_relu')(x)
return x
# XBlock实现:1x1卷积+3x3分组卷积+1x1卷积(conv后跟BN+ReLU)
def XBlock(inputs, filters_in, filters_out, group_width, stride=1, name=None):
# declare layers
groups = filters_out // group_width
# 当stide=2的时候，残差边需要使用1x1卷积降维处理保持shape一致
if stride != 1:
skip = layers.Conv2D(
filters_out,
(1, 1),
strides=stride,
use_bias=False,
kernel_initializer='he_normal',
name=name + '_skip_1x1')(inputs)
skip = layers.BatchNormalization(
momentum=0.9, epsilon=1e-5, name=name + "_skip_bn")(skip)
else:
skip = inputs
# build block
# conv_1x1_1
x = layers.Conv2D(
filters_out,
(1, 1),
use_bias=False,
kernel_initializer='he_normal',
name=name + '_conv_1x1_1')(inputs)
x = layers.BatchNormalization(
momentum=0.9, epsilon=1e-5, name=name + "_conv_1x1_1_bn")(x)
x = layers.ReLU(name=name + "_conv_1x1_1_relu")(x)
# group conv_3x3
x = layers.Conv2D(
filters_out,
(3, 3),
use_bias=False,
strides=stride,
groups=groups,
padding='same',
kernel_initializer='he_normal',
name=name + '_conv_3x3')(x)
x = layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name=name + "_conv_3x3_bn")(x)
x = layers.ReLU(name=name + "_conv_3x3_relu")(x)
# conv_1x1_2
x = layers.Conv2D(
filters_out, (1, 1),
use_bias=False,
kernel_initializer="he_normal",
name=name + "_conv_1x1_2")(x)
x = layers.BatchNormalization(momentum=0.9, epsilon=1e-5, name=name + "_conv_1x1_2_bn")(x)
x = layers.ReLU(name=name + "_exit_relu")(x + skip)
return x
def Stage(inputs,
block_type, # 必须是X、Y、Z之一
depth, # stage深度，要使用的块数
group_width, # 本stage所有块的group宽度
filters_in, #
filters_out,
name=None): # 名称前缀
x = inputs
if block_type == "X":
# 论文原话：Stage的第一个block的步长为2
x = XBlock(
x,
filters_in,
filters_out,
group_width,
stride=2,
name=f"{name}_XBlock_0")
for i in range(1, depth):
x = XBlock(x,filters_out, filters_out, group_width, name=f"{name}_XBlock_{i}")
# TODO YBlock,ZBlock
return x
def Head(x, num_classes=1000, name=None):
x = layers.GlobalAveragePooling2D(name=name+'_head_gap')(x)
x = layers.Dense(num_classes, name=name+'head_dense')(x)
return x
def RegNet(depths, # 每个stage的深度
widths, # 块宽度(输出通道数)
group_width, # 每组中要使用的通道数
block_type, # "X","Y","Z"之一
default_size, # 默认输入图像大小
model_name='regnet', # 模型的可选名称
include_preprocessing=True, # 是否包含预处理
include_top=True, # 是否包含分类头
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000, # 可选的类数量
classifier_activation='softmax'): # 分类器激活
img_input = layers.Input(shape=input_shape)
inputs = img_input
x = inputs
if include_preprocessing:
x = PreStem(x, name=model_name)
x = Stem(x, name=model_name)
in_channels = 32 # Output from Stem
for num_stage in range(4):
depth = depths[num_stage]
out_channels = widths[num_stage]
x = Stage(x,
block_type,
depth,
group_width,
in_channels,
out_channels,
name=model_name + '_Stage_' + str(num_stage))
in_channels = out_channels
if include_top:
x = Head(x, num_classes=classes,name='head')
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x - layers.GlobalMaxPooling2D()(x)
model = Model(inputs=inputs, outputs=x, name=model_name)
return model
'''
"x002": {
"depths": [1, 1, 4, 7],
"widths": [24, 56, 152, 368],
"group_width": 8,
"default_size": 224,
"block_type": "X"
}
'''
def RegNetX002(model_name='regnetx002',
include_top=True,
include_preprocessing=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax'):
return RegNet(
MODEL_CONFIGS['x002']['depths'],
MODEL_CONFIGS['x002']['widths'],
MODEL_CONFIGS['x002']['group_width'],
MODEL_CONFIGS['x002']['block_type'],
MODEL_CONFIGS['x002']['default_size'],
model_name=model_name,
include_top=include_top,
include_preprocessing=include_preprocessing,
weights=weights,
input_tensor=input_tensor,
input_shape=input_shape,
pooling=pooling,
classes=classes,
classifier_activation=classifier_activation
)
if __name__ == '__main__':
model = RegNetX002(input_shape=(224, 224, 3))
model.summary()
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或