建设咨询网站,电商创业怎么做,wordpress百度地图主题,哪有做网站的 优帮云GoogLeNet卷积神经网络输出数据形参分析-笔记
分析结果为#xff1a; 输入数据形状:[10, 3, 224, 224] 最后输出结果#xff1a;linear_0 [10, 1] [1024, 1] [1]
子空间执行逻辑
def forward_old(self, x):# 支路1只包含一个1x1卷积p1 F.relu(self.p1_1(x))# 支路2包含 1…GoogLeNet卷积神经网络输出数据形参分析-笔记
分析结果为 输入数据形状:[10, 3, 224, 224] 最后输出结果linear_0 [10, 1] [1024, 1] [1]
子空间执行逻辑
def forward_old(self, x):# 支路1只包含一个1x1卷积p1 F.relu(self.p1_1(x))# 支路2包含 1x1卷积 3x3卷积p2 F.relu(self.p2_2(F.relu(self.p2_1(x))))# 支路3包含 1x1卷积 5x5卷积p3 F.relu(self.p3_2(F.relu(self.p3_1(x))))# 支路4包含 最大池化和1x1卷积p4 F.relu(self.p4_2(self.p4_1(x)))# 将每个支路的输出特征图拼接在一起作为最终的输出结果return paddle.concat([p1, p2, p3, p4], axis1)# return self.batchnorm()其中拼接张量情况为 拼接代码paddle.concat([p1, p2, p3, p4], axis1) 如 p1[10,64,5,6,56] p2[10,128,56,56] p3[10,32,56,56] p4[10,32,56,56] 拼接后结果为【102565656】 sum(641283232)256
分析详细过程如下所示
PS E:\project\python D:/ProgramData/Anaconda3/python.exe e:/project/python/PM/GoogLeNet_PM.py
W0804 11:14:26.736726 5484 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.2, Runtime API Version: 10.2
W0804 11:14:26.747695 5484 gpu_resources.cc:91] device: 0, cuDNN Version: 7.6.
116
(10, 3, 224, 224)
[10, 3, 224, 224]
#第一模块 包括一个7X7的卷积
conv2d_0 [10, 64, 224, 224] [64, 3, 7, 7] [64]
# 3x3最大池化
max_pool2d_0 [10, 64, 112, 112]
# 第二个模块包含2个卷积层
conv2d_1 [10, 64, 112, 112] [64, 64, 1, 1] [64]
conv2d_2 [10, 192, 112, 112] [192, 64, 3, 3] [192]
# 3x3最大池化
max_pool2d_1 [10, 192, 56, 56]
# 第三个模块包含2个Inception块
print block3-1: Inception盗梦空间1 即子空间1
conv2d_3 [10, 64, 56, 56] [64, 192, 1, 1] [64]
conv2d_4 [10, 96, 56, 56] [96, 192, 1, 1] [96]
conv2d_5 [10, 128, 56, 56] [128, 96, 3, 3] [128]
conv2d_6 [10, 16, 56, 56] [16, 192, 1, 1] [16]
conv2d_7 [10, 32, 56, 56] [32, 16, 5, 5] [32]
max_pool2d_2 [10, 192, 56, 56]
conv2d_8 [10, 32, 56, 56] [32, 192, 1, 1] [32]
block3_1.shape [10, 256, 56, 56]
print block3-2: Inception盗梦空间2 即子空间2
conv2d_9 [10, 128, 56, 56] [128, 256, 1, 1] [128]
conv2d_10 [10, 128, 56, 56] [128, 256, 1, 1] [128]
conv2d_11 [10, 192, 56, 56] [192, 128, 3, 3] [192]
conv2d_12 [10, 32, 56, 56] [32, 256, 1, 1] [32]
conv2d_13 [10, 96, 56, 56] [96, 32, 5, 5] [96]
max_pool2d_3 [10, 256, 56, 56]
conv2d_14 [10, 64, 56, 56] [64, 256, 1, 1] [64]
block3_2.shape [10, 480, 56, 56]
# 3x3最大池化
max_pool2d_4 [10, 480, 28, 28]
# 第四个模块包含5个Inception块
print block4_1:
conv2d_15 [10, 192, 28, 28] [192, 480, 1, 1] [192]
conv2d_16 [10, 96, 28, 28] [96, 480, 1, 1] [96]
conv2d_17 [10, 208, 28, 28] [208, 96, 3, 3] [208]
conv2d_18 [10, 16, 28, 28] [16, 480, 1, 1] [16]
conv2d_19 [10, 48, 28, 28] [48, 16, 5, 5] [48]
max_pool2d_5 [10, 480, 28, 28]
conv2d_20 [10, 64, 28, 28] [64, 480, 1, 1] [64]
block4_1.shape [10, 512, 28, 28]
print block4_2:
conv2d_21 [10, 160, 28, 28] [160, 512, 1, 1] [160]
conv2d_22 [10, 112, 28, 28] [112, 512, 1, 1] [112]
conv2d_23 [10, 224, 28, 28] [224, 112, 3, 3] [224]
conv2d_24 [10, 24, 28, 28] [24, 512, 1, 1] [24]
conv2d_25 [10, 64, 28, 28] [64, 24, 5, 5] [64]
max_pool2d_6 [10, 512, 28, 28]
conv2d_26 [10, 64, 28, 28] [64, 512, 1, 1] [64]
block4_2.shape [10, 512, 28, 28]
print block4_3:
conv2d_27 [10, 128, 28, 28] [128, 512, 1, 1] [128]
conv2d_28 [10, 128, 28, 28] [128, 512, 1, 1] [128]
conv2d_29 [10, 256, 28, 28] [256, 128, 3, 3] [256]
conv2d_30 [10, 24, 28, 28] [24, 512, 1, 1] [24]
conv2d_31 [10, 64, 28, 28] [64, 24, 5, 5] [64]
max_pool2d_7 [10, 512, 28, 28]
conv2d_32 [10, 64, 28, 28] [64, 512, 1, 1] [64]
block4_3.shape [10, 512, 28, 28]
print block4_4:
conv2d_33 [10, 112, 28, 28] [112, 512, 1, 1] [112]
conv2d_34 [10, 144, 28, 28] [144, 512, 1, 1] [144]
conv2d_35 [10, 288, 28, 28] [288, 144, 3, 3] [288]
conv2d_36 [10, 32, 28, 28] [32, 512, 1, 1] [32]
conv2d_37 [10, 64, 28, 28] [64, 32, 5, 5] [64]
max_pool2d_8 [10, 512, 28, 28]
conv2d_38 [10, 64, 28, 28] [64, 512, 1, 1] [64]
block4_4.shape [10, 528, 28, 28]
print block4_5:
conv2d_39 [10, 256, 28, 28] [256, 528, 1, 1] [256]
conv2d_40 [10, 160, 28, 28] [160, 528, 1, 1] [160]
conv2d_41 [10, 320, 28, 28] [320, 160, 3, 3] [320]
conv2d_42 [10, 32, 28, 28] [32, 528, 1, 1] [32]
conv2d_43 [10, 128, 28, 28] [128, 32, 5, 5] [128]
max_pool2d_9 [10, 528, 28, 28]
conv2d_44 [10, 128, 28, 28] [128, 528, 1, 1] [128]
block4_5.shape [10, 832, 28, 28]
max_pool2d_10 [10, 832, 14, 14]
# 第五个模块包含2个Inception块(block5_1,block5_2)
print block5_1:
conv2d_45 [10, 256, 14, 14] [256, 832, 1, 1] [256]
conv2d_46 [10, 160, 14, 14] [160, 832, 1, 1] [160]
conv2d_47 [10, 320, 14, 14] [320, 160, 3, 3] [320]
conv2d_48 [10, 32, 14, 14] [32, 832, 1, 1] [32]
conv2d_49 [10, 128, 14, 14] [128, 32, 5, 5] [128]
max_pool2d_11 [10, 832, 14, 14]
conv2d_50 [10, 128, 14, 14] [128, 832, 1, 1] [128]
block5_1.shape [10, 832, 14, 14]
print block5_2:
conv2d_51 [10, 384, 14, 14] [384, 832, 1, 1] [384]
conv2d_52 [10, 192, 14, 14] [192, 832, 1, 1] [192]
conv2d_53 [10, 384, 14, 14] [384, 192, 3, 3] [384]
conv2d_54 [10, 48, 14, 14] [48, 832, 1, 1] [48]
conv2d_55 [10, 128, 14, 14] [128, 48, 5, 5] [128]
max_pool2d_12 [10, 832, 14, 14]
conv2d_56 [10, 128, 14, 14] [128, 832, 1, 1] [128]
block5_2.shape [10, 1024, 14, 14]
adaptive_avg_pool2d_0 [10, 1024, 1, 1]
linear_0 [10, 1] [1024, 1] [1]
PS E:\project\python分析测试代码如下所示
# GoogLeNet模型代码
#GoogLeNet卷积神经网络-笔记
import numpy as np
import paddle
from paddle.nn import Conv2D, MaxPool2D, AdaptiveAvgPool2D, Linear
## 组网
import paddle.nn.functional as F#分析形参定制版本方法
def printItem(item,x):# item是CNN类中的一个子层# 查看经过子层之后的输出数据形状try:x item(x)except:x paddle.reshape(x, [x.shape[0], -1])x item(x) if len(item.parameters())2:# 查看卷积和全连接层的数据和参数的形状# 其中item.parameters()[0]是权重参数witem.parameters()[1]是偏置参数bprint(item.full_name(), x.shape, item.parameters()[0].shape, item.parameters()[1].shape)else:# 池化层没有参数print(item.full_name(), x.shape) return x; # 定义Inception块
class Inception(paddle.nn.Layer):def __init__(self, c0, c1, c2, c3, c4, **kwargs):Inception模块的实现代码c1,图(b)中第一条支路1x1卷积的输出通道数数据类型是整数c2,图(b)中第二条支路卷积的输出通道数数据类型是tuple或list, 其中c2[0]是1x1卷积的输出通道数c2[1]是3x3c3,图(b)中第三条支路卷积的输出通道数数据类型是tuple或list, 其中c3[0]是1x1卷积的输出通道数c3[1]是3x3c4,图(b)中第一条支路1x1卷积的输出通道数数据类型是整数super(Inception, self).__init__()# 依次创建Inception块每条支路上使用到的操作self.p1_1 Conv2D(in_channelsc0,out_channelsc1, kernel_size1, stride1)self.p2_1 Conv2D(in_channelsc0,out_channelsc2[0], kernel_size1, stride1)self.p2_2 Conv2D(in_channelsc2[0],out_channelsc2[1], kernel_size3, padding1, stride1)self.p3_1 Conv2D(in_channelsc0,out_channelsc3[0], kernel_size1, stride1)self.p3_2 Conv2D(in_channelsc3[0],out_channelsc3[1], kernel_size5, padding2, stride1)self.p4_1 MaxPool2D(kernel_size3, stride1, padding1)self.p4_2 Conv2D(in_channelsc0,out_channelsc4, kernel_size1, stride1)# # 新加一层batchnorm稳定收敛# self.batchnorm paddle.nn.BatchNorm2D(c1c2[1]c3[1]c4)def forward_old(self, x):# 支路1只包含一个1x1卷积p1 F.relu(self.p1_1(x))# 支路2包含 1x1卷积 3x3卷积p2 F.relu(self.p2_2(F.relu(self.p2_1(x))))# 支路3包含 1x1卷积 5x5卷积p3 F.relu(self.p3_2(F.relu(self.p3_1(x))))# 支路4包含 最大池化和1x1卷积p4 F.relu(self.p4_2(self.p4_1(x)))# 将每个支路的输出特征图拼接在一起作为最终的输出结果return paddle.concat([p1, p2, p3, p4], axis1)# return self.batchnorm()#分析形参定制版本方法def forward(self,x):p1printItem(self.p1_1,x)p1F.relu(p1)#p2printItem(self.p2_1,x)p2F.relu(p2)p2printItem(self.p2_2,p2)p2F.relu(p2)#p3printItem(self.p3_1,x)p3F.relu(p3)p3printItem(self.p3_2,p3)p3F.relu(p3)#p4printItem(self.p4_1,x)p4printItem(self.p4_2,p4)p4F.relu(p4)return paddle.concat([p1, p2, p3, p4], axis1);class GoogLeNet(paddle.nn.Layer):def __init__(self):super(GoogLeNet, self).__init__()# GoogLeNet包含五个模块每个模块后面紧跟一个池化层# 第一个模块包含1个卷积层self.conv1 Conv2D(in_channels3,out_channels64, kernel_size7, padding3, stride1)# 3x3最大池化self.pool1 MaxPool2D(kernel_size3, stride2, padding1)# 第二个模块包含2个卷积层self.conv2_1 Conv2D(in_channels64,out_channels64, kernel_size1, stride1)self.conv2_2 Conv2D(in_channels64,out_channels192, kernel_size3, padding1, stride1)# 3x3最大池化self.pool2 MaxPool2D(kernel_size3, stride2, padding1)# 第三个模块包含2个Inception块self.block3_1 Inception(192, 64, (96, 128), (16, 32), 32)self.block3_2 Inception(256, 128, (128, 192), (32, 96), 64)# 3x3最大池化self.pool3 MaxPool2D(kernel_size3, stride2, padding1)# 第四个模块包含5个Inception块self.block4_1 Inception(480, 192, (96, 208), (16, 48), 64)self.block4_2 Inception(512, 160, (112, 224), (24, 64), 64)self.block4_3 Inception(512, 128, (128, 256), (24, 64), 64)self.block4_4 Inception(512, 112, (144, 288), (32, 64), 64)self.block4_5 Inception(528, 256, (160, 320), (32, 128), 128)# 3x3最大池化self.pool4 MaxPool2D(kernel_size3, stride2, padding1)# 第五个模块包含2个Inception块self.block5_1 Inception(832, 256, (160, 320), (32, 128), 128)self.block5_2 Inception(832, 384, (192, 384), (48, 128), 128)# 全局池化用的是global_pooling不需要设置pool_strideself.pool5 AdaptiveAvgPool2D(output_size1)self.fc Linear(in_features1024, out_features1)def forward(self, x):x self.pool1(F.relu(self.conv1(x)))x self.pool2(F.relu(self.conv2_2(F.relu(self.conv2_1(x)))))x self.pool3(self.block3_2(self.block3_1(x)))x self.block4_3(self.block4_2(self.block4_1(x)))x self.pool4(self.block4_5(self.block4_4(x)))x self.pool5(self.block5_2(self.block5_1(x)))x paddle.reshape(x, [x.shape[0], -1])x self.fc(x)return x#分析形参定制版本方法 def printStruct(self,x):print(x.shape)x paddle.to_tensor(x) #转为张量xprint(x.shape)#xprintItem(self.conv1,x)xF.relu(x)xprintItem(self.pool1,x)#xprintItem(self.conv2_1,x) xF.relu(x)xprintItem(self.conv2_2,x) xF.relu(x) xprintItem(self.pool2,x)# print(print block3-1:) xself.block3_1(x)print(block3_1.shape,x.shape)print(print block3-2:) xself.block3_2(x) print(block3_2.shape,x.shape) xprintItem(self.pool3,x) #print(print block4_1:) xself.block4_1(x)print(block4_1.shape,x.shape) print(print block4_2:) xself.block4_2(x) print(block4_2.shape,x.shape)print(print block4_3:) xself.block4_3(x) print(block4_3.shape,x.shape)print(print block4_4:) xself.block4_4(x) print(block4_4.shape,x.shape)print(print block4_5:) xself.block4_5(x) print(block4_5.shape,x.shape) xprintItem(self.pool4,x) #print(print block5_1:) xself.block5_1(x) print(block5_1.shape,x.shape) print(print block5_2:) xself.block5_2(x) print(block5_2.shape,x.shape) xprintItem(self.pool5,x) x paddle.reshape(x, [x.shape[0], -1])xprintItem(self.fc,x)return x#
import PM
# 创建模型
model GoogLeNet()
print(len(model.parameters()))
opt paddle.optimizer.Momentum(learning_rate0.001, momentum0.9, parametersmodel.parameters(), weight_decay0.001)
# 启动训练过程
#PM.train_pm(model, opt)
#输出结果
PS E:\project\python D:/ProgramData/Anaconda3/python.exe e:/project/python/PM/GoogLeNet_PM.py
W0803 18:25:55.522811 8308 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 12.2, Runtime API Version: 10.2
W0803 18:25:55.532805 8308 gpu_resources.cc:91] device: 0, cuDNN Version: 7.6.
116
start training ...
epoch: 0, batch_id: 0, loss is: 0.6920
epoch: 0, batch_id: 20, loss is: 0.8546
[validation] accuracy/loss: 0.7100/0.5381
epoch: 1, batch_id: 0, loss is: 0.6177
epoch: 1, batch_id: 20, loss is: 0.4581
[validation] accuracy/loss: 0.9400/0.3120
epoch: 2, batch_id: 0, loss is: 0.2858
epoch: 2, batch_id: 20, loss is: 0.5234
[validation] accuracy/loss: 0.5975/0.5757
epoch: 3, batch_id: 0, loss is: 0.6338
epoch: 3, batch_id: 20, loss is: 0.3180
[validation] accuracy/loss: 0.9575/0.1915
epoch: 4, batch_id: 0, loss is: 0.1087
epoch: 4, batch_id: 20, loss is: 0.3728
[validation] accuracy/loss: 0.9500/0.2322
PS E:\project\python
# 输入数据形状是 [N, 3, H, W]
# 这里用np.random创建一个随机数组作为输入数据
x np.random.randn(*[10,3,224,224])
x x.astype(float32)
# 创建CNN类的实例指定模型名称和分类的类别数目
#model VGG(1)
#
model.printStruct(x);
#
