基础网络搭建解析
人类对图像的理解和计算机是完全不用的，计算机读取的数据是一串数字，所以理解起来会比较困难。
语义鸿沟，对于计算机来说，像素和区域 极为相似或者迷惑性极强的有些人类不仔细看也容易看错更何况是机器呢？
对于解决这些问题还需要更加努力提高机器的理解和更好的ai技术
图像识别的流程
使用机器学习（深度学习）的目的：寻找一个合适的函数
我们可以通过数据处理、建立模型、训练模型、测试模型等一系类的过程得到一个比较好的结果
神经元
神经元来源于人的神经网络
人神经细胞结构大致可分为：树突、突触、细胞体及轴突。
单个神经细胞可被视为一种只有两种状态的机器——激动时为‘是’，而未激动时为‘否’。
刚刚好可以对应我们计算机的0和1 大量的神经元 进行堆叠 刚好可以对应神经网络
网络结构
网络结构分为线性，卷积等
在一个网络中上一层的输出和本层的输入必须对应
一般我们必须要考虑的是输入层和输出层至于中间的可以统一称为隐藏层
接下去我们进行举例：以输入（1,28,28）输出10为例子构建几个常见的网络
import paddle import paddle.nn as nn from paddle.nn import Linear import paddle.nn.functional as F from paddle.vision.transforms import ToTensor
# 单层线性网络 model=nn.Linear(in_features=1*28*28, out_features=10) # 定义线性网络 paddle.summary(model, (1*28*28))
--------------------------------------------------------------------------- Layer (type) Input Shape Output Shape Param # =========================================================================== Linear-3 [[784]] [10] 7,850 =========================================================================== Total params: 7,850 Trainable params: 7,850 Non-trainable params: 0 --------------------------------------------------------------------------- Input size (MB): 0.00 Forward/backward pass size (MB): 0.00 Params size (MB): 0.03 Estimated Total Size (MB): 0.03 --------------------------------------------------------------------------- {'total_params': 7850, 'trainable_params': 7850}
# DNN class MyDNN(paddle.nn.Layer): def __init__(self): super(MyDNN,self).__init__() self.hidden1 = Linear(28,100) self.hidden2 = Linear(100,100) self.hidden3 = Linear(100,28) self.hidden4 = Linear(1*28*28,10) def forward(self,input): # print(input.shape) x = self.hidden1(input) x =F.relu(x) # print(x.shape) x = self.hidden2(x) x = F.relu(x) # print(x.shape) x = self.hidden3(x) x = F.relu(x) # print(x.shape) x = paddle.reshape(x, shape=[-1,1*28*28]) x = self.hidden4(x) y = F.softmax(x) # print(y.shape) return y network = MyDNN() paddle.summary(network, (1, 28, 28))
--------------------------------------------------------------------------- Layer (type) Input Shape Output Shape Param # =========================================================================== Linear-8 [[1, 28, 28]] [1, 28, 100] 2,900 Linear-9 [[1, 28, 100]] [1, 28, 100] 10,100 Linear-10 [[1, 28, 100]] [1, 28, 28] 2,828 Linear-11 [[1, 784]] [1, 10] 7,850 =========================================================================== Total params: 23,678 Trainable params: 23,678 Non-trainable params: 0 --------------------------------------------------------------------------- Input size (MB): 0.00 Forward/backward pass size (MB): 0.05 Params size (MB): 0.09 Estimated Total Size (MB): 0.14 --------------------------------------------------------------------------- {'total_params': 23678, 'trainable_params': 23678}
CNN说明
network = nn.Sequential( nn.Conv2D(in_channels=1, out_channels=6, kernel_size=3, stride=1, padding=1), # 卷积 nn.ReLU(), # 激活函数 nn.MaxPool2D(kernel_size=2, stride=2), # 最大池化 nn.Conv2D(in_channels=6, out_channels=16, kernel_size=5, stride=1, padding=0), nn.ReLU(), nn.MaxPool2D(kernel_size=2, stride=2), nn.Flatten(), nn.Linear(in_features=400, out_features=120), # 400 = 5x5x16，输入形状为32x32， 输入形状为28x28时调整为256 nn.Linear(in_features=120, out_features=84), nn.Linear(in_features=84, out_features=10) ) paddle.summary(network, (1, 1, 28, 28))
--------------------------------------------------------------------------- Layer (type) Input Shape Output Shape Param # =========================================================================== Conv2D-12 [[1, 1, 28, 28]] [1, 6, 28, 28] 60 ReLU-3 [[1, 6, 28, 28]] [1, 6, 28, 28] 0 MaxPool2D-3 [[1, 6, 28, 28]] [1, 6, 14, 14] 0 Conv2D-13 [[1, 6, 14, 14]] [1, 16, 10, 10] 2,416 ReLU-4 [[1, 16, 10, 10]] [1, 16, 10, 10] 0 MaxPool2D-4 [[1, 16, 10, 10]] [1, 16, 5, 5] 0 Flatten-5 [[1, 16, 5, 5]] [1, 400] 0 Linear-21 [[1, 400]] [1, 120] 48,120 Linear-22 [[1, 120]] [1, 84] 10,164 Linear-23 [[1, 84]] [1, 10] 850 =========================================================================== Total params: 61,610 Trainable params: 61,610 Non-trainable params: 0 --------------------------------------------------------------------------- Input size (MB): 0.00 Forward/backward pass size (MB): 0.11 Params size (MB): 0.24 Estimated Total Size (MB): 0.35 --------------------------------------------------------------------------- {'total_params': 61610, 'trainable_params': 61610}
# api已有网络 network = paddle.vision.models.resnet101(num_classes=10) paddle.summary(network, (1, 3, 224, 224))
------------------------------------------------------------------------------- Layer (type) Input Shape Output Shape Param # =============================================================================== Conv2D-123 [[1, 3, 224, 224]] [1, 64, 112, 112] 9,408 BatchNorm2D-105 [[1, 64, 112, 112]] [1, 64, 112, 112] 256 ReLU-43 [[1, 64, 112, 112]] [1, 64, 112, 112] 0 MaxPool2D-8 [[1, 64, 112, 112]] [1, 64, 56, 56] 0 Conv2D-125 [[1, 64, 56, 56]] [1, 64, 56, 56] 4,096 BatchNorm2D-107 [[1, 64, 56, 56]] [1, 64, 56, 56] 256 ReLU-44 [[1, 256, 56, 56]] [1, 256, 56, 56] 0 Conv2D-126 [[1, 64, 56, 56]] [1, 64, 56, 56] 36,864 BatchNorm2D-108 [[1, 64, 56, 56]] [1, 64, 56, 56] 256 Conv2D-127 [[1, 64, 56, 56]] [1, 256, 56, 56] 16,384 BatchNorm2D-109 [[1, 256, 56, 56]] [1, 256, 56, 56] 1,024 Conv2D-124 [[1, 64, 56, 56]] [1, 256, 56, 56] 16,384 BatchNorm2D-106 [[1, 256, 56, 56]] [1, 256, 56, 56] 1,024 BottleneckBlock-34 [[1, 64, 56, 56]] [1, 256, 56, 56] 0 Conv2D-128 [[1, 256, 56, 56]] [1, 64, 56, 56] 16,384 BatchNorm2D-110 [[1, 64, 56, 56]] [1, 64, 56, 56] 256 ReLU-45 [[1, 256, 56, 56]] [1, 256, 56, 56] 0 Conv2D-129 [[1, 64, 56, 56]] [1, 64, 56, 56] 36,864 BatchNorm2D-111 [[1, 64, 56, 56]] [1, 64, 56, 56] 256 Conv2D-130 [[1, 64, 56, 56]] [1, 256, 56, 56] 16,384 BatchNorm2D-112 [[1, 256, 56, 56]] [1, 256, 56, 56] 1,024 BottleneckBlock-35 [[1, 256, 56, 56]] [1, 256, 56, 56] 0 Conv2D-131 [[1, 256, 56, 56]] [1, 64, 56, 56] 16,384 BatchNorm2D-113 [[1, 64, 56, 56]] [1, 64, 56, 56] 256 ReLU-46 [[1, 256, 56, 56]] [1, 256, 56, 56] 0 Conv2D-132 [[1, 64, 56, 56]] [1, 64, 56, 56] 36,864 BatchNorm2D-114 [[1, 64, 56, 56]] [1, 64, 56, 56] 256 Conv2D-133 [[1, 64, 56, 56]] [1, 256, 56, 56] 16,384 BatchNorm2D-115 [[1, 256, 56, 56]] [1, 256, 56, 56] 1,024 BottleneckBlock-36 [[1, 256, 56, 56]] [1, 256, 56, 56] 0 Conv2D-135 [[1, 256, 56, 56]] [1, 128, 56, 56] 32,768 BatchNorm2D-117 [[1, 128, 56, 56]] [1, 128, 56, 56] 512 ReLU-47 [[1, 512, 28, 28]] [1, 512, 28, 28] 0 Conv2D-136 [[1, 128, 56, 56]] [1, 128, 28, 28] 147,456 BatchNorm2D-118 [[1, 128, 28, 28]] [1, 128, 28, 28] 512 Conv2D-137 [[1, 128, 28, 28]] [1, 512, 28, 28] 65,536 BatchNorm2D-119 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048 Conv2D-134 [[1, 256, 56, 56]] [1, 512, 28, 28] 131,072 BatchNorm2D-116 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048 BottleneckBlock-37 [[1, 256, 56, 56]] [1, 512, 28, 28] 0 Conv2D-138 [[1, 512, 28, 28]] [1, 128, 28, 28] 65,536 BatchNorm2D-120 [[1, 128, 28, 28]] [1, 128, 28, 28] 512 ReLU-48 [[1, 512, 28, 28]] [1, 512, 28, 28] 0 Conv2D-139 [[1, 128, 28, 28]] [1, 128, 28, 28] 147,456 BatchNorm2D-121 [[1, 128, 28, 28]] [1, 128, 28, 28] 512 Conv2D-140 [[1, 128, 28, 28]] [1, 512, 28, 28] 65,536 BatchNorm2D-122 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048 BottleneckBlock-38 [[1, 512, 28, 28]] [1, 512, 28, 28] 0 Conv2D-141 [[1, 512, 28, 28]] [1, 128, 28, 28] 65,536 BatchNorm2D-123 [[1, 128, 28, 28]] [1, 128, 28, 28] 512 ReLU-49 [[1, 512, 28, 28]] [1, 512, 28, 28] 0 Conv2D-142 [[1, 128, 28, 28]] [1, 128, 28, 28] 147,456 BatchNorm2D-124 [[1, 128, 28, 28]] [1, 128, 28, 28] 512 Conv2D-143 [[1, 128, 28, 28]] [1, 512, 28, 28] 65,536 BatchNorm2D-125 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048 BottleneckBlock-39 [[1, 512, 28, 28]] [1, 512, 28, 28] 0 Conv2D-144 [[1, 512, 28, 28]] [1, 128, 28, 28] 65,536 BatchNorm2D-126 [[1, 128, 28, 28]] [1, 128, 28, 28] 512 ReLU-50 [[1, 512, 28, 28]] [1, 512, 28, 28] 0 Conv2D-145 [[1, 128, 28, 28]] [1, 128, 28, 28] 147,456 BatchNorm2D-127 [[1, 128, 28, 28]] [1, 128, 28, 28] 512 Conv2D-146 [[1, 128, 28, 28]] [1, 512, 28, 28] 65,536 BatchNorm2D-128 [[1, 512, 28, 28]] [1, 512, 28, 28] 2,048 BottleneckBlock-40 [[1, 512, 28, 28]] [1, 512, 28, 28] 0 Conv2D-148 [[1, 512, 28, 28]] [1, 256, 28, 28] 131,072 BatchNorm2D-130 [[1, 256, 28, 28]] [1, 256, 28, 28] 1,024 ReLU-51 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-149 [[1, 256, 28, 28]] [1, 256, 14, 14] 589,824 BatchNorm2D-131 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-150 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-132 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 Conv2D-147 [[1, 512, 28, 28]] [1, 1024, 14, 14] 524,288 BatchNorm2D-129 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-41 [[1, 512, 28, 28]] [1, 1024, 14, 14] 0 Conv2D-151 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-133 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-52 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-152 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-134 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-153 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-135 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-42 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-154 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-136 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-53 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-155 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-137 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-156 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-138 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-43 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-157 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-139 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-54 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-158 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-140 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-159 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-141 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-44 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-160 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-142 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-55 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-161 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-143 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-162 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-144 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-45 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-163 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-145 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-56 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-164 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-146 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-165 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-147 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-46 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-166 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-148 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-57 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-167 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-149 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-168 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-150 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-47 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-169 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-151 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-58 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-170 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-152 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-171 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-153 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-48 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-172 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-154 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-59 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-173 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-155 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-174 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-156 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-49 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-175 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-157 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-60 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-176 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-158 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-177 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-159 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-50 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-178 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-160 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-61 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-179 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-161 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-180 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-162 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-51 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-181 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-163 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-62 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-182 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-164 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-183 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-165 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-52 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-184 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-166 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-63 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-185 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-167 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-186 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-168 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-53 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-187 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-169 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-64 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-188 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-170 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-189 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-171 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-54 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-190 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-172 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-65 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-191 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-173 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-192 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-174 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-55 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-193 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-175 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-66 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-194 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-176 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-195 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-177 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-56 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-196 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-178 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-67 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-197 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-179 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-198 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-180 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-57 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-199 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-181 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-68 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-200 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-182 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-201 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-183 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-58 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-202 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-184 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-69 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-203 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-185 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-204 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-186 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-59 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-205 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-187 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-70 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-206 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-188 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-207 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-189 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-60 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-208 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-190 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-71 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-209 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-191 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-210 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-192 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-61 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-211 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-193 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-72 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-212 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-194 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-213 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-195 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-62 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-214 [[1, 1024, 14, 14]] [1, 256, 14, 14] 262,144 BatchNorm2D-196 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 ReLU-73 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-215 [[1, 256, 14, 14]] [1, 256, 14, 14] 589,824 BatchNorm2D-197 [[1, 256, 14, 14]] [1, 256, 14, 14] 1,024 Conv2D-216 [[1, 256, 14, 14]] [1, 1024, 14, 14] 262,144 BatchNorm2D-198 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 4,096 BottleneckBlock-63 [[1, 1024, 14, 14]] [1, 1024, 14, 14] 0 Conv2D-218 [[1, 1024, 14, 14]] [1, 512, 14, 14] 524,288 BatchNorm2D-200 [[1, 512, 14, 14]] [1, 512, 14, 14] 2,048 ReLU-74 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0 Conv2D-219 [[1, 512, 14, 14]] [1, 512, 7, 7] 2,359,296 BatchNorm2D-201 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048 Conv2D-220 [[1, 512, 7, 7]] [1, 2048, 7, 7] 1,048,576 BatchNorm2D-202 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 8,192 Conv2D-217 [[1, 1024, 14, 14]] [1, 2048, 7, 7] 2,097,152 BatchNorm2D-199 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 8,192 BottleneckBlock-64 [[1, 1024, 14, 14]] [1, 2048, 7, 7] 0 Conv2D-221 [[1, 2048, 7, 7]] [1, 512, 7, 7] 1,048,576 BatchNorm2D-203 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048 ReLU-75 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0 Conv2D-222 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,359,296 BatchNorm2D-204 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048 Conv2D-223 [[1, 512, 7, 7]] [1, 2048, 7, 7] 1,048,576 BatchNorm2D-205 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 8,192 BottleneckBlock-65 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0 Conv2D-224 [[1, 2048, 7, 7]] [1, 512, 7, 7] 1,048,576 BatchNorm2D-206 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048 ReLU-76 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0 Conv2D-225 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,359,296 BatchNorm2D-207 [[1, 512, 7, 7]] [1, 512, 7, 7] 2,048 Conv2D-226 [[1, 512, 7, 7]] [1, 2048, 7, 7] 1,048,576 BatchNorm2D-208 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 8,192 BottleneckBlock-66 [[1, 2048, 7, 7]] [1, 2048, 7, 7] 0 AdaptiveAvgPool2D-3 [[1, 2048, 7, 7]] [1, 2048, 1, 1] 0 Linear-33 [[1, 2048]] [1, 10] 20,490 =============================================================================== Total params: 42,625,994 Trainable params: 42,415,306 Non-trainable params: 210,688 ------------------------------------------------------------------------------- Input size (MB): 0.57 Forward/backward pass size (MB): 391.63 Params size (MB): 162.61 Estimated Total Size (MB): 554.81 ------------------------------------------------------------------------------- {'total_params': 42625994, 'trainable_params': 42415306}
梯度下降
为了判断学习的好坏，已经效率等，引入了梯度 的概念
# 随机梯度下降算法的优化器 sgd_optimizer=paddle.optimizer.SGD(learning_rate=0.001, parameters=model.parameters()) # loss计算 mse_loss=paddle.nn.MSELoss()
训练模块
model.prepare(paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters()), paddle.nn.CrossEntropyLoss(), # 交叉熵损失函数。线性模型+该损失函数，即softmax分类器。 paddle.metric.Accuracy(topk=(1,2))) model.fit(train_dataset, # 训练数据集 val_dataset, # 测试数据集 epochs=2, # 训练的总轮次 batch_size=64, # 训练使用的批大小 verbose=1) # 日志展示形式 model.evaluate(test_dataset,batch_size=64,verbose=1) # 评估
传说中的飞桨社区最差代码人，让我们一起努力！
记住：三岁出品必是精品 （不要脸系列）
