目录
任务简介:
学习网络模型中采用的神经网络层,包括卷积层,池化层,全连接层和激活函数层,学会如何区分二维卷积和三维卷积;
详细说明:
本节学习卷积神经网络中最重要的卷积层,了解卷积操作的过程与步骤,同时学会区分一维/二维/三维卷积,最后学习转置卷积(Transpose Convolution)的由来以及实现方法;
一、1d/2d/3d卷积
卷积维度:一般情况下,卷积核在几个维度上滑动,就是几维卷积。
- 一维卷积:
- 二维卷积:
- 三维卷积:
二、卷积–nn.Conv2d()
1. nn.Conv2d()
padding:保持输入输出的图像尺寸不变
dilation:常用于图像分割
groups:常用于模型轻量化
2. AlexNet:分组卷积
3.尺寸计算
代码:
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
import torch.nn as nn
from PIL import Image
from torchvision import transforms
from matplotlib import pyplot as plt
path_tools = os.path.abspath(os.path.join(BASE_DIR, "..", "..", "tools", "common_tools.py"))
assert os.path.exists(path_tools), "{}不存在,请将common_tools.py文件放到 {}".format(path_tools, os.path.dirname(path_tools))
import sys
hello_pytorch_DIR = os.path.abspath(os.path.dirname(__file__)+os.path.sep+".."+os.path.sep+"..")
sys.path.append(hello_pytorch_DIR)
from tools.common_tools import transform_invert, set_seed
set_seed(2) # 设置随机种子
# ================================= load img ==================================
path_img = os.path.join(os.path.dirname(os.path.abspath(__file__)), "lena.png")
img = Image.open(path_img).convert('RGB') # 0~255
# convert to tensor
img_transform = transforms.Compose([transforms.ToTensor()])
img_tensor = img_transform(img)
img_tensor.unsqueeze_(dim=0) # C*H*W to B*C*H*W
# ================================= create convolution layer ==================================
# ================ 2d
flag = 1
# flag = 0
if flag:
conv_layer = nn.Conv2d(3, 1, 3) # input:(i, o, size) weights:(o, i , h, w)
nn.init.xavier_normal_(conv_layer.weight.data)
# calculation
img_conv = conv_layer(img_tensor)
# ================ transposed
# flag = 1
flag = 0
if flag:
conv_layer = nn.ConvTranspose2d(3, 1, 3, stride=2) # input:(i, o, size)
nn.init.xavier_normal_(conv_layer.weight.data)
# calculation
img_conv = conv_layer(img_tensor)
# ================================= visualization ==================================
print("卷积前尺寸:{}\n卷积后尺寸:{}".format(img_tensor.shape, img_conv.shape))
img_conv = transform_invert(img_conv[0, 0:1, ...], img_transform)
img_raw = transform_invert(img_tensor.squeeze(), img_transform)
plt.subplot(122).imshow(img_conv, cmap='gray')
plt.subplot(121).imshow(img_raw)
plt.show()
输出:
卷积前尺寸:torch.Size([1, 3, 512, 512])
卷积后尺寸:torch.Size([1, 1, 510, 510])
随机种子为1时:
随机种子为2时:
随机种子为3时:
4.三维卷积核实现二维卷积
三、转置卷积–nn.ConvTranspose
卷积核:K4*16。16:卷积核3*3周围补0即为16;4:输出图像大小。
1.为何称为转置卷积
卷积核:K16*4。4:卷积核3*3,但最多只有4个权值与图像相乘,故采用剔除的方法从9个权值中挑选对应的4个,16:输出图像的大小。
仅仅是形状转置,但权值不同,即正常卷积和转置卷积是不可逆的。
2.nn.ConvTranspose2d()
3.尺寸计算
代码:
# ================ transposed
flag = 1
# flag = 0
if flag:
conv_layer = nn.ConvTranspose2d(3, 1, 3, stride=2) # input:(i, o, size)
nn.init.xavier_normal_(conv_layer.weight.data)
# calculation
img_conv = conv_layer(img_tensor)
输出:
卷积前尺寸:torch.Size([1, 3, 512, 512])
卷积后尺寸:torch.Size([1, 1, 1025, 1025])