论文阅读
感谢p导
论文链接：MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
主要亮点有两个：1、Depthwise separable convlution(a depthwise convolution and a 1*1 convolution) replace standard convolution
2、添加了两个超参数：α、β
提出来一个有效的模型——mobilenet，用在移动设备和嵌入式设备上，使用深度可分离卷积，引进了两个超参数来权衡延迟和准确率
使用两个超参数来定义更小更有效的MobileNets
mobilenet 是基于深度可分离卷积实现的，深度可分离卷积是将普通卷积分为了两部分，一个逐通道卷积和一个1*1卷积
普通卷积的计算量：DK是卷积核大小，DF是输入的特征图的大小(本文中特征图长宽一致),M是输入特征图的通道数，N是输出特征图的通道数
变换成深度可分离卷积之后的计算量以及两者之比
两个超参数
第一个是改变channels
第二个是改变每个feature map的size
代码实现
因为霹雳吧啦这次没有实现v1的代码，自己按照论文中的模型表随便瞎写的
使用torchsummary输出模型
就按照论文中给出的网络结构图来实现即可
model
from torch import nn
class BasicConv2d_dw(nn.Module):
def __init__(self,
in_channels: int,
out_channels: int,
stride: int):
super(BasicConv2d_dw, self).__init__()
self.conv_dw = nn.Sequential(
nn.Conv2d(in_channels=in_channels, out_channels=in_channels,
groups=in_channels, kernel_size=3, stride=stride, padding=1,bias=False),
nn.BatchNorm2d(in_channels),
nn.ReLU6(inplace=True),
nn.Conv2d(in_channels=in_channels, out_channels=out_channels,
kernel_size=1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(out_channels),
nn.ReLU6(inplace=True),
)
def forward(self, x):
return self.conv_dw(x)
class MobileNet_v1(nn.Module):
def __init__(self, num_classes=1000):
super().__init__()
self.model = nn.Sequential(
nn.Conv2d(in_channels=3, out_channels=32, kernel_size=3,
stride=2, padding=1, bias=False),
nn.BatchNorm2d(32),
nn.ReLU6(inplace=True),
BasicConv2d_dw(32, 64, 1),
BasicConv2d_dw(64, 128, 2),
BasicConv2d_dw(128, 128, 1),
BasicConv2d_dw(128, 256, 2),
BasicConv2d_dw(256, 256, 1),
BasicConv2d_dw(256, 512, 2),
BasicConv2d_dw(512, 512, 1),
BasicConv2d_dw(512, 512, 1),
BasicConv2d_dw(512, 512, 1),
BasicConv2d_dw(512, 512, 1),
BasicConv2d_dw(512, 512, 1),
BasicConv2d_dw(512, 1024, 2),
BasicConv2d_dw(1024, 1024, 1),
nn.AvgPool2d(7),
)
self.fc = nn.Linear(1024, num_classes)
# weight initialization
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out')
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, nn.BatchNorm2d):
nn.init.ones_(m.weight)
nn.init.zeros_(m.bias)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.zeros_(m.bias)
def forward(self, x):
x = self.model(x)
x = x.view(-1, 1024)
x = self.fc(x)
return x
train
import os
import sys
import json
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import transforms, datasets
from tqdm import tqdm
from model_v1 import MobileNet_v1
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("using {} device.".format(device))
batch_size = 16
epochs = 20
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
"val": transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])}
data_root = os.path.abspath(os.path.join(os.getcwd(), "../")) # get data root path
image_path = os.path.join(data_root, "flower_data") # flower data set path
assert os.path.exists(image_path), "{} path does not exist.".format(image_path)
train_dataset = datasets.ImageFolder(root=os.path.join(image_path, "train"),
transform=data_transform["train"])
validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
transform=data_transform["val"])
val_num = len(validate_dataset)
train_num = len(train_dataset)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size, shuffle=True)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=batch_size, shuffle=False)
print("using {} images for training, {} images for validation.".format(train_num,
val_num))
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
# create model
net = MobileNet_v1(num_classes=5).to(device)
# load pretrain weights,这里我没有去pytorch上下载预训练好的模型，只是有这部分代码，在一开始训练时候把这部分注释了，之后运行就可以取消注释
model_weight_path = "./MobileNetV1.pth"
assert os.path.exists(model_weight_path), "file {} dose not exist.".format(model_weight_path)
pre_weights = torch.load(model_weight_path, map_location=device)
# delete classifier weights
pre_dict = {k: v for k, v in pre_weights.items() if net.state_dict()[k].numel() == v.numel()}
missing_keys, unexpected_keys = net.load_state_dict(pre_dict, strict=False)
# define loss function
loss_function = nn.CrossEntropyLoss()
# construct an optimizer
optimizer = optim.Adam(net.parameters(), lr=0.0001)
best_acc = 0.0
save_path = './MobileNetV1.pth'
train_steps = len(train_loader)
for epoch in range(epochs):
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader)
for data in train_bar:
images, labels = data
optimizer.zero_grad()
logits = net(images.to(device))
loss = loss_function(logits, labels.to(device))
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,
epochs,
loss)
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
val_bar = tqdm(validate_loader, file=sys.stdout)
for val_data in val_bar:
val_images, val_labels = val_data
outputs = net(val_images.to(device))
# loss = loss_function(outputs, test_labels)
predict_y = torch.max(outputs, dim=1)[1]
acc += torch.eq(predict_y, val_labels.to(device)).sum().item()
val_bar.desc = "valid epoch[{}/{}]".format(epoch + 1,
epochs)
val_accurate = acc / val_num
print('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %
(epoch + 1, running_loss / train_steps, val_accurate))
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(), save_path)
print('Finished Training')
if __name__ == '__main__':
main()
predict
import os
import json
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from model_v1 import MobileNet_v1
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
data_transform = transforms.Compose(
[transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
# load image
img_path = "../tulip.jpg"
assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
img = Image.open(img_path)
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# read class_indict
json_path = './class_indices.json'
assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)
json_file = open(json_path, "r")
class_indict = json.load(json_file)
# create model
model = MobileNet_v1(num_classes=5).to(device)
# load model weights
model_weight_path = "./MobileNetV1.pth"
model.load_state_dict(torch.load(model_weight_path, map_location=device))
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
print_res = "class: {} prob: {:.3}".format(class_indict[str(predict_cla)],
predict[predict_cla].numpy())
plt.title(print_res)
for i in range(len(predict)):
print("class: {:10} prob: {:.3}".format(class_indict[str(i)],
predict[i].numpy()))
plt.show()
if __name__ == '__main__':
main()
实验结果
训练了20轮，在p导的花分类上面准确率74.5%
版权声明：本文为CSDN博主「每个人都是孙笑川」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/qq_41488595/article/details/122752071
暂无评论