B站資源
csdn本家

文章目錄

• model
• train
• predict

model

1.BasicConv2d類
2.Inception
3.InceptionAux(nn.Module):#輔助分類器
4.GoogLeNet

其中上表格查的第一個參數(shù)，輸入：

import torch.nn as nn import torch import torch.nn.functional as Fclass GoogLeNet(nn.Module):def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):#aux_logits=是否使用輔助分類器super(GoogLeNet, self).__init__()self.aux_logits = aux_logitsself.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)#如果是小數(shù)，ceil_mode向上取整，false向下self.conv2 = BasicConv2d(64, 64, kernel_size=1)#第二份64是查的self.conv3 = BasicConv2d(64, 192, kernel_size=3, padding=1)#第二份192是查的self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)#64, 96, 128, 16, 32, 32后6個self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)self.maxpool3 = nn.MaxPool2d(3, stride=2, ceil_mode=True)self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)self.maxpool4 = nn.MaxPool2d(3, stride=2, ceil_mode=True)self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)if self.aux_logits:#兩個輔助分類器self.aux1 = InceptionAux(512, num_classes)#深度，類別個數(shù)self.aux2 = InceptionAux(528, num_classes)self.avgpool = nn.AdaptiveAvgPool2d((1, 1))#自適應(yīng)到1，1的高和寬，不用在意輸入圖像大小了self.dropout = nn.Dropout(0.4)self.fc = nn.Linear(1024, num_classes)if init_weights:#如果有初始化的權(quán)重self._initialize_weights()def forward(self, x):# N x 3 x 224 x 224x = self.conv1(x)# N x 64 x 112 x 112x = self.maxpool1(x)# N x 64 x 56 x 56x = self.conv2(x)# N x 64 x 56 x 56x = self.conv3(x)# N x 192 x 56 x 56x = self.maxpool2(x)# N x 192 x 28 x 28x = self.inception3a(x)# N x 256 x 28 x 28x = self.inception3b(x)# N x 480 x 28 x 28x = self.maxpool3(x)# N x 480 x 14 x 14x = self.inception4a(x)# N x 512 x 14 x 14if self.training and self.aux_logits: # eval model lose this layer，訓(xùn)練模式時才用輔助分類器aux1 = self.aux1(x)x = self.inception4b(x)# N x 512 x 14 x 14x = self.inception4c(x)# N x 512 x 14 x 14x = self.inception4d(x)# N x 528 x 14 x 14if self.training and self.aux_logits: # eval model lose this layer，訓(xùn)練模式時才用輔助分類器aux2 = self.aux2(x)x = self.inception4e(x)# N x 832 x 14 x 14x = self.maxpool4(x)# N x 832 x 7 x 7x = self.inception5a(x)# N x 832 x 7 x 7x = self.inception5b(x)# N x 1024 x 7 x 7x = self.avgpool(x)# N x 1024 x 1 x 1x = torch.flatten(x, 1)# N x 1024x = self.dropout(x)x = self.fc(x)# N x 1000 (num_classes)if self.training and self.aux_logits: # eval model lose this layerreturn x, aux2, aux1return xdef _initialize_weights(self):for m in self.modules():if isinstance(m, nn.Conv2d):nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')if m.bias is not None:nn.init.constant_(m.bias, 0)elif isinstance(m, nn.Linear):nn.init.normal_(m.weight, 0, 0.01)nn.init.constant_(m.bias, 0)class Inception(nn.Module):# Iception結(jié)構(gòu)的模型，四個并行，單獨訓(xùn)練，輸出直接合并def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):#第一個是輸入矩陣，后6個是對應(yīng)六個模塊要的，ch1*1就是#1*1，red是reducesuper(Inception, self).__init__()self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)#卷積核大小是1，步距也是1省略self.branch2 = nn.Sequential(#Sequential方便合并，不用管了BasicConv2d(in_channels, ch3x3red, kernel_size=1),BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1) #padding=1 保證輸出大小等于輸入大小)self.branch3 = nn.Sequential(BasicConv2d(in_channels, ch5x5red, kernel_size=1),BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2) # 保證輸出大小等于輸入大小)

self.branch4 = nn.Sequential(nn.MaxPool2d(kernel_size=3, stride=1, padding=1),BasicConv2d(in_channels, pool_proj, kernel_size=1)#pool_proj是卷積核個數(shù))def forward(self, x):branch1 = self.branch1(x)branch2 = self.branch2(x)branch3 = self.branch3(x)branch4 = self.branch4(x)outputs = [branch1, branch2, branch3, branch4]return torch.cat(outputs, 1)#放在一個列表里，torch.cat合并，第二個參數(shù)1是在第一個維度進(jìn)行合并（channels）（第0個是batch）

class InceptionAux(nn.Module):#輔助分類器def __init__(self, in_channels, num_classes):super(InceptionAux, self).__init__()self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)self.conv = BasicConv2d(in_channels, 128, kernel_size=1) # output[batch, 128, 4, 4]self.fc1 = nn.Linear(2048, 1024)self.fc2 = nn.Linear(1024, num_classes)#分類類別個數(shù)def forward(self, x):# aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14 #輸出x = self.averagePool(x)# aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4x = self.conv(x)# N x 128 x 4 x 4x = torch.flatten(x, 1)#從channel進(jìn)行展平x = F.dropout(x, 0.5, training=self.training)# N x 2048x = F.relu(self.fc1(x), inplace=True)x = F.dropout(x, 0.5, training=self.training)# N x 1024x = self.fc2(x)# N x num_classesreturn xclass BasicConv2d(nn.Module):##卷積與relu共同使用，不然很麻煩def __init__(self, in_channels, out_channels, **kwargs):super(BasicConv2d, self).__init__()self.conv = nn.Conv2d(in_channels, out_channels, **kwargs)self.relu = nn.ReLU(inplace=True)def forward(self, x):x = self.conv(x)x = self.relu(x)return x

train

print(1) import torch print(2) import torch.nn as nn print(3) from torchvision import transforms, datasets import torchvision import json import matplotlib.pyplot as plt import os import torch.optim as optim from model import GoogLeNetprint(4)device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") print(5) #device = torch.device("cpu")if torch.cuda.is_available():print('yes') print(device)data_transform = {"train": transforms.Compose([transforms.RandomResizedCrop(224),transforms.RandomHorizontalFlip(),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),"val": transforms.Compose([transforms.Resize((224, 224)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path image_path = data_root + "/data_set/flower_data/" # flower data set pathtrain_dataset = datasets.ImageFolder(root=image_path + "train",transform=data_transform["train"]) train_num = len(train_dataset)# {'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)batch_size = 32 train_loader = torch.utils.data.DataLoader(train_dataset,batch_size=batch_size, shuffle=True,num_workers=0)validate_dataset = datasets.ImageFolder(root=image_path + "val",transform=data_transform["val"]) val_num = len(validate_dataset) validate_loader = torch.utils.data.DataLoader(validate_dataset,batch_size=batch_size, shuffle=False,num_workers=0) #################################################### test_data_iter = iter(validate_loader) # test_image, test_label = test_data_iter.next()# net = torchvision.models.googlenet(num_classes=5) # model_dict = net.state_dict() # pretrain_model = torch.load("googlenet.pth") # del_list = ["aux1.fc2.weight", "aux1.fc2.bias", # "aux2.fc2.weight", "aux2.fc2.bias", # "fc.weight", "fc.bias"] # pretrain_dict = {k: v for k, v in pretrain_model.items() if k not in del_list} # model_dict.update(pretrain_dict) # net.load_state_dict(model_dict)######################################################net = GoogLeNet(num_classes=5, aux_logits=True, init_weights=True) net.to(device) loss_function = nn.CrossEntropyLoss() optimizer = optim.Adam(net.parameters(), lr=0.0003)best_acc = 0.0 save_path = './googleNet.pth' # import os ##導(dǎo)入預(yù)訓(xùn)練參數(shù)if os.path.exists(save_path):net.load_state_dict(torch.load(save_path))#高晗的預(yù)訓(xùn)練加載代碼 # model = MyModel().to(lib.device) # optimizer = Adam(model.parameters(), 0.001) # if os.path.exists(r"F:\code\NLP學(xué)習(xí) 2020\文本情感分類\model\model_ch2.pkl"): # model.load_state_dict(torch.load( # r"F:\code\NLP學(xué)習(xí) 2020\文本情感分類\model\model_ch2.pkl")) # optimizer.load_state_dict(torch.load( # r"F:\code\NLP學(xué)習(xí) 2020\文本情感分類\model\optimizer_ch2.pkl"))for epoch in range(30):# train## 這里可以加一條輸出上次訓(xùn)練的殘差與準(zhǔn)確度net.train()running_loss = 0.0for step, data in enumerate(train_loader, start=0):images, labels = dataoptimizer.zero_grad()#三個輸出logits, aux_logits2, aux_logits1 = net(images.to(device))loss0 = loss_function(logits, labels.to(device))loss1 = loss_function(aux_logits1, labels.to(device))loss2 = loss_function(aux_logits2, labels.to(device))loss = loss0 + loss1 * 0.3 + loss2 * 0.3#加權(quán)加入，0.3時論文給的loss.backward()#反向傳播optimizer.step()#優(yōu)化器更新參數(shù)# print statisticsrunning_loss += loss.item()# print train processrate = (step + 1) / len(train_loader)a = "*" * int(rate * 50)b = "." * int((1 - rate) * 50)print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss), end="")print()# validatenet.eval()acc = 0.0 # accumulate accurate number / epochwith torch.no_grad():for val_data in validate_loader:val_images, val_labels = val_dataoutputs = net(val_images.to(device)) # eval model only have last output layerpredict_y = torch.max(outputs, dim=1)[1]acc += (predict_y == val_labels.to(device)).sum().item()val_accurate = acc / val_numif val_accurate > best_acc:best_acc = val_accuratetorch.save(net.state_dict(), save_path)print('[epoch %d] train_loss: %.3f test_accuracy: %.3f' %(epoch + 1, running_loss / step, val_accurate))print('Finished Training')

predict

import torch from model import GoogLeNet from PIL import Image from torchvision import transforms import matplotlib.pyplot as plt import jsondata_transform = transforms.Compose([transforms.Resize((224, 224)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])# load image img = Image.open("../tulip.jpg") plt.imshow(img) # [N, C, H, W] img = data_transform(img) # expand batch dimension img = torch.unsqueeze(img, dim=0)# read class_indict try:json_file = open('./class_indices.json', 'r')class_indict = json.load(json_file) except Exception as e:print(e)exit(-1)# create model model = GoogLeNet(num_classes=5, aux_logits=False) # load model weights model_weight_path = "./googleNet.pth" missing_keys, unexpected_keys = model.load_state_dict(torch.load(model_weight_path), strict=False)#strict=False就不精確匹配參數(shù)（因為有兩個輔助分類器沒有） model.eval() with torch.no_grad():# predict classoutput = torch.squeeze(model(img))predict = torch.softmax(output, dim=0)predict_cla = torch.argmax(predict).numpy() print(class_indict[str(predict_cla)]) plt.show()

總結(jié)

以上是生活随笔為你收集整理的5.2 使用pytorch搭建GoogLeNet网络 笔记的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。