1. 程式人生 > >pytorch + visdom CNN處理自建圖片資料集

pytorch + visdom CNN處理自建圖片資料集

環境

系統:win10
cpu:i7-6700HQ
gpu:gtx965m
python : 3.6
pytorch :0.3

資料下載

來源自Sasank Chilamkurthy 的教程; 資料:下載連結。
下載後解壓放到專案根目錄:
這裡寫圖片描述
資料集為用來分類 螞蟻和蜜蜂。有大約120個訓練影象,每個類有75個驗證影象。

資料匯入

可以使用 torchvision.datasets.ImageFolder(root,transforms) 模組 可以將 圖片轉換為 tensor。
先定義transform:

data_transforms = {
    'train'
: transforms.Compose([ # 隨機切成224x224 大小圖片 統一圖片格式 transforms.RandomResizedCrop(224), # 影象翻轉 transforms.RandomHorizontalFlip(), # totensor 歸一化(0,255) >> (0,1) normalize channel=(channel-mean)/std transforms.ToTensor(), transforms.Normalize(mean=[0.485
, 0.456, 0.406], std=[0.229, 0.224, 0.225]) ]), "val" : transforms.Compose([ # 圖片大小縮放 統一圖片格式 transforms.Resize(256), # 以中心裁剪 transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) ]) }

匯入,載入資料:

data_dir = './hymenoptera_data'
# trans data
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']}
# load data
data_loaders = {x: DataLoader(image_datasets[x], batch_size=BATCH_SIZE, shuffle=True) for x in ['train', 'val']}

data_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes
print(data_sizes, class_names)
{'train': 244, 'val': 153} ['ants', 'bees']

訓練集 244圖片 , 測試集153圖片 。

視覺化部分圖片看看,由於visdom支援tensor輸入 ,不用換成numpy,直接用tensor計算即可 :

inputs, classes = next(iter(data_loaders['val']))

out = torchvision.utils.make_grid(inputs)
inp = torch.transpose(out, 0, 2)
mean = torch.FloatTensor([0.485, 0.456, 0.406])
std = torch.FloatTensor([0.229, 0.224, 0.225])
inp = std * inp + mean
inp = torch.transpose(inp, 0, 2)
viz.images(inp)

這裡寫圖片描述

建立CNN

net 根據上一篇的處理cifar10的改了一下規格:

class CNN(nn.Module):
    def __init__(self, in_dim, n_class):
        super(CNN, self).__init__()
        self.cnn = nn.Sequential(
            nn.BatchNorm2d(in_dim),
            nn.ReLU(True),
            nn.Conv2d(in_dim, 16, 7), # 224 >> 218
            nn.BatchNorm2d(16),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2),  # 218 >> 109
            nn.ReLU(True),
            nn.Conv2d(16, 32, 5),  # 105
            nn.BatchNorm2d(32),
            nn.ReLU(True),
            nn.Conv2d(32, 64, 5),  # 101
            nn.BatchNorm2d(64),
            nn.ReLU(True),
            nn.Conv2d(64, 64, 3, 1, 1),
            nn.BatchNorm2d(64),
            nn.ReLU(True),
            nn.MaxPool2d(2, 2),  # 101 >> 50
            nn.Conv2d(64, 128, 3, 1, 1),  #
            nn.BatchNorm2d(128),
            nn.ReLU(True),
            nn.MaxPool2d(3),  # 50 >> 16
        )
        self.fc = nn.Sequential(
            nn.Linear(128*16*16, 120),
            nn.BatchNorm1d(120),
            nn.ReLU(True),
            nn.Linear(120, n_class))
    def forward(self, x):
        out = self.cnn(x)
        out = self.fc(out.view(-1, 128*16*16))
        return out

# 輸入3層rgb ,輸出 分類 2       
model = CNN(3, 2)

loss,優化函式:

line = viz.line(Y=np.arange(10))
loss_f = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=LR, momentum=0.9)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)

引數:

BATCH_SIZE = 4
LR = 0.001
EPOCHS = 10

執行 10個 epoch 看看:

[9/10] train_loss:0.650|train_acc:0.639|test_loss:0.621|test_acc0.706
[10/10] train_loss:0.645|train_acc:0.627|test_loss:0.654|test_acc0.686
Training complete in 1m 16s
Best val Acc: 0.712418

這裡寫圖片描述

執行 20個看看:

[19/20] train_loss:0.592|train_acc:0.701|test_loss:0.563|test_acc0.712
[20/20] train_loss:0.564|train_acc:0.721|test_loss:0.571|test_acc0.706
Training complete in 2m 30s
Best val Acc: 0.745098

這裡寫圖片描述

準確率比較低:只有74.5%

我們使用models 裡的 resnet18 執行 10個epoch:

model = torchvision.models.resnet18(True)
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, 2)
[9/10] train_loss:0.621|train_acc:0.652|test_loss:0.588|test_acc0.667
[10/10] train_loss:0.610|train_acc:0.680|test_loss:0.561|test_acc0.667
Training complete in 1m 24s
Best val Acc: 0.686275

效果也很一般,想要短時間內就訓練出效果很好的models,我們可以下載訓練好的state,在此基礎上訓練:

model = torchvision.models.resnet18(pretrained=True)
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, 2)
[9/10] train_loss:0.308|train_acc:0.877|test_loss:0.160|test_acc0.941
[10/10] train_loss:0.267|train_acc:0.885|test_loss:0.148|test_acc0.954
Training complete in 1m 25s
Best val Acc: 0.954248

10個epoch直接的到95%的準確率。

這裡寫圖片描述

程式碼在這。