我一直在尝试使用预先训练的模型来预测从未见过的图像上的标签。我训练了一个CNN，使用Kaggle花识别数据集对5种类型的花进行分类。到目前为止，我已经将模型训练到了97％的准确性，并将模型保存到了目录中。现在，我想从这些类型中下载花朵的任何图像，并能够使用此预先训练的模型来预测标签。到目前为止，这是我的代码：（所有这方面的代码回顾将非常有帮助，因为这是我有史以来的第一个项目）
这是我训练的CNN模型：
from multiprocessing import freeze_support
import torch
from torch import nn
from torch.autograd import Variable
from torch.utils.data import DataLoader, Sampler
from torchvision import datasets
from torchvision.transforms import transforms
from torch.optim import Adam
import matplotlib.pyplot as plt
import numpy as np
# Hyperparameters.
num_epochs = 20
num_classes = 5
batch_size = 100
learning_rate = 0.001
num_of_workers = 5
DATA_PATH_TRAIN = 'C:\\Users\Aeryes\PycharmProjects\simplecnn\images\\train\\'
DATA_PATH_TEST = 'C:\\Users\Aeryes\PycharmProjects\simplecnn\images\\test\\'
MODEL_STORE_PATH = 'C:\\Users\Aeryes\PycharmProjects\simplecnn\model'
trans = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.Resize(32),
transforms.CenterCrop(32),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5),(0.5, 0.5, 0.5))
])
# Flowers dataset.
train_dataset = datasets.ImageFolder(root=DATA_PATH_TRAIN, transform=trans)
test_dataset = datasets.ImageFolder(root=DATA_PATH_TEST, transform=trans)
# Create custom random sampler class to iter over dataloader.
train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True, num_workers=num_of_workers)
test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False, num_workers=num_of_workers)
# CNN we are going to implement.
class Unit(nn.Module):
def __init__(self, in_channels, out_channels):
super(Unit, self).__init__()
self.conv = nn.Conv2d(in_channels=in_channels, kernel_size=3, out_channels=out_channels, stride=1, padding=1)
self.bn = nn.BatchNorm2d(num_features=out_channels)
self.relu = nn.ReLU()
def forward(self, input):
output = self.conv(input)
output = self.bn(output)
output = self.relu(output)
return output
class CNNet(nn.Module):
def __init__(self, num_class):
super(CNNet, self).__init__()
# Create 14 layers of the unit with max pooling in between
self.unit1 = Unit(in_channels=3, out_channels=32)
self.unit2 = Unit(in_channels=32, out_channels=32)
self.unit3 = Unit(in_channels=32, out_channels=32)
self.pool1 = nn.MaxPool2d(kernel_size=2)
self.unit4 = Unit(in_channels=32, out_channels=64)
self.unit5 = Unit(in_channels=64, out_channels=64)
self.unit6 = Unit(in_channels=64, out_channels=64)
self.unit7 = Unit(in_channels=64, out_channels=64)
self.pool2 = nn.MaxPool2d(kernel_size=2)
self.unit8 = Unit(in_channels=64, out_channels=128)
self.unit9 = Unit(in_channels=128, out_channels=128)
self.unit10 = Unit(in_channels=128, out_channels=128)
self.unit11 = Unit(in_channels=128, out_channels=128)
self.pool3 = nn.MaxPool2d(kernel_size=2)
self.unit12 = Unit(in_channels=128, out_channels=128)
self.unit13 = Unit(in_channels=128, out_channels=128)
self.unit14 = Unit(in_channels=128, out_channels=128)
self.avgpool = nn.AvgPool2d(kernel_size=4)
# Add all the units into the Sequential layer in exact order
self.net = nn.Sequential(self.unit1, self.unit2, self.unit3, self.pool1, self.unit4, self.unit5, self.unit6
, self.unit7, self.pool2, self.unit8, self.unit9, self.unit10, self.unit11, self.pool3,
self.unit12, self.unit13, self.unit14, self.avgpool)
self.fc = nn.Linear(in_features=128, out_features=num_class)
def forward(self, input):
output = self.net(input)
output = output.view(-1, 128)
output = self.fc(output)
return output
# Check if gpu support is available
cuda_avail = torch.cuda.is_available()
# Create model, optimizer and loss function
model = CNNet(num_classes)
# if cuda is available, move the model to the GPU
if cuda_avail:
model.cuda()
# Define the optimizer and loss function
optimizer = Adam(model.parameters(), lr=0.0001, weight_decay=0.0001)
loss_fn = nn.CrossEntropyLoss()
def save_models(epoch):
torch.save(model.state_dict(), f"flowermodel_{epoch}.model")
print("Checkpoint saved")
def test():
model.eval()
test_acc = 0.0
for i, (images, labels) in enumerate(test_loader):
if cuda_avail:
images = Variable(images.cuda())
labels = Variable(labels.cuda())
# Predict classes using images from the test set
outputs = model(images)
_, prediction = torch.max(outputs.data, 1)
test_acc += torch.sum(prediction == labels.data).float()
# Compute the average acc and loss over all 10000 test images
test_acc = test_acc / 4242 * 100
return test_acc
def train(num_epoch):
best_acc = 0.0
for epoch in range(num_epoch):
model.train()
train_acc = 0.0
train_loss = 0.0
for i, (images, labels) in enumerate(train_loader):
# Move images and labels to gpu if available
if cuda_avail:
images = Variable(images.cuda())
labels = Variable(labels.cuda())
# Clear all accumulated gradients
optimizer.zero_grad()
# Predict classes using images from the test set
outputs = model(images)
# Compute the loss based on the predictions and actual labels
loss = loss_fn(outputs, labels)
# Backpropagate the loss
loss.backward()
# Adjust parameters according to the computed gradients
optimizer.step()
train_loss += loss.cpu().data[0] * images.size(0)
_, prediction = torch.max(outputs.data, 1)
train_acc += torch.sum(prediction == labels.data).float()
# Call the learning rate adjustment function
#adjust_learning_rate(epoch)
# Compute the average acc and loss over all 50000 training images
train_acc = train_acc / 4242 * 100
train_loss = train_loss / 8484
# Evaluate on the test set
test_acc = test()
# Save the model if the test acc is greater than our current best
if test_acc > best_acc:
save_models(epoch)
best_acc = test_acc
# Print the metrics
print(f"Epoch {epoch + 1}, Train Accuracy: {train_acc} , TrainLoss: {train_loss} , Test Accuracy: {test_acc}")
if __name__ == '__main__':
freeze_support()
train(num_epochs)
这是我的图像加载器，用于查看预处理后的图像：
from multiprocessing import freeze_support
import torch
from torch import nn
import torchvision
from torch.autograd import Variable
from torch.utils.data import DataLoader, Sampler
from torchvision import datasets
from torchvision.transforms import transforms
from torch.optim import Adam
import matplotlib.pyplot as plt
import numpy as np
import PIL
num_classes = 5
batch_size = 100
num_of_workers = 5
DATA_PATH_TRAIN = 'C:\\Users\Aeryes\PycharmProjects\simplecnn\images\\train'
DATA_PATH_TEST = 'C:\\Users\Aeryes\PycharmProjects\simplecnn\images\\test'
trans = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.Resize(32),
transforms.CenterCrop(32),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5),(0.5, 0.5, 0.5))
])
train_dataset = datasets.ImageFolder(root=DATA_PATH_TRAIN, transform=trans)
train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True, num_workers=num_of_workers)
def imshow(img):
img = img / 2 + 0.5 # unnormalize
#npimg = img.numpy()
plt.imshow(np.transpose(img[0].numpy(), (1, 2, 0)))
plt.show()
def main():
# get some random training images
dataiter = iter(train_loader)
images, labels = dataiter.next()
# show images
imshow(images)
if __name__ == "__main__":
main()
到目前为止，这是我对新图像文件进行分类所要进行的工作，该文件将对新图像进行分类：
from multiprocessing import freeze_support
import torch
from torch import nn
from torch.autograd import Variable
from torch.utils.data import DataLoader, Sampler
from torchvision import datasets
from torchvision.transforms import transforms
from torch.optim import Adam
import matplotlib.pyplot as plt
import numpy as np
def classify_new_image():
# Classify a new image using a pretrained model from the above training.
# Location of the image we will classify.
IMG_PATH = "C:\\Users\\Aeryes\\PycharmProjects\\simplecnn\\images\\pretrain_classify\\"
# Pre-processing the new image using transform.
min_img_size = 32
trans = transforms.Compose([transforms.Resize(min_img_size),
transforms.CenterCrop(32),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])])
# Picture dataset.
classify_dataset = datasets.ImageFolder(root=IMG_PATH, transform=trans)
# Create custom random sampler class to iter over dataloader.
classify_loader = DataLoader(dataset=classify_dataset, batch_size=1, shuffle=True, num_workers=5)
# Check if gpu support is available
cuda_avail = torch.cuda.is_available()
model = torch.load('C:\\Users\\Aeryes\\PycharmProjects\\simplecnn\\src\\flowermodel_20.tar')['state_dict']
# if cuda is available, move the model to the GPU
if cuda_avail:
model.cuda()
if __name__ == "__main__":
classify_new_image()
我还面临的一个大问题是弄清输出。我从CNN模型打印了预测变量，它给了我一个从0-4的数字张量，我认为这是我数据文件夹中的5个类。如果有人可以帮助我理解这一点，我将非常感激。
这是我的直接问题：如何使用预先训练的模型预测从未见过的花朵图像？
答案 0 :(得分：1)
您可以对单个图像执行此操作，
import torch
from torchvision.transforms import transforms
from PIL import Image
from cnn_main import CNNet
from pathlib import Path
model = CNNet(5)
checkpoint = torch.load(Path('C:/Users/Aeryes/PycharmProjects/simplecnn/src/19.model'))
model.load_state_dict(checkpoint)
trans = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.Resize(32),
transforms.CenterCrop(32),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5),(0.5, 0.5, 0.5))
])
image = Image.open(Path('C:/Users/Aeryes/PycharmProjects/simplecnn/images/pretrain_classify/rose_classify.jpg'))
input = trans(image)
input = input.view(1, 3, 32,32)
output = model(input)
prediction = int(torch.max(output.data, 1)[1].numpy())
print(prediction)
if (prediction == 0):
print ('daisy')
if (prediction == 1):
print ('dandelion')
if (prediction == 2):
print ('rose')
if (prediction == 3):
print ('sunflower')
if (prediction == 4):
print ('tulip')