Github项目-CNNResnet9-残差神经网络水果多分类项目

ResNet-论文全文完整翻译+注解 - 知乎

你必须要知道CNN模型:ResNet - 知乎

python 复制代码
#!/usr/bin/env python
# coding: utf-8
#https://github.com/SehajS/cnn-resnet-fruit-classification
# # Classifying Fruits from their Images
# 
# This project aims at creating a deep learning model which predicts the names of the fruits by looking at their images. 
# 
# The dataset is taken from kaggle and can be accessed using this link: https://www.kaggle.com/moltean/fruits
# 
# A complete walkthrough from downloading the dataset to the creating the CNN-ResNet model with extensive comments has been provided. 

# ## Import all the requried libraries/modules

# In[1]:


#import opendatasets as od
import os
import shutil
import torch
from torchvision.datasets import ImageFolder
import torchvision.transforms as tt
from torch.utils.data import random_split
from torch.utils.data import DataLoader
from torchvision.utils import make_grid
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
get_ipython().run_line_magic('matplotlib', 'inline')


# ## Downloading the dataset

# In[2]:


#dataset_url = "https://www.kaggle.com/moltean/fruits"
#od.download(dataset_url)


# ## Cleaning the downloaded dataset

# In[3]:


data_direc = './datadev'
os.listdir(data_direc)


# There are some files that one won't be needing in the project. Hence, one should remove them.

# In[4]:


#shutil.rmtree('./fruits/fruits-360/test-multiple_fruits')


# In[5]:


#shutil.rmtree('./fruits/fruits-360/papers')


# In[6]:


train_data_direc = "./datadev/train"
test_data_direc = "./datadev/test"


# ## Import the Dataset using PyTorch

# In[7]:


print(f'The total number of labels is: {len(os.listdir(train_data_direc))}')


# In[8]:


dataset = ImageFolder(train_data_direc)
len(dataset)


# In total, there are 67692 non-test images in our dataset.

# Let us peek at one of the elements of the dataset. This gives further insights on the way data is stored.

# In[9]:


dataset[0]


# In[10]:


img, label = dataset[0]
plt.imshow(img)


# One would now like to convert the images to tensors.

# In[11]:


dataset = ImageFolder(train_data_direc, tt.ToTensor())


# In[12]:


image, label = dataset[0]
plt.imshow(image.permute(1,2,0))


# ## Training and Validation Sets

# In[13]:


val_pct = 0.1        # 10% of the images in Train folder will be used as validation set
val_size = int(len(dataset) * 0.1)
train_size = len(dataset) - val_size
val_size, train_size


# In[14]:


train_ds, val_ds = random_split(dataset, [train_size, val_size])


# In[15]:


len(train_ds), len(val_ds)


# It is time to use Data Loaders to load the dataset in batches.

# In[16]:


batch_size = 64
train_dl = DataLoader(train_ds, batch_size, shuffle=True, num_workers = 4, pin_memory=True)
val_dl = DataLoader(val_ds, batch_size*2, num_workers = 4, pin_memory=True)


# In[17]:


def show_batch(dl):
    for images, labels in dl:
        fig, ax = plt.subplots(figsize=(12, 6))
        ax.set_xticks([]); ax.set_yticks([])
        ax.imshow(make_grid(images, nrow=16).permute(1, 2, 0))
        break


# In[18]:


show_batch(train_dl)


# ## Utility Functions and Classes
# 
# The creation and training of the model is done using GPU. Below are the functions that make sure that tensors and the model is using a GPU as the default device.

# In[19]:


def get_default_device():
    """Pick GPU if available, else CPU"""
    if torch.cuda.is_available():
        return torch.device('cuda')
    else:
        return torch.device('cpu')
    
def to_device(data, device):
    """Move tensor(s) to chosen device"""
    if isinstance(data, (list,tuple)):
        return [to_device(x, device) for x in data]
    return data.to(device, non_blocking=True)

class DeviceDataLoader():
    """Wrap a dataloader to move data to a device"""
    def __init__(self, dl, device):
        self.dl = dl
        self.device = device
        
    def __iter__(self):
        """Yield a batch of data after moving it to device"""
        for b in self.dl: 
            yield to_device(b, self.device)

    def __len__(self):
        """Number of batches"""
        return len(self.dl)


# In[20]:


device = get_default_device()
device


# In[21]:


train_dl = DeviceDataLoader(train_dl, device)
val_dl = DeviceDataLoader(val_dl, device)


# ## Model and Training Utilities

# In[22]:


class ImageClassificationBase(nn.Module):
    def training_step(self, batch):
        images, labels = batch 
        out = self(images)                  # Generate predictions
        loss = F.cross_entropy(out, labels) # Calculate loss
        return loss
    
    def validation_step(self, batch):
        images, labels = batch 
        out = self(images)                    # Generate predictions
        loss = F.cross_entropy(out, labels)   # Calculate loss
        acc = accuracy(out, labels)           # Calculate accuracy
        return {'val_loss': loss.detach(), 'val_acc': acc}
        
    def validation_epoch_end(self, outputs):
        batch_losses = [x['val_loss'] for x in outputs]
        epoch_loss = torch.stack(batch_losses).mean()   # Combine losses
        batch_accs = [x['val_acc'] for x in outputs]
        epoch_acc = torch.stack(batch_accs).mean()      # Combine accuracies
        return {'val_loss': epoch_loss.item(), 'val_acc': epoch_acc.item()}
    
    def epoch_end(self, epoch, result):
        print("Epoch [{}], train_loss: {:.4f}, val_loss: {:.4f}, val_acc: {:.4f}".format(
            epoch, result['train_loss'], result['val_loss'], result['val_acc']))
        
def accuracy(outputs, labels):
    _, preds = torch.max(outputs, dim=1)
    return torch.tensor(torch.sum(preds == labels).item() / len(preds))


# In[23]:


@torch.no_grad()
def evaluate(model, val_loader):
    model.eval()
    outputs = [model.validation_step(batch) for batch in val_loader]
    return model.validation_epoch_end(outputs)

def fit(epochs, lr, model, train_loader, val_loader, opt_func=torch.optim.SGD):
    history = []
    optimizer = opt_func(model.parameters(), lr)
    for epoch in range(epochs):
        # Training Phase 
        model.train()
        train_losses = []
        for batch in train_loader:
            loss = model.training_step(batch)
            train_losses.append(loss)
            loss.backward()
            optimizer.step()
            optimizer.zero_grad()
        # Validation phase
        result = evaluate(model, val_loader)
        result['train_loss'] = torch.stack(train_losses).mean().item()
        model.epoch_end(epoch, result)
        history.append(result)
    return history


# In[24]:


def conv_block(in_channels, out_channels, pool=False):
    layers = [nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1), 
              nn.BatchNorm2d(out_channels), 
              nn.ReLU(inplace=True)]
    if pool: layers.append(nn.MaxPool2d(2))
    return nn.Sequential(*layers)


# In[25]:


class ResNet9(ImageClassificationBase):
    def __init__(self, in_channels, num_classes):
        super().__init__()
        
        self.conv1 = conv_block(in_channels, 64)
        self.conv2 = conv_block(64, 128, pool=True)
        self.res1 = nn.Sequential(conv_block(128, 128), conv_block(128, 128))
        
        self.conv3 = conv_block(128, 256, pool=True)
        self.conv4 = conv_block(256, 512, pool=True)
        self.res2 = nn.Sequential(conv_block(512, 512), conv_block(512, 512))
        
        self.classifier = nn.Sequential(nn.AdaptiveAvgPool2d(1), 
                                        nn.Flatten(), 
                                        nn.Dropout(0.2),
                                        nn.Linear(512, num_classes))
        
    def forward(self, xb):
        out = self.conv1(xb)
        out = self.conv2(out)
        out = self.res1(out) + out
        out = self.conv3(out)
        out = self.conv4(out)
        out = self.res2(out) + out
        out = self.classifier(out)
        return out


# In[26]:


model = to_device(ResNet9(3, len(dataset.classes)), device)
model


# 
# Pass one batch of input tensor through the model.
# 

# In[27]:


torch.cuda.empty_cache()

for batch in train_dl:
    images, labels = batch
    print('images.shape: ', images.shape)
    print('images.device: ', images.device)
    preds = model(images)
    print('preds.shape: ', preds.shape)
    break


# ## Training the Model

# In[28]:


history = [evaluate(model, val_dl)]
history


# Let us train for 5 epochs with the learning rate of 0.001. Note that we use Adam as the optimizer of choice.

# In[29]:


history += fit(5, 0.001, model, train_dl, val_dl, torch.optim.Adam)


# The accuracy achieved on teh valiation set is very high and close to 100%, therefore, one should not train the model for any more epochs. We end the training at 5 epochs.

# In[ ]:


def plot_accuracies(history):
    accuracies = [x['val_acc'] for x in history]
    plt.plot(accuracies, '-x')
    plt.xlabel('epoch')
    plt.ylabel('accuracy')
    plt.title('Accuracy vs. No. of epochs');


# In[ ]:


plot_accuracies(history)


# In[ ]:


def plot_losses(history):
    train_losses = [x.get('train_loss') for x in history]
    val_losses = [x['val_loss'] for x in history]
    plt.plot(train_losses, '-bx')
    plt.plot(val_losses, '-rx')
    plt.xlabel('epoch')
    plt.ylabel('loss')
    plt.legend(['Training', 'Validation'])
    plt.title('Loss vs. No. of epochs');


# In[ ]:


plot_losses(history)


# ## Testing with Individual Images
# 
# Now, one would like to test outthe model that we have built in previous section on the Test dataset and see how it performs.

# In[ ]:


def predict_image(img, model):
    # Convert to a batch of 1
    xb = to_device(img.unsqueeze(0), device)
    # Get predictions from model
    yb = model(xb)
    # Pick index with highest probability
    _, preds  = torch.max(yb, dim=1)
    # Retrieve the class label
    return dataset.classes[preds[0].item()]


# In[ ]:


test_dataset = ImageFolder(test_data_direc, tt.ToTensor())


# In[ ]:


len(test_dataset)


# In[ ]:


def get_prediction(torch_ds, model):
    img, label = torch_ds
    plt.imshow(img.permute(1, 2, 0))
    print('Label:', dataset.classes[label], ', Predicted:', predict_image(img, model))


# In[ ]:


get_prediction(test_dataset[0], model)


# In[ ]:


get_prediction(test_dataset[-1], model)


# In[ ]:


get_prediction(test_dataset[999], model)


# In[ ]:


test_loader = DeviceDataLoader(DataLoader(test_dataset, batch_size*2), device)
result = evaluate(model, test_loader)
result


# Therefore, the accuracy of the model on the test set is little above 98% which is great.
# 
# Naturally, a curious mind would like to know for which items did the model perform the worst.

# In[ ]:


wrong_preds = []
for test_ds in test_dataset:
    img, label = test_ds
    prediction = predict_image(img, model)
    if dataset.classes[label] != prediction:
        wrong_preds.append([dataset.classes[label], prediction])


# In[ ]:


print(f'Therefore, there are in total {len(wrong_preds)} out of {len(test_dataset)} items in the test set for which the model has made a wrong prediction')


# In[ ]:


#len(wrong_labels)


# Let us check what did our model predict for each of the wrongly predicted items. 

# In[ ]:


checked = []
for item in wrong_preds:
    if item not in checked:
        checked.append(item)
        print(f'{item[0]} has been wrongfully predicted as {item[1]}')


# ## Saving the Model

# In[ ]:


torch.save(model.state_dict(), '√SehajS-CNN-ResNet9-fruit-prediction.pth')
相关推荐
feifeikon19 分钟前
Python Day5 进阶语法(列表表达式/三元/断言/with-as/异常捕获/字符串方法/lambda函数
开发语言·python
龙的爹233330 分钟前
论文 | The Capacity for Moral Self-Correction in LargeLanguage Models
人工智能·深度学习·机器学习·语言模型·自然语言处理·prompt
杰仔正在努力1 小时前
python成长技能之枚举类
开发语言·python
Eiceblue1 小时前
通过Python 调整Excel行高、列宽
开发语言·vscode·python·pycharm·excel
Jam-Young1 小时前
Python中的面向对象编程,类,对象,封装,继承,多态
开发语言·python
Light601 小时前
低代码牵手 AI 接口:开启智能化开发新征程
人工智能·python·深度学习·低代码·链表·线性回归
墨绿色的摆渡人1 小时前
用 Python 从零开始创建神经网络(六):优化(Optimization)介绍
人工智能·python·深度学习·神经网络
小han的日常2 小时前
pycharm分支提交操作
python·pycharm
明月清风徐徐2 小时前
Scrapy爬取豆瓣电影Top250排行榜
python·selenium·scrapy
theLuckyLong2 小时前
SpringBoot后端解决跨域问题
spring boot·后端·python