Introduction

――I tried to do what the title says. I've done it all, so as a memo. ――There is a reason why you can't touch the contents deeply, and there are some parts that are a little messy. ――For example, where did you declare that variable? There may be a target --Since the original was cut and pasted with a notebook, there are magic commands --There are reference links here and there.

What i did

--Multi-class, multi-label classification of images. -An image like "This image is class A. This image corresponds to A and B." --I wanted to use pytorch, so I implemented it with pytorch. ――That's natural! Do you need such a comment? Because it is immature to see something like this.

Folder structure

I did the following. But this may not be the best honestly. This happened because the investigation started running moderately.

`Folder structure`


.
├── data
│   ├── labels        //Image and label combination json storage
│   │     ├── A.json
│   │     ├── B.json
│ │ └── and many other json
│   └── images        //jpg Image storage. Mixed for learning and verification
│         ├── A.jpg
│         ├── B.jpg
│ └── Many other jpgs
├── model             //Model save destination
└── predict           //Installed as an image storage area that you want to predict

By the way, the contents of json under labels are like this. The key is the image name and the value is the class information (1 or 0).

`sample`


# A.json
{
    "A": {
        "Label A": 1,
        "Label B": 1,
        "Label C": 0
    }
}

# B.json
{
    "B": {
        "Label A": 0,
        "Label B": 0,
        "Label C": 1
    }
}

code

Various preparations

# ref: https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html#sphx-glr-beginner-blitz-cifar10-tutorial-py

from PIL import Image
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import numpy as np
import pathlib
import random


#Use if you have a GPU
def check_cuda():
    return 'cuda:0' if torch.cuda.is_available() else 'cpu'
device = torch.device(check_cuda())

#Training data, test data division
image_set = {pathlib.Path(i).stem for i in pathlib.Path('data/images').glob('*.jpg')}
n_data = len(image_set)
traindata_rate = 0.7
train_idx = random.sample(range(n_data), int(n_data*traindata_rate))

_trainset = {}
_testset = {}
for i, _tuple in enumerate(image_set.items()):
    k, v = _tuple    
    if i in train_idx:
        _trainset[k] = v
    else :
        _testset[k] = v

Transform

# ref: https://qiita.com/takurooo/items/e4c91c5d78059f92e76d
trfm = transforms.Compose([
    transforms.Resize((100, 100)),    # image size --> (100, 100)
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
])

Dataset

class MultiLabelDataSet(torch.utils.data.Dataset):
    def __init__(self, labels, image_dir='./data/images',　ext='.jpg', transform=None):
        self.labels = labels
        self.image_dir = image_dir
        self.ext = ext
        self.transform = transform

        self.keys = list(labels.keys())
        self.vals = list(labels.values())

    def __len__(self):
        return len(self.labels)

    def __getitem__(self, idx):
        image_path = f'{self.image_dir}/{self.keys[idx]}{self.ext}'
        image_array = Image.open(image_path)
        if self.transform:
            image = self.transform(image_array)
        else:
            image = torch.Tensor(np.transpose(image_array, (2, 0, 1)))/255  # for 0~1 scaling
            
        label = torch.Tensor(list(self.vals[idx].values()))

        return {'image': image, 'label': label}

DataLoader

batch_size = 8

trainset = MultiLabelDataSet(_trainset, transform=trfm)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
                                          shuffle=False, num_workers=2)

testset = MultiLabelDataSet(_testset, transform=trfm)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
                                         shuffle=False, num_workers=2)

classes = ['A', 'B', 'C'...]Like

data check

import matplotlib.pyplot as plt
%matplotlib inline

# functions to show an image
def imshow(img):
    plt.imshow(np.transpose(img, (1, 2, 0)))
    plt.show()

# sample data
dataiter = iter(trainloader)
tmp = dataiter.next()
images = tmp['image']
labels = tmp['label']

# print images
imshow(torchvision.utils.make_grid(images))

model

The number of layers and channels is appropriate ... I use BCEWithLogitsLoss so I don't bite the sigmoid (I said so when I googled)

class MultiClassifier(nn.Module):
    def __init__(self):
        super(MultiClassifier, self).__init__()

        self.ConvLayer1 = nn.Sequential(
            # ref(H_out & W_out): https://pytorch.org/docs/stable/nn.html#conv2d
            nn.Conv2d(3, 32, 3),
            nn.MaxPool2d(2),
            nn.ReLU(),
            )

        self.ConvLayer2 = nn.Sequential(
            nn.Conv2d(32, 64, 3),
            nn.MaxPool2d(2),
            nn.ReLU(),
            )

        self.ConvLayer3 = nn.Sequential(
            nn.Conv2d(64, 128, 3),
            nn.MaxPool2d(2),
            nn.ReLU(),
            )    

        self.ConvLayer4 = nn.Sequential(
            nn.Conv2d(128, 256, 3),
            nn.MaxPool2d(2),
            nn.ReLU(),
            nn.Dropout(0.2, inplace=True),
            )    

        self.Linear1 = nn.Linear(256 * 4 * 4, 2048)
        self.Linear2 = nn.Linear(2048, 1024)
        self.Linear3 = nn.Linear(1024, 512)
        self.Linear4 = nn.Linear(512, len(classes))


    def forward(self, x):
        x = self.ConvLayer1(x)
        x = self.ConvLayer2(x)
        x = self.ConvLayer3(x)
        x = self.ConvLayer4(x)
#         print(x.size())
        x = x.view(-1, 256 * 4 * 4)
        x = self.Linear1(x)
        x = self.Linear2(x)
        x = self.Linear3(x)
        x = self.Linear4(x)
        return x

def try_gpu(target):
    if check_cuda():
        device = torch.device(check_cuda())
        target.to(device)

model = MultiClassifier()
try_gpu(model)

training

A variable called pos_weight suddenly appears in the criterion, but this is because of the weighting when the positive class is correct. https://pytorch.org/docs/stable/nn.html#torch.nn.BCEWithLogitsLoss

If you don't need such an operation, you don't need to specify it. I specified it because I wanted to increase the weight at the time of correct answer. The details are linked as ref, so there ~~ I escape the explanation ~~

# ref: https://medium.com/@thevatsalsaglani/training-and-deploying-a-multi-label-image-classifier-using-pytorch-flask-reactjs-and-firebase-c39c96f9c427
import numpy as np
from pprint import pprint
from torch.autograd import Variable
import torch.optim as optim

# ref: https://discuss.pytorch.org/t/bceloss-vs-bcewithlogitsloss/33586
# ref: https://discuss.pytorch.org/t/weights-in-bcewithlogitsloss/27452
criterion = nn.BCEWithLogitsLoss(pos_weight=pos_weight)
try_gpu(criterion)

optimizer = optim.SGD(model.parameters(), lr = 0.005, momentum = 0.9)

def pred_acc(original, predicted):
    # ref: https://pytorch.org/docs/stable/torch.html#module-torch
    return torch.round(predicted).eq(original).sum().numpy()/len(original)


def fit_model(epochs, model, dataloader, phase='training', volatile = False):
    if phase == 'training':
        model.train()
        
    if phase == 'validataion':
        model.eval()
        volatile = True
        
    running_loss = []
    running_acc = []
    for i, data in enumerate(dataloader):
        inputs, target = Variable(data['image']), Variable(data['label'])
        
        # for GPU
        if device != 'cpu':
            inputs, target = inputs.to(device), target.to(device)

        if phase == 'training':
            optimizer.zero_grad()  #Gradient initialization

        ops = model(inputs)
         acc_ = []
         for j, d in enumerate(ops):
             acc = pred_acc(torch.Tensor.cpu(target[j]), torch.Tensor.cpu(d))
             acc_.append(acc)

        loss = criterion(ops, target)
        running_loss.append(loss.item())
        running_acc.append(np.asarray(acc_).mean())
        
        if phase == 'training':
            loss.backward()  #Backpropagation of error
            optimizer.step() #Parameter update

    total_batch_loss = np.asarray(running_loss).mean()
    total_batch_acc = np.asarray(running_acc).mean()

    if epochs % 10 == 0:
        pprint(f"[{phase}] Epoch: {epochs}, loss: {total_batch_loss}.")
        pprint(f"[{phase}] Epoch: {epochs}, accuracy: {total_batch_acc}.")
    
    return total_batch_loss, total_batch_acc


from tqdm import tqdm

num = 50
best_val = 99
trn_losses = []; trn_acc = []
val_losses = []; val_acc = []
for idx in tqdm(range(1, num+1)):
    trn_l, trn_a = fit_model(idx, model, trainloader)
    val_l, val_a = fit_model(idx, model, testloader, phase='validation')
    trn_losses.append(trn_l); trn_acc.append(trn_a)
    val_losses.append(val_l); val_acc.append(val_a)

    if best_val > val_l:
        torch.save(model.state_dict(), f'model/best_model.pth')
        best_val = val_l
        best_idx = idx

Forecast

def get_tensor(img):
    tfms = transforms.Compose([
        transforms.Resize((100, 100)),
        transforms.ToTensor(),
        transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
        ])
    return tfms(Image.open(img)).unsqueeze(0)

def predict(img, label_lst, model):
    tnsr = get_tensor(img)
    op = model(tnsr)  # Predict result(float)
    op_b = torch.round(op) # Rounding result(0 or 1)
    op_b_np = torch.Tensor.cpu(op_b).detach().numpy()
    preds = np.where(op_b_np == 1)[1]  # result == 1
    
    sigs_op = torch.Tensor.cpu(torch.round((op)*100)).detach().numpy()[0]
    o_p = np.argsort(torch.Tensor.cpu(op).detach().numpy())[0][::-1]  # label index order by score desc
    
    # anser label
    label = [label_lst[i] for i in preds]
    
    # all result
    arg_s = {label_lst[int(j)] : sigs_op[int(j)] for j in o_p}

    return label, dict(arg_s.items())


model = MultiClassifier()
model.load_state_dict(torch.load(f'model/best_model.pth', map_location=torch.device('cpu')))
model = model.eval()    #Switch to inference mode

target = 'XXXXXX'
img = Image.open(f'predict/{target}.jpg').resize((100, 100))
plt.imshow(img)

_, all_result = predict(f'predict/{target}.jpg', classes, model)
print('predict top5: ', *sorted(all_result.items(), key=lambda x: x[1], reverse=True)[:5])

Finally

That's all for implementation.

Data Augmentation (It seems easy to implement), model polishing, I think there is still room for improvement in accuracy if appropriate weight settings are made during evaluation.

I was satisfied because I was able to make it for the time being.

…For your reference. I made something to predict like this.

It is a completely private work and does not represent the organization to which it belongs.

[PYTHON] Multi-class, multi-label classification of images with pytorch

Introduction

What i did

Folder structure

Folder structure

sample

code

Various preparations

data check

model

training

Forecast

Finally

`Folder structure`

`sample`