我怎样才能预测下面的 model。 我想在训练有素的 model 中输入图像并获得 output？

Question

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import os
import torch
import torchvision
from torchvision import datasets
from torchvision import transforms as T # for simplifying the transforms
from torch import nn, optim
from torch.nn import functional as F
from torch.utils.data import DataLoader, sampler, random_split
from torchvision import models
!pip install timm # kaggle doesnt have it installed by default
import timm
from timm.loss import LabelSmoothingCrossEntropy
import sys
from tqdm import tqdm
import time
import copy


def get_classes(data_dir):
    all_data = datasets.ImageFolder(data_dir)
    return all_data.classes


def get_data_loaders(data_dir, batch_size, train = False):
    if train:
        #train
        transform = T.Compose([
            T.RandomHorizontalFlip(),
            T.RandomVerticalFlip(),
            T.RandomApply(torch.nn.ModuleList([T.ColorJitter()]), p=0.25),
            T.Resize(256),
            T.CenterCrop(224),
            T.ToTensor(),
            T.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)), # imagenet means
            T.RandomErasing(p=0.2, value='random')
        ])
        train_data = datasets.ImageFolder(os.path.join(data_dir, "train/"), transform = transform)
        train_loader = DataLoader(train_data, batch_size=batch_size, shuffle=True, num_workers=4)
        return train_loader, len(train_data)
    else:
        # val/test
        transform = T.Compose([ # We dont need augmentation for test transforms
            T.Resize(256),
            T.CenterCrop(224),
            T.ToTensor(),
            T.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)), # imagenet means
        ])
        val_data = datasets.ImageFolder(os.path.join(data_dir, "validation/"), transform=transform)
        test_data = datasets.ImageFolder(os.path.join(data_dir, "train/"), transform=transform)
        val_loader = DataLoader(val_data, batch_size=batch_size, shuffle=True, num_workers=4)
        test_loader = DataLoader(test_data, batch_size=batch_size, shuffle=True, num_workers=4)
        return val_loader, test_loader, len(val_data), len(test_data)
dataset_path = "/kaggle/input/dfdc-faces-of-the-train-sample"
(train_loader, train_data_len) = get_data_loaders(dataset_path, 128, train=True)
(val_loader, test_loader, valid_data_len, test_data_len) = get_data_loaders(dataset_path, 32, train=False)


classes = get_classes("/kaggle/input/dfdc-faces-of-the-train-sample/train")

print(classes, len(classes))
dataloaders = {
    "train": train_loader,
    "validation": val_loader
}
dataset_sizes = {
    "train": train_data_len,
    "validation": valid_data_len
}

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

model = torch.hub.load('facebookresearch/deit:main', 'deit_tiny_patch16_224', pretrained=True)

for param in model.parameters(): #freeze model
    param.requires_grad = False

n_inputs = model.head.in_features
model.head = nn.Sequential(
    nn.Linear(n_inputs, 512),
    nn.ReLU(),
    nn.Dropout(0.3),
    nn.Linear(512, len(classes))
)
model = model.to(device)
print(model.head)

criterion = LabelSmoothingCrossEntropy()
criterion = criterion.to(device)
optimizer = optim.Adam(model.head.parameters(), lr=0.001)

# lr scheduler
exp_lr_scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=3, gamma=0.97)

def train_model(model, criterion, optimizer, scheduler, num_epochs=1):
    since = time.time()
    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0
    
    for epoch in range(num_epochs):
        print(f'Epoch {epoch}/{num_epochs - 1}')
        print("-"*10)
        
        for phase in ['train', 'validation']: # We do training and validation phase per epoch
            if phase == 'train':
                model.train() # model to training mode
            else:
                model.eval() # model to evaluate
            
            running_loss = 0.0
            running_corrects = 0.0
            
            for inputs, labels in tqdm(dataloaders[phase]):
                inputs = inputs.to(device)
                labels = labels.to(device)
                
                optimizer.zero_grad()
                
                with torch.set_grad_enabled(phase == 'train'): # no autograd makes validation go faster
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1) # used for accuracy
                    loss = criterion(outputs, labels)
                    
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)
                
            if phase == 'train':
                scheduler.step() # step at end of epoch
            
            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc =  running_corrects.double() / dataset_sizes[phase]
            
            print("{} Loss: {:.4f} Acc: {:.4f}".format(phase, epoch_loss, epoch_acc))
            
            if phase == 'validation' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict()) # keep the best validation accuracy model
        print()
    time_elapsed = time.time() - since # slight error
    print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
    print("Best Val Acc: {:.4f}".format(best_acc))
    
    model.load_state_dict(best_model_wts)
    return model

model_ft = train_model(model, criterion, optimizer, exp_lr_scheduler)# now it is a lot faster


test_loss = 0.0
class_correct = list(0 for i in range(len(classes)))
class_total = list(0 for i in range(len(classes)))
model.eval()

for data, target in tqdm(test_loader):
    data, target = data.to(device), target.to(device)
    with torch.no_grad(): # turn off autograd for faster testing
        output = model(data)
        loss = criterion(output, target)
    test_loss = loss.item() * data.size(0)
    _, pred = torch.max(output, 1)
    correct_tensor = pred.eq(target.data.view_as(pred))
    correct = np.squeeze(correct_tensor.cpu().numpy())
    if len(target) == 32:
        for i in range(32):
            label = target.data[i]
            class_correct[label] += correct[i].item()
            class_total[label] += 1

test_loss = test_loss / test_data_len
print('Test Loss: {:.4f}'.format(test_loss))
for i in range(len(classes)):
    if class_total[i] > 0:
        print("Test Accuracy of %5s: %2d%% (%2d/%2d)" % (
            classes[i], 100*class_correct[i]/class_total[i], np.sum(class_correct[i]), np.sum(class_total[i])
        ))
    else:
        print("Test accuracy of %5s: NA" % (classes[i]))
print("Test Accuracy of %2d%% (%2d/%2d)" % (
            100*np.sum(class_correct)/np.sum(class_total), np.sum(class_correct), np.sum(class_total)
        ))

torch.save(model.state_dict(),'checkpoint.pt')

I have copied this code from Kaggle and similarly the data. The dataset is also present on kaggle and it's name is same as used in the code dataset path above. The code just works fine and also makes the model, but I don't know how to make a prediction.

Answer 1

from PIL import Image
import cv2

path_to_model = 'checkpoint.pt'

imgpath='../input/dfdc-faces-of-the-train-sample/train/fake/aapnvogymq_0_0.png'
img=cv2.imread(imgpath)

transform = T.Compose([ # We dont need augmentation for test transforms
            T.Resize(256),
            T.CenterCrop(224),
            T.ToTensor(),
            T.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)), # imagenet means
        ])

PIL_image = Image.fromarray(np.uint8(img)).convert('RGB')
imge=transform(PIL_image)
imge=imge.view(-1,3,224,224)
print(imge.shape)
model.load_state_dict(torch.load(path_to_model))
#print(summary(model,(3,224,224)))
model.eval()
labels = labels.to(device)
logits = model(imge.to(device))
params = list(model.parameters())
sm = nn.Softmax()
#weight_softmax = model.linear1.weight.detach().cpu().numpy()
logits = sm(logits)
_,prediction = torch.max(logits,1)
confidence = logits[:,int(prediction.item())].item()*100
print('confidence of prediction:',logits[:,int(prediction.item())].item()*100)
print(prediction.item())

I did it myself and I can predict now