Pytorch实现姿态识别（三）——训练与推理

ゝ一世哀愁。 2023-02-28 12:57 46阅读 0赞

# train.py #

#dataset:https://www.crcv.ucf.edu/data/UCF101.php
    
    import timeit
    from datetime import datetime
    import socket
    import os
    import glob
    from tqdm import tqdm
    
    import torch
    from tensorboardX import SummaryWriter
    from torch import nn, optim
    from torch.utils.data import DataLoader
    from torch.autograd import Variable
    
    from dataloaders.dataset import VideoDataset
    from network import C3D_model
    
    # Use GPU if available else revert to CPU
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    print("Device being used:", device)
    
    nEpochs = 101  # Number of epochs for training
    resume_epoch = 0  # Default is 0, change if want to resume
    useTest = True # See evolution of the test set when training
    nTestInterval = 20 # Run on test set every nTestInterval epochs
    snapshot = 25 # Store a model every snapshot epochs
    lr = 1e-5 # Learning rate
    
    dataset = 'ucf101' # Options: hmdb51 or ucf101
    
    if dataset == 'hmdb51':
        num_classes=51
    elif dataset == 'ucf101':
        num_classes = 101
    else:
        print('We only implemented hmdb and ucf datasets.')
        raise NotImplementedError
    
    save_dir_root = os.path.join(os.path.dirname(os.path.abspath(__file__)))
    exp_name = os.path.dirname(os.path.abspath(__file__)).split('/')[-1]
    
    if resume_epoch != 0:
        runs = sorted(glob.glob(os.path.join(save_dir_root, 'run', 'run_*')))
        run_id = int(runs[-1].split('_')[-1]) if runs else 0
    else:
        runs = sorted(glob.glob(os.path.join(save_dir_root, 'run', 'run_*')))
        run_id = int(runs[-1].split('_')[-1]) + 1 if runs else 0
    
    save_dir = os.path.join(save_dir_root, 'run', 'run_' + str(run_id))
    modelName = 'C3D' # Options: C3D or R2Plus1D or R3D
    saveName = modelName + '-' + dataset
    
    def train_model(dataset=dataset, save_dir=save_dir, num_classes=num_classes, lr=lr,
                    num_epochs=nEpochs, save_epoch=snapshot, useTest=useTest, test_interval=nTestInterval):
        """
            Args:
                num_classes (int): Number of classes in the data
                num_epochs (int, optional): Number of epochs to train for.
        """
    
    
        model = C3D_model.C3D(num_classes=num_classes, pretrained=False)
        train_params = [{
        'params': C3D_model.get_1x_lr_params(model), 'lr': lr},
                        {
        'params': C3D_model.get_10x_lr_params(model), 'lr': lr * 10}]
        
        criterion = nn.CrossEntropyLoss()  # standard crossentropy loss for classification
        optimizer = optim.SGD(train_params, lr=lr, momentum=0.9, weight_decay=5e-4)
        scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=10,
                                              gamma=0.1)  # the scheduler divides the lr by 10 every 10 epochs
    
        if resume_epoch == 0:
            print("Training {} from scratch...".format(modelName))
        else:
            checkpoint = torch.load(os.path.join(save_dir, 'models', saveName + '_epoch-' + str(resume_epoch - 1) + '.pth.tar'),
                           map_location=lambda storage, loc: storage)   # Load all tensors onto the CPU
            print("Initializing weights from: {}...".format(
                os.path.join(save_dir, 'models', saveName + '_epoch-' + str(resume_epoch - 1) + '.pth.tar')))
            model.load_state_dict(checkpoint['state_dict'])
            optimizer.load_state_dict(checkpoint['opt_dict'])
    
        print('Total params: %.2fM' % (sum(p.numel() for p in model.parameters()) / 1000000.0))
        model.to(device)
        criterion.to(device)
    
        log_dir = os.path.join(save_dir, 'models', datetime.now().strftime('%b%d_%H-%M-%S') + '_' + socket.gethostname())
        writer = SummaryWriter(log_dir=log_dir)
    
        print('Training model on {} dataset...'.format(dataset))
        train_dataloader = DataLoader(VideoDataset(dataset=dataset, split='train',clip_len=16), batch_size=6, shuffle=True, num_workers=0)
        val_dataloader   = DataLoader(VideoDataset(dataset=dataset, split='val',  clip_len=16), batch_size=6, num_workers=0)
        test_dataloader  = DataLoader(VideoDataset(dataset=dataset, split='test', clip_len=16), batch_size=6, num_workers=0)
    
        trainval_loaders = {
        'train': train_dataloader, 'val': val_dataloader}
        trainval_sizes = {
        x: len(trainval_loaders[x].dataset) for x in ['train', 'val']}
        test_size = len(test_dataloader.dataset)
    
        for epoch in range(resume_epoch, num_epochs):
            # each epoch has a training and validation step
            for phase in ['train', 'val']:
                start_time = timeit.default_timer()
    
                # reset the running loss and corrects
                running_loss = 0.0
                running_corrects = 0.0
    
                # set model to train() or eval() mode depending on whether it is trained
                # or being validated. Primarily affects layers such as BatchNorm or Dropout.
                if phase == 'train':
                    # scheduler.step() is to be called once every epoch during training
                    scheduler.step()
                    model.train()
                else:
                    model.eval()
    
                for inputs, labels in tqdm(trainval_loaders[phase]):
                    # move inputs and labels to the device the training is taking place on
                    inputs = Variable(inputs, requires_grad=True).to(device)
                    labels = Variable(labels).to(device)
                    optimizer.zero_grad()
    
                    if phase == 'train':
                        outputs = model(inputs)
                    else:
                        with torch.no_grad():
                            outputs = model(inputs)
    
                    probs = nn.Softmax(dim=1)(outputs)
                    preds = torch.max(probs, 1)[1]
                    loss = criterion(outputs, labels.long())
    
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()
    
                    running_loss += loss.item() * inputs.size(0)
                    running_corrects += torch.sum(preds == labels.data)
    
                epoch_loss = running_loss / trainval_sizes[phase]
                epoch_acc = running_corrects.double() / trainval_sizes[phase]
    
                if phase == 'train':
                    writer.add_scalar('data/train_loss_epoch', epoch_loss, epoch)
                    writer.add_scalar('data/train_acc_epoch', epoch_acc, epoch)
                else:
                    writer.add_scalar('data/val_loss_epoch', epoch_loss, epoch)
                    writer.add_scalar('data/val_acc_epoch', epoch_acc, epoch)
    
                print("[{}] Epoch: {}/{} Loss: {} Acc: {}".format(phase, epoch+1, nEpochs, epoch_loss, epoch_acc))
                stop_time = timeit.default_timer()
                print("Execution time: " + str(stop_time - start_time) + "\n")
    
            if epoch % save_epoch == (save_epoch - 1):
                torch.save({
        
                    'epoch': epoch + 1,
                    'state_dict': model.state_dict(),
                    'opt_dict': optimizer.state_dict(),
                }, os.path.join(save_dir, 'models', saveName + '_epoch-' + str(epoch) + '.pth.tar'))
                print("Save model at {}\n".format(os.path.join(save_dir, 'models', saveName + '_epoch-' + str(epoch) + '.pth.tar')))
    
            if useTest and epoch % test_interval == (test_interval - 1):
                model.eval()
                start_time = timeit.default_timer()
    
                running_loss = 0.0
                running_corrects = 0.0
    
                for inputs, labels in tqdm(test_dataloader):
                    inputs = inputs.to(device)
                    labels = labels.to(device)
    
                    with torch.no_grad():
                        outputs = model(inputs)
                    probs = nn.Softmax(dim=1)(outputs)
                    preds = torch.max(probs, 1)[1]
                    loss = criterion(outputs, labels.long())
    
                    running_loss += loss.item() * inputs.size(0)
                    running_corrects += torch.sum(preds == labels.data)
    
                epoch_loss = running_loss / test_size
                epoch_acc = running_corrects.double() / test_size
    
                writer.add_scalar('data/test_loss_epoch', epoch_loss, epoch)
                writer.add_scalar('data/test_acc_epoch', epoch_acc, epoch)
    
                print("[test] Epoch: {}/{} Loss: {} Acc: {}".format(epoch+1, nEpochs, epoch_loss, epoch_acc))
                stop_time = timeit.default_timer()
                print("Execution time: " + str(stop_time - start_time) + "\n")
    
        writer.close()
    
    
    if __name__ == "__main__":
        train_model()

# inference.py #

import torch
    import numpy as np
    from network import C3D_model
    import cv2
    torch.backends.cudnn.benchmark = True
    
    def CenterCrop(frame, size):
        h, w = np.shape(frame)[0:2]
        th, tw = size
        x1 = int(round((w - tw) / 2.))
        y1 = int(round((h - th) / 2.))
    
        frame = frame[y1:y1 + th, x1:x1 + tw, :]
        return np.array(frame).astype(np.uint8)
    
    
    def center_crop(frame):
        frame = frame[8:120, 30:142, :]
        return np.array(frame).astype(np.uint8)
    
    
    def main():
        device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
        print("Device being used:", device)
    
        with open('./dataloaders/ucf_labels.txt', 'r') as f:
            class_names = f.readlines()
            f.close()
        # init model
        model = C3D_model.C3D(num_classes=101)
        checkpoint = torch.load(r'.\run\\run_0\\models\\C3D-ucf101_epoch-99.pth.tar', map_location=lambda storage, loc: storage)
        
        """
        state_dict = model.state_dict()
        for k1, k2 in zip(state_dict.keys(), checkpoint.keys()):
            state_dict[k1] = checkpoint[k2]
        model.load_state_dict(state_dict)
        """
        model.load_state_dict(checkpoint['state_dict'])#模型参数
        #optimizer.load_state_dict(checkpoint['opt_dict'])#优化参数
        
        model.to(device)
        model.eval()
    
        # read video
        video = r'F:\DATASET\UCF-101\UCF-101\ApplyEyeMakeup\v_ApplyEyeMakeup_g08_c03.avi'
        cap = cv2.VideoCapture(video)
        retaining = True
    
        clip = []
        while retaining:
            retaining, frame = cap.read()
            if not retaining and frame is None:
                continue
            tmp_ = center_crop(cv2.resize(frame, (171, 128)))
            tmp = tmp_ - np.array([[[90.0, 98.0, 102.0]]])
            clip.append(tmp)
            if len(clip) == 16:
                inputs = np.array(clip).astype(np.float32)
                inputs = np.expand_dims(inputs, axis=0)
                inputs = np.transpose(inputs, (0, 4, 1, 2, 3))
                inputs = torch.from_numpy(inputs)
                inputs = torch.autograd.Variable(inputs, requires_grad=False).to(device)
                with torch.no_grad():
                    outputs = model.forward(inputs)
    
                probs = torch.nn.Softmax(dim=1)(outputs)
                label = torch.max(probs, 1)[1].detach().cpu().numpy()[0]
    
                cv2.putText(frame, class_names[label].split(' ')[-1].strip(), (20, 20),
                            cv2.FONT_HERSHEY_SIMPLEX, 0.6,
                            (0, 0, 255), 1)
                cv2.putText(frame, "prob: %.4f" % probs[0][label], (20, 40),
                            cv2.FONT_HERSHEY_SIMPLEX, 0.6,
                            (0, 0, 255), 1)
                clip.pop(0)
    
            cv2.imshow('result', frame)
            cv2.waitKey(30)
    
        cap.release()
        cv2.destroyAllWindows()
    
    
    if __name__ == '__main__':
        main()

看下效果  
![在这里插入图片描述][20200721165242762.gif]  
![在这里插入图片描述][20200721165508176.gif]

[20200721165242762.gif]: /images/20230209/5cb903dd07a54197aecbd098e786249b.png
[20200721165508176.gif]: https://img-blog.csdnimg.cn/20200721165508176.gif