pytorch 检测图片中是否有人
Posted wzyuan
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了pytorch 检测图片中是否有人相关的知识，希望对你有一定的参考价值。
照搬pytorch官方代码，只是将数据集换成了INRIAPerson数据集中的train和test文件夹。
贴下代码和效果，代码是官方的，就不详细解释了。
# License: BSD # Author: Sasank Chilamkurthy from __future__ import print_function, division import torch import torch.nn as nn import torch.optim as optim from torch.optim import lr_scheduler import numpy as np import torchvision from torchvision import datasets, models, transforms import matplotlib.pyplot as plt import time import os import copy plt.ion() # interactive mode
# Data augmentation and normalization for training # Just normalization for validation data_transforms = { ‘train‘: transforms.Compose([ transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]), ‘val‘: transforms.Compose([ transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]), } data_dir = ‘person‘ image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in [‘train‘, ‘val‘]} dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4, shuffle=True, num_workers=4) for x in [‘train‘, ‘val‘]} dataset_sizes = {x: len(image_datasets[x]) for x in [‘train‘, ‘val‘]} class_names = image_datasets[‘train‘].classes device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
def imshow(inp, title=None): """Imshow for Tensor.""" inp = inp.numpy().transpose((1, 2, 0)) mean = np.array([0.485, 0.456, 0.406]) std = np.array([0.229, 0.224, 0.225]) inp = std * inp + mean inp = np.clip(inp, 0, 1) plt.imshow(inp) if title is not None: plt.title(title) plt.pause(0.001) # pause a bit so that plots are updated # Get a batch of training data inputs, classes = next(iter(dataloaders[‘train‘])) # Make a grid from batch out = torchvision.utils.make_grid(inputs) imshow(out, title=[class_names[x] for x in classes])
def train_model(model, criterion, optimizer, scheduler, num_epochs=25): since = time.time() best_model_wts = copy.deepcopy(model.state_dict()) best_acc = 0.0 for epoch in range(num_epochs): print(‘Epoch {}/{}‘.format(epoch, num_epochs - 1)) print(‘-‘ * 10) # Each epoch has a training and validation phase for phase in [‘train‘, ‘val‘]: if phase == ‘train‘: scheduler.step() model.train() # Set model to training mode else: model.eval() # Set model to evaluate mode running_loss = 0.0 running_corrects = 0 # Iterate over data. for inputs, labels in dataloaders[phase]: inputs = inputs.to(device) labels = labels.to(device) # zero the parameter gradients optimizer.zero_grad() # forward # track history if only in train with torch.set_grad_enabled(phase == ‘train‘): outputs = model(inputs) _, preds = torch.max(outputs, 1) loss = criterion(outputs, labels) # backward + optimize only if in training phase if phase == ‘train‘: loss.backward() optimizer.step() # statistics running_loss += loss.item() * inputs.size(0) running_corrects += torch.sum(preds == labels.data) 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)) # deep copy the model if phase == ‘val‘ and epoch_acc > best_acc: best_acc = epoch_acc best_model_wts = copy.deepcopy(model.state_dict()) print() time_elapsed = time.time() - since print(‘Training complete in {:.0f}m {:.0f}s‘.format( time_elapsed // 60, time_elapsed % 60)) print(‘Best val Acc: {:4f}‘.format(best_acc)) # load best model weights model.load_state_dict(best_model_wts) return model
def visualize_model(model, num_images=6): was_training = model.training model.eval() images_so_far = 0 fig = plt.figure() with torch.no_grad(): for i, (inputs, labels) in enumerate(dataloaders[‘val‘]): inputs = inputs.to(device) labels = labels.to(device) outputs = model(inputs) _, preds = torch.max(outputs, 1) for j in range(inputs.size()[0]): images_so_far += 1 ax = plt.subplot(num_images//2, 2, images_so_far) ax.axis(‘off‘) ax.set_title(‘predicted: {}‘.format(class_names[preds[j]])) imshow(inputs.cpu().data[j]) if images_so_far == num_images: model.train(mode=was_training) return model.train(mode=was_training)
model_ft = models.resnet18(pretrained=True) num_ftrs = model_ft.fc.in_features model_ft.fc = nn.Linear(num_ftrs, 2) model_ft = model_ft.to(device) criterion = nn.CrossEntropyLoss() # Observe that all parameters are being optimized optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9) # Decay LR by a factor of 0.1 every 7 epochs exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
num_epochs=25)
Epoch 0/24 ---------- train Loss: 0.4124 Acc: 0.8477 val Loss: 0.0737 Acc: 0.9744 Epoch 1/24 ---------- train Loss: 0.2891 Acc: 0.9023 val Loss: 0.0836 Acc: 0.9703 Epoch 2/24 ---------- train Loss: 0.3094 Acc: 0.9050 val Loss: 0.0614 Acc: 0.9771 Epoch 3/24 ---------- train Loss: 0.2308 Acc: 0.9279 val Loss: 0.0429 Acc: 0.9865 Epoch 4/24 ---------- train Loss: 0.1748 Acc: 0.9498 val Loss: 0.0331 Acc: 0.9906 Epoch 5/24 ---------- train Loss: 0.2252 Acc: 0.9301 val Loss: 0.0702 Acc: 0.9906 Epoch 6/24 ---------- train Loss: 0.1726 Acc: 0.9531 val Loss: 0.0442 Acc: 0.9852 Epoch 7/24 ---------- train Loss: 0.1595 Acc: 0.9536 val Loss: 0.0359 Acc: 0.9906 Epoch 8/24 ---------- train Loss: 0.1310 Acc: 0.9651 val Loss: 0.0355 Acc: 0.9892 Epoch 9/24 ---------- train Loss: 0.1172 Acc: 0.9689 val Loss: 0.0325 Acc: 0.9906 Epoch 10/24 ---------- train Loss: 0.1070 Acc: 0.9733 val Loss: 0.0515 Acc: 0.9838 Epoch 11/24 ---------- train Loss: 0.1304 Acc: 0.9683 val Loss: 0.0452 Acc: 0.9892 Epoch 12/24 ---------- train Loss: 0.1164 Acc: 0.9656 val Loss: 0.0424 Acc: 0.9892 Epoch 13/24 ---------- train Loss: 0.0751 Acc: 0.9809 val Loss: 0.0396 Acc: 0.9906 Epoch 14/24 ---------- train Loss: 0.1091 Acc: 0.9749 val Loss: 0.0279 Acc: 0.9946 Epoch 15/24 ---------- train Loss: 0.0751 Acc: 0.9842 val Loss: 0.0352 Acc: 0.9906 Epoch 16/24 ---------- train Loss: 0.1353 Acc: 0.9705 val Loss: 0.0413 Acc: 0.9879 Epoch 17/24 ---------- train Loss: 0.0957 Acc: 0.9787 val Loss: 0.0332 Acc: 0.9906 Epoch 18/24 ---------- train Loss: 0.1091 Acc: 0.9689 val Loss: 0.0317 Acc: 0.9906 Epoch 19/24 ---------- train Loss: 0.1101 Acc: 0.9700 val Loss: 0.0402 Acc: 0.9879 Epoch 20/24 ---------- train Loss: 0.1133 Acc: 0.9754 val Loss: 0.0392 Acc: 0.9892 Epoch 21/24 ---------- train Loss: 0.0970 Acc: 0.9776 val Loss: 0.0424 Acc: 0.9865 Epoch 22/24 ---------- train Loss: 0.0865 Acc: 0.9814 val Loss: 0.0348 Acc: 0.9919 Epoch 23/24 ---------- train Loss: 0.1319 Acc: 0.9656 val Loss: 0.0341 Acc: 0.9892 Epoch 24/24 ---------- train Loss: 0.0997 Acc: 0.9771 val Loss: 0.0328 Acc: 0.9906 Training complete in 9m 32s Best val Acc: 0.994602 In [30]: visualize_model(model_ft)
visualize_model(model_ft)
model_conv = torchvision.models.resnet18(pretrained=True) for param in model_conv.parameters(): param.requires_grad = False # Parameters of newly constructed modules have requires_grad=True by default num_ftrs = model_conv.fc.in_features model_conv.fc = nn.Linear(num_ftrs, 2) model_conv = model_conv.to(device) criterion = nn.CrossEntropyLoss() # Observe that only parameters of final layer are being optimized as # opoosed to before. optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9) # Decay LR by a factor of 0.1 every 7 epochs exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)
model_conv = train_model(model_conv, criterion, optimizer_conv,
exp_lr_scheduler, num_epochs=25)
Epoch 0/24 ---------- train Loss: 0.3994 Acc: 0.8466 val Loss: 0.2137 Acc: 0.9109 Epoch 1/24 ---------- train Loss: 0.2783 Acc: 0.8963 val Loss: 0.0649 Acc: 0.9744 Epoch 2/24 ---------- train Loss: 0.2976 Acc: 0.8870 val Loss: 0.0577 Acc: 0.9811 Epoch 3/24 ---------- train Loss: 0.2873 Acc: 0.9039 val Loss: 0.0477 Acc: 0.9825 Epoch 4/24 ---------- train Loss: 0.3214 Acc: 0.8843 val Loss: 0.0499 Acc: 0.9798 Epoch 5/24 ---------- train Loss: 0.3244 Acc: 0.8772 val Loss: 0.0483 Acc: 0.9798 Epoch 6/24 ---------- train Loss: 0.2855 Acc: 0.8985 val Loss: 0.0446 Acc: 0.9825 Epoch 7/24 ---------- train Loss: 0.2425 Acc: 0.9121 val Loss: 0.0460 Acc: 0.9798 Epoch 8/24 ---------- train Loss: 0.2070 Acc: 0.9219 val Loss: 0.0390 Acc: 0.9879 Epoch 9/24 ---------- train Loss: 0.2189 Acc: 0.9127 val Loss: 0.0408 Acc: 0.9825 Epoch 10/24 ---------- train Loss: 0.2243 Acc: 0.9148 val Loss: 0.0577 Acc: 0.9825 Epoch 11/24 ---------- train Loss: 0.2042 Acc: 0.9236 val Loss: 0.0519 Acc: 0.9852 Epoch 12/24 ---------- train Loss: 0.2425 Acc: 0.9083 val Loss: 0.0440 Acc: 0.9838 Epoch 13/24 ---------- train Loss: 0.2127 Acc: 0.9198 val Loss: 0.0454 Acc: 0.9865 Epoch 14/24 ---------- train Loss: 0.2479 Acc: 0.9045 val Loss: 0.0551 Acc: 0.9771 Epoch 15/24 ---------- train Loss: 0.2562 Acc: 0.8990 val Loss: 0.0491 Acc: 0.9852 Epoch 16/24 ---------- train Loss: 0.2104 Acc: 0.9143 val Loss: 0.0448 Acc: 0.9852 Epoch 17/24 ---------- train Loss: 0.2606 Acc: 0.8974 val Loss: 0.0480 Acc: 0.9798 Epoch 18/24 ---------- train Loss: 0.2474 Acc: 0.9067 val Loss: 0.0639 Acc: 0.9798 Epoch 19/24 ---------- train Loss: 0.2159 Acc: 0.9176 val Loss: 0.0495 Acc: 0.9852 Epoch 20/24 ---------- train Loss: 0.2107 Acc: 0.9170 val Loss: 0.0482 Acc: 0.9838 Epoch 21/24 ---------- train Loss: 0.2128 Acc: 0.9121 val Loss: 0.0522 Acc: 0.9838 Epoch 22/24 ---------- train Loss: 0.2263 Acc: 0.9176 val Loss: 0.0459 Acc: 0.9852 Epoch 23/24 ---------- train Loss: 0.1907 Acc: 0.9329 val Loss: 0.0460 Acc: 0.9906 Epoch 24/24 ---------- train Loss: 0.2302 Acc: 0.9181 val Loss: 0.0425 Acc: 0.9879 Training complete in 4m 31s Best val Acc: 0.990553 In [33]: visualize_model(model_conv)
visualize_model(model_conv) plt.ioff() plt.show()
微调和特征提取两种方法的效果都很棒
以上是关于pytorch 检测图片中是否有人的主要内容，如果未能解决你的问题，请参考以下文章
Python代码阅读（第13篇）：检测列表中的元素是否都一样
在一个片段中检测Recyclerview的上下滑动，我怎么做？
物体检测object detection object recognition和coco数据集 动手学深度学习v2 pytorch