1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
|
""" @author: zj @file: finetune.py @time: 2020-02-26 """
import time import copy import os import numpy as np import matplotlib.pyplot as plt import torch import torch.nn as nn import torch.optim as optim from torch.utils.data import DataLoader import torchvision import torchvision.datasets as datasets import torchvision.transforms as transforms import torchvision.models as models
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)
def load_data(): 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 = 'data/hymenoptera_data' image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']} dataloaders = {x: 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
return dataloaders, dataset_sizes, class_names
def show_data(dataloaders): inputs, classes = next(iter(dataloaders['train'])) out = torchvision.utils.make_grid(inputs) imshow(out, title=[class_names[x] for x in classes])
def visualize_model(model, dataloaders, class_names, num_images=6): """ 可视化模型训练结果 """ 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)
def visualize_train(): """ 可视化训练损失和精度 """
def create_model(mode='ri'): if mode == 'fixed': model_conv = torchvision.models.resnet18(pretrained=True) for param in model_conv.parameters(): param.requires_grad = False return model_conv elif mode == 'ft': return models.resnet18(pretrained=True) else: return models.resnet18()
def train_model(model, criterion, optimizer, scheduler, dataset_sizes, dataloaders, 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)
for phase in ['train', 'val']: if phase == 'train': model.train() else: model.eval()
running_loss = 0.0 running_corrects = 0
for inputs, labels in dataloaders[phase]: inputs = inputs.to(device) labels = labels.to(device)
optimizer.zero_grad()
with torch.set_grad_enabled(phase == 'train'): outputs = model(inputs) _, preds = torch.max(outputs, 1) 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()
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 == '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))
model.load_state_dict(best_model_wts) return model
if __name__ == '__main__': device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
dataloaders, dataset_sizes, class_names = load_data() show_data(dataloaders)
for mode_name in {'ri', 'ft', 'fixed'}: print('begin mode: %s' % mode_name) print('#' * 20) model = create_model(mode=mode_name)
num_ftrs = model.fc.in_features model.fc = nn.Linear(num_ftrs, 2)
model_conv = model.to(device) criterion = nn.CrossEntropyLoss() optimizer_conv = optim.SGD(model_conv.parameters(), lr=0.001, momentum=0.9) exp_lr_scheduler = optim.lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)
model_conv = train_model(model_conv, criterion, optimizer_conv, exp_lr_scheduler, dataset_sizes, dataloaders, num_epochs=25)
|