torch.utils.data.Dataset
,实现__len__
和__getitem__
参考
dict
)torch.nn.Sequential()
容器进行快速搭建,模型的各层被顺序添加到容器中。缺点是每层的编号是默认的阿拉伯数字,不易区分。add_module()
添加每一层,并且为每一层增加了一个单独的名字。# Method 1
class Net1(torch.nn.Module):
def __init__(self):
super(Net1, self).__init__()
self.conv1 = torch.nn.Conv2d(3, 32, 3, 1, 1)
self.dense1 = torch.nn.Linear(32 * 3 * 3, 128)
self.dense2 = torch.nn.Linear(128, 10)
def forward(self, x):
x = F.max_pool2d(F.relu(self.conv(x)), 2)
x = x.view(x.size(0), -1)
x = F.relu(self.dense1(x))
x = self.dense2(x)
return x
# Method 2
class Net2(torch.nn.Module):
def __init__(self):
super(Net2, self).__init__()
self.conv = torch.nn.Sequential(
torch.nn.Conv2d(3, 32, 3, 1, 1),
torch.nn.ReLU(),
torch.nn.MaxPool2d(2))
self.dense = torch.nn.Sequential(
torch.nn.Linear(32 * 3 * 3, 128),
torch.nn.ReLU(),
torch.nn.Linear(128, 10)
)
def forward(self, x):
conv_out = self.conv1(x)
res = conv_out.view(conv_out.size(0), -1)
out = self.dense(res)
return out
# Method 3
class Net3(torch.nn.Module):
def __init__(self):
super(Net3, self).__init__()
self.conv=torch.nn.Sequential()
self.conv.add_module("conv1",torch.nn.Conv2d(3, 32, 3, 1, 1))
self.conv.add_module("relu1",torch.nn.ReLU())
self.conv.add_module("pool1",torch.nn.MaxPool2d(2))
self.dense = torch.nn.Sequential()
self.dense.add_module("dense1",torch.nn.Linear(32 * 3 * 3, 128))
self.dense.add_module("relu2",torch.nn.ReLU())
self.dense.add_module("dense2",torch.nn.Linear(128, 10))
def forward(self, x):
conv_out = self.conv1(x)
res = conv_out.view(conv_out.size(0), -1)
out = self.dense(res)
return out
# Method 4
class Net4(torch.nn.Module):
def __init__(self):
super(Net4, self).__init__()
self.conv = torch.nn.Sequential(
OrderedDict(
[
("conv1", torch.nn.Conv2d(3, 32, 3, 1, 1)),
("relu1", torch.nn.ReLU()),
("pool", torch.nn.MaxPool2d(2))
]
))
self.dense = torch.nn.Sequential(
OrderedDict([
("dense1", torch.nn.Linear(32 * 3 * 3, 128)),
("relu2", torch.nn.ReLU()),
("dense2", torch.nn.Linear(128, 10))
])
)
def forward(self, x):
conv_out = self.conv1(x)
res = conv_out.view(conv_out.size(0), -1)
out = self.dense(res)
return out
Mask-R-CNN-Fine-tune
# vis_model
example = torch.rand(1, 3, 480, 640)
torch_out = torch.onnx.export(model, example, "test.onnx")
netron.start("test.onnx")
def get_model_instance_segmentation2(num_classes):
# Backbone
backbone = tv.models.mobilenet_v2(pretrained=True).features
backbone.out_channels = 1280 # FasterRCNN需要backbone的输出通道
anchor_gen = AnchorGenerator(sizes=((32,64,128,256,512),),
aspect_ratios=((0.5,1.0,2.0),))
roi_pooler = tv.ops.MultiScaleRoIAlign(featmap_names=['0'],
output_size=7, sampling_ratio=2)
mask_roi_pooler = tv.ops.MultiScaleRoIAlign(featmap_names=['0'],
output_size=14, sampling_ratio=2)
model = MaskRCNN(backbone, num_classes=num_classes,
rpn_anchor_generator=anchor_gen, box_roi_pool=roi_pooler,
mask_roi_pool=mask_roi_pooler)
# model = FasterRCNN(backbone, num_classes=num_classes,
# rpn_anchor_generator=anchor_gen, box_roi_pool=roi_pooler)
return model
- 初始化预训练模型
- 重塑最终图层,使其输出数量与新数据集中的类数相同
- 为优化算法定义我们要在训练期间更新哪些参数
- 运行训练步骤
(classifier): Sequential(
...
(6): Linear(in_features=4096,
out_features=1000, bias=True)
)
(classifier): Sequential(
...
(6): Linear(in_features=4096, out_features=1000, bias=True)
)
(classifier): Sequential(
(0): Dropout(p=0.5)
(1): Conv2d(512, 1000, kernel_size=(1, 1), stride=(1, 1))
(2): ReLU(inplace)
(3): AvgPool2d(kernel_size=13, stride=1, padding=0)
)
(AuxLogits): InceptionAux(
...
(fc): Linear(in_features=768, out_features=1000, bias=True)
)
...
(fc): Linear(in_features=2048, out_features=1000, bias=True)
from __future__ import print_function
from __future__ import division
import torch, torchvision
import torch.nn as nn
import torch.optim as optim
import numpy as np
import matplotlib.pyplot as plt
from torchvision import datasets, models, transforms
import time, os, copy
def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False):
since = time.time()
val_acc_history = []
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)
# zero the parameter gradients
optimizer.zero_grad()
# forward
# track history if only in train
with torch.set_grad_enabled(phase == 'train'):
# Get model outputs and calculate loss
# Special case for inception because in training it has an auxiliary output. In train
# mode we calculate the loss by summing the final output and the auxiliary output
# but in testing we only consider the final output.
if is_inception and phase == 'train':
# From https://discuss.pytorch.org/t/how-to-optimize-inception-model-with-auxiliary-classifiers/7958
outputs, aux_outputs = model(inputs)
loss1 = criterion(outputs, labels)
loss2 = criterion(aux_outputs, labels)
loss = loss1 + 0.4*loss2
else:
outputs = model(inputs)
loss = criterion(outputs, labels)
_, preds = torch.max(outputs, 1)
# 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 / len(dataloaders[phase].dataset)
epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
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())
if phase == 'val':
val_acc_history.append(epoch_acc)
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, val_acc_history
def set_parameter_requires_grad(model, feature_extracting):
if feature_extracting:
for param in model.parameters():
param.requires_grad = False
def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):
# Initialize these variables which will be set in this if statement. Each of these
# variables is model specific.
model_ft = None
input_size = 0
if model_name == "resnet":
""" Resnet18
"""
model_ft = models.resnet18(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, num_classes)
input_size = 224
elif model_name == "alexnet":
""" Alexnet
"""
model_ft = models.alexnet(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.classifier[6].in_features
model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
input_size = 224
elif model_name == "vgg":
""" VGG11_bn
"""
model_ft = models.vgg11_bn(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.classifier[6].in_features
model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
input_size = 224
elif model_name == "squeezenet":
""" Squeezenet
"""
model_ft = models.squeezenet1_0(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1))
model_ft.num_classes = num_classes
input_size = 224
elif model_name == "densenet":
""" Densenet
"""
model_ft = models.densenet121(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.classifier.in_features
model_ft.classifier = nn.Linear(num_ftrs, num_classes)
input_size = 224
elif model_name == "inception":
""" Inception v3
Be careful, expects (299,299) sized images and has auxiliary output
"""
model_ft = models.inception_v3(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
# Handle the auxilary net
num_ftrs = model_ft.AuxLogits.fc.in_features
model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes)
# Handle the primary net
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs,num_classes)
input_size = 299
else:
print("Invalid model name, exiting...")
exit()
return model_ft, input_size
if __name__ == '__main__':
data_dir = './Dataset/hymenoptera_data'
model_name = 'squeezenet'
num_classes = 2
batch_size = 8
num_epochs = 15
feature_extract = True
# Detect if we have a GPU available
device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu")
# Initialize the model for this run
model_ft, input_size = initialize_model(model_name, num_classes,
feature_extract, use_pretrained=True)
# Send the model to GPU
model_ft = model_ft.to(device)
# Data
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize(input_size),
transforms.CenterCrop(input_size),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
print("Initializing Datasets and Dataloaders...")
# Create training and validation datasets
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
data_transforms[x]) for x in ['train', 'val']}
# Create training and validation dataloaders
dataloaders_dict = {x: torch.utils.data.DataLoader(image_datasets[x],
batch_size=batch_size, shuffle=True, num_workers=4) for x in ['train', 'val']}
# Gather the parameters to be optimized/updated in this run.
params_to_update = model_ft.parameters()
print("Params to learn:")
if feature_extract:
params_to_update = []
for name,param in model_ft.named_parameters():
if param.requires_grad == True:
params_to_update.append(param)
print("\t",name)
else:
for name,param in model_ft.named_parameters():
if param.requires_grad == True:
print("\t",name)
# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(params_to_update, lr=0.001, momentum=0.9)
# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
# Train and evaluate
model_ft, hist = train_model(model_ft, dataloaders_dict, criterion,
optimizer_ft, num_epochs=num_epochs, is_inception=(model_name=="inception"))
# Initialize the non-pretrained version of the model used for this run
scratch_model,_ = initialize_model(model_name, num_classes, feature_extract=False, use_pretrained=False)
scratch_model = scratch_model.to(device)
scratch_optimizer = optim.SGD(scratch_model.parameters(), lr=0.001, momentum=0.9)
scratch_criterion = nn.CrossEntropyLoss()
_,scratch_hist = train_model(scratch_model, dataloaders_dict, scratch_criterion, scratch_optimizer, num_epochs=num_epochs, is_inception=(model_name=="inception"))
# Plot the training curves of validation accuracy vs. number
# of training epochs for the transfer learning method and
# the model trained from scratch
ohist = []
shist = []
ohist = [h.cpu().numpy() for h in hist]
shist = [h.cpu().numpy() for h in scratch_hist]
plt.title("Validation Accuracy vs. Number of Training Epochs")
plt.xlabel("Training Epochs")
plt.ylabel("Validation Accuracy")
plt.plot(range(1,num_epochs+1),ohist,label="Pretrained")
plt.plot(range(1,num_epochs+1),shist,label="Scratch")
plt.ylim((0,1.))
plt.xticks(np.arange(1, num_epochs+1, 1.0))
plt.legend()
plt.show()
plt.savefig('Compare.png')
特征图 > 变换矩阵
import torch, torchvision
import numpy as np
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
import matplotlib.pyplot as plt
import torchvision.datasets as datasets
import torchvision.transforms as transforms
device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu")
# Data
# Training dataset
train_loader = torch.utils.data.DataLoader(
datasets.MNIST(root='.', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])), batch_size=64, shuffle=True, num_workers=4)
# Test dataset
test_loader = torch.utils.data.DataLoader(
datasets.MNIST(root='.', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])), batch_size=64, shuffle=True, num_workers=4)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.conv2_drop = nn.Dropout2d() # 0.5
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
# Spatial transformer localization-network
self.localization = nn.Sequential(
nn.Conv2d(1, 8, kernel_size=7), # 22
nn.MaxPool2d(2, stride=2), # 11
nn.ReLU(True), #
nn.Conv2d(8, 10, kernel_size=5),# 7
nn.MaxPool2d(2, stride=2), # 3
nn.ReLU(True)
)
# Regressor for the 3 * 2 affine matrix
self.fc_loc = nn.Sequential(
nn.Linear(10 * 3 * 3, 32),
nn.ReLU(True),
nn.Linear(32, 3 * 2)
)
# Initialize the weights/bias with identity transformation
self.fc_loc[2].weight.data.zero_()
self.fc_loc[2].bias.data.copy_(torch.tensor([1, 0, 0, 0, 1, 0], dtype=torch.float))
# Spatial transformer network forward function
def stn(self, x):
xs = self.localization(x)
xs = xs.view(-1, 10 * 3 * 3)
theta = self.fc_loc(xs)
theta = theta.view(-1, 2, 3)
grid = F.affine_grid(theta, x.size()) # theta 28x28
x = F.grid_sample(x, grid) # resample
return x
def forward(self, x):
# transform the input
x = self.stn(x)
# Perform the usual forward pass
# conv-pool-conv-drop-pool-fc-relu-drop-fc
x = F.relu(F.max_pool2d(self.conv1(x), 2)) # 24 -> 12
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2)) # 8 -> 4
x = x.view(-1, 320) # 4x4x20
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def convert_image_np(inp):
"""Convert a Tensor to numpy image."""
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)
return inp
def visualize_stn():
with torch.no_grad():
# Get a batch of training data
data = next(iter(test_loader))[0].to(device)
input_tensor = data.cpu()
transformed_input_tensor = model.stn(data).cpu()
in_grid = convert_image_np(
torchvision.utils.make_grid(input_tensor))
out_grid = convert_image_np(
torchvision.utils.make_grid(transformed_input_tensor))
# Plot the results side-by-side
f, axarr = plt.subplots(1, 2)
axarr[0].imshow(in_grid)
axarr[0].set_title('Dataset Images')
axarr[1].imshow(out_grid)
axarr[1].set_title('Transformed Images')
def train(epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % 500 == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
def test():
with torch.no_grad():
model.eval()
test_loss = 0
correct = 0
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
# sum up batch loss
test_loss += F.nll_loss(output, target, size_average=False).item()
# get the index of the max log-probability
pred = output.max(1, keepdim=True)[1]
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'
.format(test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
# Model + Optimizer
model = Net().to(device)
optimizer = optim.SGD(model.parameters(), lr=0.01)
for epoch in range(1, 20+1):
train(epoch)
test()
visualize_stn()
plt.ioff()
plt.show()
plt.savefig('stn_vis.png')
from __future__ import print_function
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from PIL import Image
import matplotlib.pyplot as plt
import torchvision.transforms as transforms
import torchvision.models as models
import copy
def image_loader(image_name):
image = Image.open(image_name)
# fake batch dimension required to fit network's input dimensions
image = loader(image).unsqueeze(0)
return image.to(device, torch.float)
unloader = transforms.ToPILImage() # reconvert into PIL image
def imshow(tensor, title=None):
image = tensor.cpu().clone() # we clone the tensor to not do changes on it
image = image.squeeze(0) # remove the fake batch dimension
image = unloader(image)
plt.imshow(image)
if title is not None:
plt.title(title)
plt.pause(0.001) # pause a bit so that plots are updated
class ContentLoss(nn.Module):
# 尽管此模块名为ContentLoss,但它不是真正的PyTorch损失函数。
# 如果要将内容损失定义为PyTorch损失函数,
# 则必须创建一个PyTorch autograd函数以在backward方法中手动重新计算/实现梯度。
def __init__(self, target,):
super(ContentLoss, self).__init__()
# we 'detach' the target content from the tree used
# to dynamically compute the gradient: this is a stated value,
# not a variable. Otherwise the forward method of the criterion
# will throw an error.
self.target = target.detach()
def forward(self, input):
self.loss = F.mse_loss(input, self.target)
return input
def gram_matrix(input):
a, b, c, d = input.size() # a=batch size(=1)
# b=number of feature maps
# (c,d)=dimensions of a f. map (N=c*d)
features = input.view(a * b, c * d) # resise F_XL into \hat F_XL
G = torch.mm(features, features.t()) # compute the gram product
# we 'normalize' the values of the gram matrix
# by dividing by the number of element in each feature maps.
return G.div(a * b * c * d)
class StyleLoss(nn.Module):
def __init__(self, target_feature):
super(StyleLoss, self).__init__()
self.target = gram_matrix(target_feature).detach()
def forward(self, input):
G = gram_matrix(input)
self.loss = F.mse_loss(G, self.target)
return input
# create a module to normalize input image so we can easily put it in a
# nn.Sequential
class Normalization(nn.Module):
def __init__(self, mean, std):
super(Normalization, self).__init__()
# .view the mean and std to make them [C x 1 x 1] so that they can
# directly work with image Tensor of shape [B x C x H x W].
# B is batch size. C is number of channels. H is height and W is width.
self.mean = torch.tensor(mean).view(-1, 1, 1)
self.std = torch.tensor(std).view(-1, 1, 1)
def forward(self, img):
# normalize img
return (img - self.mean) / self.std
# desired depth layers to compute style/content losses :
content_layers_default = ['conv_4']
style_layers_default = ['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']
def get_style_model_and_losses(cnn, normalization_mean, normalization_std,
style_img, content_img,
content_layers=content_layers_default,
style_layers=style_layers_default):
cnn = copy.deepcopy(cnn)
# normalization module
normalization = Normalization(normalization_mean, normalization_std).to(device)
# just in order to have an iterable access to or list of content/syle
# losses
content_losses = []
style_losses = []
# assuming that cnn is a nn.Sequential, so we make a new nn.Sequential
# to put in modules that are supposed to be activated sequentially
model = nn.Sequential(normalization)
i = 0 # increment every time we see a conv
for layer in cnn.children():
if isinstance(layer, nn.Conv2d):
i += 1
name = 'conv_{}'.format(i)
elif isinstance(layer, nn.ReLU):
name = 'relu_{}'.format(i)
# The in-place version doesn't play very nicely with the ContentLoss
# and StyleLoss we insert below. So we replace with out-of-place
# ones here.
layer = nn.ReLU(inplace=False)
elif isinstance(layer, nn.MaxPool2d):
name = 'pool_{}'.format(i)
elif isinstance(layer, nn.BatchNorm2d):
name = 'bn_{}'.format(i)
else:
raise RuntimeError('Unrecognized layer: {}'.format(layer.__class__.__name__))
model.add_module(name, layer)
if name in content_layers:
# add content loss:
target = model(content_img).detach()
content_loss = ContentLoss(target)
model.add_module("content_loss_{}".format(i), content_loss)
content_losses.append(content_loss)
if name in style_layers:
# add style loss:
target_feature = model(style_img).detach()
style_loss = StyleLoss(target_feature)
model.add_module("style_loss_{}".format(i), style_loss)
style_losses.append(style_loss)
# now we trim off the layers after the last content and style losses
for i in range(len(model) - 1, -1, -1):
if isinstance(model[i], ContentLoss) or isinstance(model[i], StyleLoss):
break
model = model[:(i + 1)]
return model, style_losses, content_losses
def get_input_optimizer(input_img):
# this line to show that input is a parameter that requires a gradient
optimizer = optim.LBFGS([input_img.requires_grad_()])
return optimizer
def run_style_transfer(cnn, normalization_mean, normalization_std,
content_img, style_img, input_img, num_steps=300,
style_weight=1000000, content_weight=1):
"""Run the style transfer."""
print('Building the style transfer model..')
model, style_losses, content_losses = get_style_model_and_losses(cnn,
normalization_mean, normalization_std, style_img, content_img)
optimizer = get_input_optimizer(input_img)
print('Optimizing..')
run = [0]
while run[0] <= num_steps:
def closure():
# correct the values of updated input image
input_img.data.clamp_(0, 1)
optimizer.zero_grad()
model(input_img)
style_score = 0
content_score = 0
for sl in style_losses:
style_score += sl.loss
for cl in content_losses:
content_score += cl.loss
style_score *= style_weight
content_score *= content_weight
loss = style_score + content_score
loss.backward() # loss得bp!!!
run[0] += 1
if run[0] % 50 == 0:
print("run {}:".format(run))
print('Style Loss : {:4f} Content Loss: {:4f}'.format(
style_score.item(), content_score.item()))
print()
return style_score + content_score
optimizer.step(closure)
# a last correction...
input_img.data.clamp_(0, 1)
return input_img
if __name__ == '__main__':
#1 Prepare
device = torch.device('cuda:1' if torch.cuda.is_available() else 'cpu')
# desired size of the output image
imsize = 512 if torch.cuda.is_available() else 128 # use small size if no gpu
loader = transforms.Compose([
transforms.Resize(imsize), # scale imported image
transforms.ToTensor()]) # transform it into a torch tensor
style_img = image_loader("./Dataset/neural-style/picasso.jpg")
content_img = image_loader("./Dataset/neural-style/dancing.jpg")
assert style_img.size() == content_img.size(), \
"we need to import style and content images of the same size"
#2 Model
cnn = models.vgg19(pretrained=True).features.to(device).eval()
cnn_normalization_mean = torch.tensor([0.485, 0.456, 0.406]).to(device)
cnn_normalization_std = torch.tensor([0.229, 0.224, 0.225]).to(device)
#3 Input: 使用内容图像或白噪声的副本
input_img = content_img.clone()
# input_img = torch.randn(content_img.data.size(), device=device)
#4 Train
output = run_style_transfer(cnn, cnn_normalization_mean, cnn_normalization_std,
content_img, style_img, input_img)
plt.figure()
imshow(output, title='Output Image')
plt.ioff()
plt.show()
plt.savefig('transferImg.png')
TODO
3x64x64
的图像,输出是输入图像来自实际数据的概率TODO
from setuptools import setup, Extension
from torch.utils import cpp_extension
setup(name='lltm_cpp',
ext_modules=[cpp_extension.CppExtension('lltm_cpp', ['lltm.cpp'])],
cmdclass={'build_ext': cpp_extension.BuildExtension})
#include
#include
torch::Tensor d_sigmoid(torch::Tensor z) {
auto s = torch::sigmoid(z);
return (1 - s) * s;
}
torch::Tensor
。它的完整 API 可以在 这里查到。注意,我们可以包含 或任何其他 C 或 C++ 头文件 – 我们可以使用 C++11 的全部功能#include
std::vector<at::Tensor> lltm_forward(
torch::Tensor input,
torch::Tensor weights,
torch::Tensor bias,
torch::Tensor old_h,
torch::Tensor old_cell) {
auto X = torch::cat({old_h, input}, /*dim=*/1);
auto gate_weights = torch::addmm(bias, X, weights.transpose(0, 1));
auto gates = gate_weights.chunk(3, /*dim=*/1);
auto input_gate = torch::sigmoid(gates[0]);
auto output_gate = torch::sigmoid(gates[1]);
auto candidate_cell = torch::elu(gates[2], /*alpha=*/1.0);
auto new_cell = old_cell + candidate_cell * input_gate;
auto new_h = torch::tanh(new_cell) * output_gate;
return {new_h,
new_cell,
input_gate,
output_gate,
candidate_cell,
X,
gate_weights};
}
#include
std::vector<at::Tensor> lltm_forward(
torch::Tensor input,
torch::Tensor weights,
torch::Tensor bias,
torch::Tensor old_h,
torch::Tensor old_cell) {
auto X = torch::cat({old_h, input}, /*dim=*/1);
auto gate_weights = torch::addmm(bias, X, weights.transpose(0, 1));
auto gates = gate_weights.chunk(3, /*dim=*/1);
auto input_gate = torch::sigmoid(gates[0]);
auto output_gate = torch::sigmoid(gates[1]);
auto candidate_cell = torch::elu(gates[2], /*alpha=*/1.0);
auto new_cell = old_cell + candidate_cell * input_gate;
auto new_h = torch::tanh(new_cell) * output_gate;
return {new_h,
new_cell,
input_gate,
output_gate,
candidate_cell,
X,
gate_weights};
}
PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
m.def("forward", &lltm_forward, "LLTM forward");
m.def("backward", &lltm_backward, "LLTM backward");
}
#include
#include