PyTorch 2.2 中文官方教程（四）（2）

# imports
import matplotlib.pyplot as plt
import numpy as np
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
# transforms
transform = transforms.Compose(
    [transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))])
# datasets
trainset = torchvision.datasets.FashionMNIST('./data',
    download=True,
    train=True,
    transform=transform)
testset = torchvision.datasets.FashionMNIST('./data',
    download=True,
    train=False,
    transform=transform)
# dataloaders
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                        shuffle=True, num_workers=2)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                        shuffle=False, num_workers=2)
# constant for classes
classes = ('T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
        'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle Boot')
# helper function to show an image
# (used in the `plot_classes_preds` function below)
def matplotlib_imshow(img, one_channel=False):
    if one_channel:
        img = img.mean(dim=0)
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    if one_channel:
        plt.imshow(npimg, cmap="Greys")
    else:
        plt.imshow(np.transpose(npimg, (1, 2, 0))) 

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 4 * 4, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)
    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 4 * 4)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
net = Net() 

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) 

from torch.utils.tensorboard import SummaryWriter
# default `log_dir` is "runs" - we'll be more specific here
writer = SummaryWriter('runs/fashion_mnist_experiment_1') 

# get some random training images
dataiter = iter(trainloader)
images, labels = next(dataiter)
# create grid of images
img_grid = torchvision.utils.make_grid(images)
# show images
matplotlib_imshow(img_grid, one_channel=True)
# write to tensorboard
writer.add_image('four_fashion_mnist_images', img_grid) 

tensorboard --logdir=runs 

writer.add_graph(net, images)
writer.close() 

# helper function
def select_n_random(data, labels, n=100):
  '''
 Selects n random datapoints and their corresponding labels from a dataset
 '''
    assert len(data) == len(labels)
    perm = torch.randperm(len(data))
    return data[perm][:n], labels[perm][:n]
# select random images and their target indices
images, labels = select_n_random(trainset.data, trainset.targets)
# get the class labels for each image
class_labels = [classes[lab] for lab in labels]
# log embeddings
features = images.view(-1, 28 * 28)
writer.add_embedding(features,
                    metadata=class_labels,
                    label_img=images.unsqueeze(1))
writer.close() 

# helper functions
def images_to_probs(net, images):
  '''
 Generates predictions and corresponding probabilities from a trained
 network and a list of images
 '''
    output = net(images)
    # convert output probabilities to predicted class
    _, preds_tensor = torch.max(output, 1)
    preds = np.squeeze(preds_tensor.numpy())
    return preds, [F.softmax(el, dim=0)[i].item() for i, el in zip(preds, output)]
def plot_classes_preds(net, images, labels):
  '''
 Generates matplotlib Figure using a trained network, along with images
 and labels from a batch, that shows the network's top prediction along
 with its probability, alongside the actual label, coloring this
 information based on whether the prediction was correct or not.
 Uses the "images_to_probs" function.
 '''
    preds, probs = images_to_probs(net, images)
    # plot the images in the batch, along with predicted and true labels
    fig = plt.figure(figsize=(12, 48))
    for idx in np.arange(4):
        ax = fig.add_subplot(1, 4, idx+1, xticks=[], yticks=[])
        matplotlib_imshow(images[idx], one_channel=True)
        ax.set_title("{0}, {1:.1f}%\n(label: {2})".format(
            classes[preds[idx]],
            probs[idx] * 100.0,
            classes[labels[idx]]),
                    color=("green" if preds[idx]==labels[idx].item() else "red"))
    return fig 

running_loss = 0.0
for epoch in range(1):  # loop over the dataset multiple times
    for i, data in enumerate(trainloader, 0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data
        # zero the parameter gradients
        optimizer.zero_grad()
        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if i % 1000 == 999:    # every 1000 mini-batches...
            # ...log the running loss
            writer.add_scalar('training loss',
                            running_loss / 1000,
                            epoch * len(trainloader) + i)
            # ...log a Matplotlib Figure showing the model's predictions on a
            # random mini-batch
            writer.add_figure('predictions vs. actuals',
                            plot_classes_preds(net, inputs, labels),
                            global_step=epoch * len(trainloader) + i)
            running_loss = 0.0
print('Finished Training') 

# 1\. gets the probability predictions in a test_size x num_classes Tensor
# 2\. gets the preds in a test_size Tensor
# takes ~10 seconds to run
class_probs = []
class_label = []
with torch.no_grad():
    for data in testloader:
        images, labels = data
        output = net(images)
        class_probs_batch = [F.softmax(el, dim=0) for el in output]
        class_probs.append(class_probs_batch)
        class_label.append(labels)
test_probs = torch.cat([torch.stack(batch) for batch in class_probs])
test_label = torch.cat(class_label)
# helper function
def add_pr_curve_tensorboard(class_index, test_probs, test_label, global_step=0):
  '''
 Takes in a "class_index" from 0 to 9 and plots the corresponding
 precision-recall curve
 '''
    tensorboard_truth = test_label == class_index
    tensorboard_probs = test_probs[:, class_index]
    writer.add_pr_curve(classes[class_index],
                        tensorboard_truth,
                        tensorboard_probs,
                        global_step=global_step)
    writer.close()
# plot all the pr curves
for i in range(len(classes)):
    add_pr_curve_tensorboard(i, test_probs, test_label) 

wget https://www.cis.upenn.edu/~jshi/ped_html/PennFudanPed.zip -P data
cd data && unzip PennFudanPed.zip 

PennFudanPed/
  PedMasks/
    FudanPed00001_mask.png
    FudanPed00002_mask.png
    FudanPed00003_mask.png
    FudanPed00004_mask.png
    ...
  PNGImages/
    FudanPed00001.png
    FudanPed00002.png
    FudanPed00003.png
    FudanPed00004.png 

import matplotlib.pyplot as plt
from torchvision.io import read_image
image = read_image("data/PennFudanPed/PNGImages/FudanPed00046.png")
mask = read_image("data/PennFudanPed/PedMasks/FudanPed00046_mask.png")
plt.figure(figsize=(16, 8))
plt.subplot(121)
plt.title("Image")
plt.imshow(image.permute(1, 2, 0))
plt.subplot(122)
plt.title("Mask")
plt.imshow(mask.permute(1, 2, 0)) 

<matplotlib.image.AxesImage object at 0x7f489920ffd0> 

import os
import torch
from torchvision.io import read_image
from torchvision.ops.boxes import masks_to_boxes
from torchvision import tv_tensors
from torchvision.transforms.v2 import functional as F
class PennFudanDataset(torch.utils.data.Dataset):
    def __init__(self, root, transforms):
        self.root = root
        self.transforms = transforms
        # load all image files, sorting them to
        # ensure that they are aligned
        self.imgs = list(sorted(os.listdir(os.path.join(root, "PNGImages"))))
        self.masks = list(sorted(os.listdir(os.path.join(root, "PedMasks"))))
    def __getitem__(self, idx):
        # load images and masks
        img_path = os.path.join(self.root, "PNGImages", self.imgs[idx])
        mask_path = os.path.join(self.root, "PedMasks", self.masks[idx])
        img = read_image(img_path)
        mask = read_image(mask_path)
        # instances are encoded as different colors
        obj_ids = torch.unique(mask)
        # first id is the background, so remove it
        obj_ids = obj_ids[1:]
        num_objs = len(obj_ids)
        # split the color-encoded mask into a set
        # of binary masks
        masks = (mask == obj_ids[:, None, None]).to(dtype=torch.uint8)
        # get bounding box coordinates for each mask
        boxes = masks_to_boxes(masks)
        # there is only one class
        labels = torch.ones((num_objs,), dtype=torch.int64)
        image_id = idx
        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])
        # suppose all instances are not crowd
        iscrowd = torch.zeros((num_objs,), dtype=torch.int64)
        # Wrap sample and targets into torchvision tv_tensors:
        img = tv_tensors.Image(img)
        target = {}
        target["boxes"] = tv_tensors.BoundingBoxes(boxes, format="XYXY", canvas_size=F.get_size(img))
        target["masks"] = tv_tensors.Mask(masks)
        target["labels"] = labels
        target["image_id"] = image_id
        target["area"] = area
        target["iscrowd"] = iscrowd
        if self.transforms is not None:
            img, target = self.transforms(img, target)
        return img, target
    def __len__(self):
        return len(self.imgs)