【腾讯云 HAI域探秘】HAI推动Pytorch2.0 AI框架新时代

mkdir dataset-fashion-mnist #创建文件夹 dataset-fashion-mnist
cd dataset-fashion-mnist
wget https://mirror.tuna.tsinghua.edu.cn/raspberry-pi-os/raspbian/pool/main/d/dataset-fashion-mnist/dataset-fashion-mnist_0.0~git20200523.55506a9.orig.tar.xz #下载数据集
tar -xf dataset-fashion-mnist_0.0~git20200523.55506a9.orig.tar.xz --strip-components=1
cd data && mkdir FashionMNIST && mkdir FashionMNIST/raw 

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor

# 加载本地训练数据
training_data = datasets.FashionMNIST(
    root="/root/dataset-fashion-mnist/data",
    train=True,
    download=True,
    transform=ToTensor(),
)
# 加载本地测试数据
test_data = datasets.FashionMNIST(
    root="/root/dataset-fashion-mnist/data",
    train=False,
    download=True,
    transform=ToTensor(),
)

pip config set global.index-url http://mirrors.cloud.tencent.com/pypi/simple
pip config set global.trusted-host mirrors.cloud.tencent.com

pip install matplotlib

import matplotlib.pyplot as plt

labels_map = {
    0: "T-Shirt",
    1: "Trouser",
    2: "Pullover",
    3: "Dress",
    4: "Coat",
    5: "Sandal",
    6: "Shirt",
    7: "Sneaker",
    8: "Bag",
    9: "Ankle Boot",
}
figure = plt.figure(figsize=(8, 8))
cols, rows = 3, 3
for i in range(1, cols * rows + 1):
    sample_idx = torch.randint(len(training_data), size=(1,)).item()
    img, label = training_data[sample_idx]
    figure.add_subplot(rows, cols, i)
    plt.title(labels_map[label])
    plt.axis("off")
    plt.imshow(img.squeeze(), cmap="gray")
plt.show()

batch_size = 64

# 创建 dataloader
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)

for X, y in test_dataloader:
    print(f"Shape of X [N, C, H, W]: {X.shape}")
    print(f"Shape of y: {y.shape} {y.dtype}")
    break

# 获取用于训练的 cpu 或 gpu 设备
device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
print(f"Using {device} device")

# 定义模型
class NeuralNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10)
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

model = NeuralNetwork().to(device)
print(model)

loss_fn = nn.CrossEntropyLoss() 
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)

        # 计算预测误差
        pred = model(X)
        loss = loss_fn(pred, y)

        # 反向传播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            loss, current = loss.item(), (batch + 1) * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")

epochs = 5
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train(train_dataloader, model, loss_fn, optimizer)
    test(test_dataloader, model, loss_fn)
print("Done!")

torch.save(model.state_dict(), "/root/model.pth")
print("Saved PyTorch Model State to model.pth")

model = NeuralNetwork()
model.load_state_dict(torch.load("/root/model.pth"))

classes = [
    "包",
    "上衣",
    "套头衫",
    "连衣裙",
    "外套",
    "凉鞋",
    "衬衫",
    "运动鞋",
    "包",
    "短靴",
] #定义了一个包含类别标签的 classes 列表

model.eval() #将 PyTorch 模型设置为评估模式
x, y = test_data[1][0], test_data[1][1]#测试数据 test_data 中获取样本 分别为图像数据和其真实标签
with torch.no_grad():
    pred = model(x)
    predicted, actual = classes[pred[0].argmax(0)], classes[y]#选择具有最高概率的类别索引
    print(f'Predicted: "{predicted}", Actual: "{actual}"') #模型的预测结果 predicted 与真实标签 actual 进行比较，并使用 print 函数输出这两个值。
#输出图片信息
# 将 x 转换回图像格式
image = x.numpy().transpose(1, 2, 0)
# 显示图像
plt.figure(figsize=(4, 4))
plt.imshow(image)
# 设置中文标题
print('预测结果: "{predicted}", 实际结果: "{actual}"'.format(predicted=predicted, actual=actual))
plt.axis('off')
plt.show()

cd /root
wget https://gitee.com/mmliujc/tencent_gpu/raw/master/data.zip
unzip data

from __future__ import unicode_literals, print_function, division
from io import open
import glob
import os
import unicodedata
import string

all_letters = string.ascii_letters + " .,;'-"
n_letters = len(all_letters) + 1 # Plus EOS marker

def findFiles(path): return glob.glob(path)

# Turn a Unicode string to plain ASCII, thanks to https://stackoverflow.com/a/518232/2809427
def unicodeToAscii(s):
    return ''.join(
        c for c in unicodedata.normalize('NFD', s)
        if unicodedata.category(c) != 'Mn'
        and c in all_letters
    )

# Read a file and split into lines
def readLines(filename):
    with open(filename, encoding='utf-8') as some_file:
        return [unicodeToAscii(line.strip()) for line in some_file]

# Build the category_lines dictionary, a list of lines per category
category_lines = {}
all_categories = []
for filename in findFiles('/root/data/names/*.txt'):
    category = os.path.splitext(os.path.basename(filename))[0]
    all_categories.append(category)
    lines = readLines(filename)
    category_lines[category] = lines

n_categories = len(all_categories)

if n_categories == 0:
    raise RuntimeError('Data not found. Make sure that you downloaded data '
        'from https://download.pytorch.org/tutorial/data.zip and extract it to '
        'the current directory.')

print('# categories:', n_categories, all_categories)
print(unicodeToAscii("O'Néàl"))

import torch
import torch.nn as nn

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size

        self.i2h = nn.Linear(n_categories + input_size + hidden_size, hidden_size)
        self.i2o = nn.Linear(n_categories + input_size + hidden_size, output_size)
        self.o2o = nn.Linear(hidden_size + output_size, output_size)
        self.dropout = nn.Dropout(0.1)
        self.softmax = nn.LogSoftmax(dim=1)

    def forward(self, category, input, hidden):
        input_combined = torch.cat((category, input, hidden), 1)
        hidden = self.i2h(input_combined)
        output = self.i2o(input_combined)
        output_combined = torch.cat((hidden, output), 1)
        output = self.o2o(output_combined)
        output = self.dropout(output)
        output = self.softmax(output)
        return output, hidden

    def initHidden(self):
        return torch.zeros(1, self.hidden_size)

import random

# Random item from a list
def randomChoice(l):
    return l[random.randint(0, len(l) - 1)]

# Get a random category and random line from that category
def randomTrainingPair():
    category = randomChoice(all_categories)
    line = randomChoice(category_lines[category])
    return category, line

# One-hot vector for category
def categoryTensor(category):
    li = all_categories.index(category)
    tensor = torch.zeros(1, n_categories)
    tensor[0][li] = 1
    return tensor

# One-hot matrix of first to last letters (not including EOS) for input
def inputTensor(line):
    tensor = torch.zeros(len(line), 1, n_letters)
    for li in range(len(line)):
        letter = line[li]
        tensor[li][0][all_letters.find(letter)] = 1
    return tensor

# ``LongTensor`` of second letter to end (EOS) for target
def targetTensor(line):
    letter_indexes = [all_letters.find(line[li]) for li in range(1, len(line))]
    letter_indexes.append(n_letters - 1) # EOS
    return torch.LongTensor(letter_indexes)

# Make category, input, and target tensors from a random category, line pair
def randomTrainingExample():
    category, line = randomTrainingPair()
    category_tensor = categoryTensor(category)
    input_line_tensor = inputTensor(line)
    target_line_tensor = targetTensor(line)
    return category_tensor, input_line_tensor, target_line_tensor

criterion = nn.NLLLoss()

learning_rate = 0.0005

def train(category_tensor, input_line_tensor, target_line_tensor):
    target_line_tensor.unsqueeze_(-1)
    hidden = rnn.initHidden()

    rnn.zero_grad()

    loss = 0

    for i in range(input_line_tensor.size(0)):
        output, hidden = rnn(category_tensor, input_line_tensor[i], hidden)
        l = criterion(output, target_line_tensor[i])
        loss += l

    loss.backward()

    for p in rnn.parameters():
        p.data.add_(p.grad.data, alpha=-learning_rate)

    return output, loss.item() / input_line_tensor.size(0)

import time
import math

def timeSince(since):
    now = time.time()
    s = now - since
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)

rnn = RNN(n_letters, 128, n_letters)

n_iters = 100000
print_every = 5000
plot_every = 500
all_losses = []
total_loss = 0 # Reset every ``plot_every`` ``iters``

start = time.time()

for iter in range(1, n_iters + 1):
    output, loss = train(*randomTrainingExample())
    total_loss += loss

    if iter % print_every == 0:
        print('%s (%d %d%%) %.4f' % (timeSince(start), iter, iter / n_iters * 100, loss))

    if iter % plot_every == 0:
        all_losses.append(total_loss / plot_every)
        total_loss = 0

import matplotlib.pyplot as plt

plt.figure()
plt.plot(all_losses)

max_length = 20

# Sample from a category and starting letter
def sample(category, start_letter='A'):
    with torch.no_grad():  # no need to track history in sampling
        category_tensor = categoryTensor(category)
        input = inputTensor(start_letter)
        hidden = rnn.initHidden()

        output_name = start_letter

        for i in range(max_length):
            output, hidden = rnn(category_tensor, input[0], hidden)
            topv, topi = output.topk(1)
            topi = topi[0][0]
            if topi == n_letters - 1:
                break
            else:
                letter = all_letters[topi]
                output_name += letter
            input = inputTensor(letter)

        return output_name

# Get multiple samples from one category and multiple starting letters
def samples(category, start_letters='ABC'):
    for start_letter in start_letters:
        print(sample(category, start_letter))

samples('Russian', 'RUS')

samples('German', 'GER')

samples('Spanish', 'SPA')

samples('Chinese', 'CHI')

git clone https://gitee.com/ai-toys/RobustVideoMatting
# 输入你的gitee账号密码
cd RobustVideoMatting

ssh-keygen -t ed25519 -C ""  #双引号里面填ssh key，一般填自己邮箱
# 回车一直默认即可，会在家目录生成 ~/.ssh 文件夹，存放密钥信息
cat ~/.ssh/id_ed25519.pub  # 查看生成的公钥

git clone git@gitee.com:ai-toys/RobustVideoMatting 
# 输入yes 回车确认

pip install -r requirements_inference.txt

wget https://gitee.com/mmliujc/tencent_gpu/raw/master/rvm_res.zip
unzip rvm_res.zip

import torch
import base64


from model import MattingNetwork
from inference import convert_video

model = MattingNetwork('mobilenetv3').eval().cuda()  # 或 "resnet50"
model.load_state_dict(torch.load('rvm_mobilenetv3.pth'))


convert_video(
    model,                           # 模型，可以加载到任何设备（cpu 或 cuda）
    input_source='1917.mp4',        # 视频文件，或图片序列文件夹
    output_type='video',             # 可选 "video"（视频）或 "png_sequence"（PNG 序列）
    output_composition='output/com.mp4',    # 若导出视频，提供文件路径。若导出 PNG 序列，提供文件夹路径
    output_alpha="output/pha.mp4",          # [可选项] 输出透明度预测
    output_foreground="output/fgr.mp4",     # [可选项] 输出前景预测
    output_video_mbps=4,             # 若导出视频，提供视频码率
    downsample_ratio=None,           # 下采样比，可根据具体视频调节，或 None 选择自动
    seq_chunk=12,                    # 设置多帧并行计算
)

mkdir output
python test.py

import torch
import base64
from IPython.display import HTML

outpath = "com.mp4"
mp4 = open(outpath,'rb').read()
data_url = "data:video/mp4;base64," + base64.b64encode(mp4).decode()
HTML("""
<video width=400 controls>
      <source src="%s" type="video/mp4">
</video>
""" % data_url)