七月在線 課程：https://www.julyedu.com/course/getDetail/262

什么是關(guān)鍵點(diǎn)？

關(guān)鍵點(diǎn)定義：關(guān)鍵點(diǎn)也稱(chēng)為興趣點(diǎn)，它是2D圖像、3D點(diǎn)云或曲面模型上，可以通過(guò)定義檢測(cè)標(biāo)準(zhǔn)來(lái)獲取的具有穩(wěn)定性、區(qū)別性的點(diǎn)集。關(guān)鍵點(diǎn)檢測(cè)涉及同時(shí)檢測(cè)人和定位他們的關(guān)鍵點(diǎn)。關(guān)鍵點(diǎn)與興趣點(diǎn)相同。它們是空間位置或圖像中的點(diǎn)，它們定義了圖像中有趣或突出的內(nèi)容。它們對(duì)圖像旋轉(zhuǎn)、收縮、平移、失真等是不變的。

關(guān)鍵點(diǎn)的意義？

加快后續(xù)識(shí)別、追蹤等數(shù)據(jù)的處理速度。

環(huán)境配置

nvidia GPU 配置：

https://docs.nvidia.com/deeplearning/cudnn/install-guide/index.html

code ： MNIST

MNIST實(shí)戰(zhàn)！

import torch from torchvision import datasets, transforms import matplotlib.pyplot as plt import os import torchvision import numpy as np from torch.autograd import Variable import random %matplotlib inlinetransform = transforms.Compose([ transforms.ToTensor(), transforms.Normalize([0.5], [0.5])])data_train = datasets.MNIST(root = "./data/",transform=transform,train = True,download = True)data_test = datasets.MNIST(root="./data/",transform = transform,train = False)data_loader_train = torch.utils.data.DataLoader(dataset=data_train,batch_size = 64,shuffle = True,num_workers=2)data_loader_test = torch.utils.data.DataLoader(dataset=data_test,batch_size = 64,shuffle = True,num_workers=2)images, labels = next(iter(data_loader_train)) img = torchvision.utils.make_grid(images)img = img.numpy().transpose(1,2,0) std = [0.5,0.5,0.5] mean = [0.5,0.5,0.5] img = img*std+mean print([labels[i] for i in range(64)]) plt.imshow(img)class Model(torch.nn.Module):def __init__(self):super(Model, self).__init__()self.conv1 = torch.nn.Sequential(torch.nn.Conv2d(1,64,kernel_size=3,stride=1,padding=1),torch.nn.ReLU(),torch.nn.Conv2d(64,128,kernel_size=3,stride=1,padding=1),torch.nn.ReLU(),torch.nn.MaxPool2d(stride=2,kernel_size=2))self.dense = torch.nn.Sequential(torch.nn.Linear(14*14*128,1024),torch.nn.ReLU(),torch.nn.Dropout(p=0.5),torch.nn.Linear(1024, 10))def forward(self, x):x = self.conv1(x)x = x.view(-1, 14*14*128)x = self.dense(x)return xcost = torch.nn.CrossEntropyLoss() optimizer = torch.optim.Adam(model.parameters()) n_epochs = 5for epoch in range(n_epochs):running_loss = 0.0running_correct = 0print("Epoch {}/{}".format(epoch, n_epochs))print("-"*10)for data in data_loader_train:X_train, y_train = dataX_train, y_train = Variable(X_train), Variable(y_train)outputs = model(X_train)_,pred = torch.max(outputs.data, 1)optimizer.zero_grad()loss = cost(outputs, y_train)loss.backward()optimizer.step() #進(jìn)行單次優(yōu)化running_loss += loss.datarunning_correct += torch.sum(pred == y_train.data)testing_correct = 0for data in data_loader_test:X_test, y_test = dataX_test, y_test = Variable(X_test), Variable(y_test)outputs = model(X_test)_, pred = torch.max(outputs.data, 1)testing_correct += torch.sum(pred == y_test.data)print("Loss is:{:.4f}, Train Accuracy is:{:.4f}%, Test Accuracy is:{:.4f}".format(running_loss/len(data_train),100*running_correct/len(data_train),100*testing_correct/len(data_test))) torch.save(model.state_dict(), "model_parameter.pkl")

reference resources

• https://paperswithcode.com/sota/keypoint-detection-on-coco-test-dev

總結(jié)

以上是生活随笔為你收集整理的七月在线 《关键点检测概览与环境配置》的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。