1. Prospects
Recently, I have been investigating pedestrian attribute recognition. There are many papers on pedestrian attribute recognition. After reading many papers, I wrote an independent project dedicated to pedestrian attribute recognition.
The code in the project mainly refers to two papers, the paper corresponding to ResNest and the paper corresponding to Bag of Tricks for Image Classification.
The backbone network uses the strongest improved version of ResNet: ResNest50. Please refer to my previous blog for detailed papers .
The training skills mainly use the training skills in "Bag of Tricks for Image Classification with Convolutional Neural Networks". For detailed explanation, please refer to my column: Model Training Skills .
The training data uses the pedestrian attribute data set PA100K. For the introduction of PA100K, please refer to my blog .
2. Explanation of the training part of the code
A total of 10 attributes are trained, namely: gender, age, orientation, whether to wear a hat, whether to wear glasses, whether to have a handbag, whether to have a shoulder bag, whether to have a backpack, top type, and bottom type.
for epoch in range(1, args.e + 1):
if epoch > args.warm:
train_scheduler.step(epoch)
#training procedure
net.train()
for batch_index, (images, labels) in enumerate(train_dataloader):
if epoch <= args.warm:
warmup_scheduler.step()
images = images.cuda()
labels = labels.cuda()
optimizer.zero_grad()
predicts = net(images)
loss_gender = cross_entropy(predicts[0], labels[:, 0].long())
loss_age = cross_entropy(predicts[1], labels[:, 1].long())
loss_orientation = cross_entropy(predicts[2], labels[:, 2].long())
loss_hat = cross_entropy(predicts[3], labels[:, 3].long())
loss_glasses = cross_entropy(predicts[4], labels[:, 4].long())
loss_handBag = cross_entropy(predicts[5], labels[:, 5].long())
loss_shoulderBag = cross_entropy(predicts[6], labels[:, 6].long())
loss_backBag = cross_entropy(predicts[7], labels[:, 7].long())
loss_upClothing = cross_entropy(predicts[8], labels[:, 8].long())
loss_downClothing= cross_entropy(predicts[9], labels[:, 9].long())
loss = loss_gender + loss_age + loss_orientation + loss_hat + loss_glasses + loss_handBag + loss_shoulderBag + loss_backBag + loss_upClothing + loss_downClothing
loss.backward()
optimizer.step()
n_iter = (epoch - 1) * len(train_dataloader) + batch_index + 1
if batch_index % 10 == 0:
print('Training Epoch: {epoch} [{trained_samples}/{total_samples}]\tLoss: {:0.4f}\tLoss_gender: {:0.4f}\tLoss_age: {:0.4f}\tLoss_ori: {:0.4f}\tLoss_hat: {:0.4f}\tLoss_glasses: {:0.4f}\tLoss_handBag: {:0.4f}\t'.format(
loss.item(),
loss_gender.item(),
loss_age.item(),
loss_orientation.item(),
loss_hat.item(),
loss_glasses.item(),
loss_handBag.item(),
epoch=epoch,
trained_samples=batch_index * args.b + len(images),
total_samples=len(train_dataloader.dataset),
))
#visualization
visualize_lastlayer(writer, net, n_iter)
visualize_train_loss(writer, loss.item(), n_iter)
visualize_learning_rate(writer, optimizer.param_groups[0]['lr'], epoch)
visualize_param_hist(writer, net, epoch)
net.eval()
total_loss = 0
correct = np.zeros(10)
ignore = np.zeros(10)
print("=>test model")
for images, labels in tqdm(test_dataloader):
images = images.cuda()
labels = labels.cuda()
predicts = net(images)
for index in range(10):
_, preds = predicts[index].max(1)
ignore[index] += int((labels[:, index]==-1).sum())
correct[index] += preds.eq(labels[:, index]).sum().float()
loss = cross_entropy(predicts[index], labels[:, index].long())
total_loss += loss.item()
test_loss = total_loss / len(test_dataloader)
all_list = np.array([len(test_dataloader.dataset) for i in range(10)])-ignore
acc_list = correct / all_list
print(acc_list.tolist())The training process is as follows:
3. Explanation of test code
"""
author:guopei
"""
import os
import cv2
import torch
from torch.nn import DataParallel
import numpy as np
from PIL import Image,ImageDraw,ImageFont
import transforms
from models import resnest50
class Person_Attribute(object):
def __init__(self, weights="resnest50.pth"):
self.device = torch.device("cuda")
self.net = resnest50().to(self.device)
self.net = DataParallel(self.net)
self.weights = weights
self.net.load_state_dict(torch.load(self.weights))
TRAIN_MEAN = [0.485, 0.499, 0.432]
TRAIN_STD = [0.232, 0.227, 0.266]
self.transforms = transforms.Compose([
transforms.ToCVImage(),
transforms.Resize((128,256)),
transforms.ToTensor(),
transforms.Normalize(TRAIN_MEAN, TRAIN_STD)
])
def recog(self, img_path):
img = cv2.imread(img_path)
img = self.transforms(img)
img = img.unsqueeze(0)
with torch.no_grad():
self.net.eval()
img_input = img.to(self.device)
outputs = self.net(img_input)
results = []
for output in outputs:
output = torch.softmax(output, 1)
output = np.array(output[0].cpu())
label = np.argmax(output)
score = output[label]
results.append((label, score))
return results
name_dict = {
"gender":['男', '女'],
"age":["老年", "中年", "少年"],
"orientation":['正面', '侧面', '背面'],
"hat":["不戴帽子", "戴帽子"],
"glasses":["不戴眼镜", "戴眼镜"],
"handBag":["没有", "有"],
"shoulderBag":["没有", "有"],
"backBag":["没有", "有"],
"upClothing":["短袖", "长袖"],
"downClothing":["长裤", "短裤", "裙子"]
}
if __name__ == "__main__":
atts = ["gender","age", "orientation", "hat", "glasses",
"handBag", "shoulderBag", "backBag", "upClothing", "downClothing"]
person_attribute = Person_Attribute("./resnest50-50-regular.pth")
img_path = "test.jpg"
results = person_attribute.recog(img_path)
print(results)
img = cv2.imread(img_path)
img = cv2.resize(img, (128,256))
img1 = img*0 +255
img1[:,:,0] *= 255
img1[:,:,2] *= 255
line = ""
labels = [i[0] for i in results]
for att, label in zip(atts, labels):
if label == -1:
continue
line += "%s:%s\n" % (att, name_dict[att][label])
img1 = cv2.cvtColor(img1, cv2.COLOR_BGR2RGB)
img1 = Image.fromarray(img1)
draw = ImageDraw.Draw(img1)
font = ImageFont.truetype("simhei.ttf", 12, encoding="utf-8")
draw.text((0, 0), line, (255, 0, 0), font=font)
img1 = cv2.cvtColor(np.array(img1), cv2.COLOR_RGB2BGR)
img_rst = np.hstack([img, img1])
cv2.imwrite(os.path.basename(img_path), img_rst)The test results are as follows:
Note: The training data used in this article are all public data sets. If you need a trained model or training data or technical exchanges, please leave a message or WeChat. The code will be open source in the near future.
