記事ディレクトリ
犬の年齢予測
Ali Tianchi ペットの年齢予測
https://tianchi.aliyun.com/competition/
はさまざまな方法を試しましたが、最終結果はあまり良くありませんでした。コンテスト後にもっと良いアイデアがあればアドバイスしてください。
论文顔のランドマークのない 1 枚の画像から実際の年齢と見た目の年齢を深く予想する
- 直接回帰
- セグメント分類
- セクション内の確率と重み付き期待値を求めることは、実際には回帰と同等です。
3 つのメソッドのパフォーマンス
その他の方法:
- ワンホットではなく分布を当てはめる
- 並び替え
- データバランス
参考:
https://github.com/NICE-FUTURE/predict-gender-and-age-from-camera/tree/master
分類損失関数
1. マルチカテゴリクロスエントロピー損失関数:
torch.nn.CrossEntropyLoss() = log_softmax + nll_loss
詳細な紹介: https://zhuanlan.zhihu.com/p/159477597
2. KLDiv 損失: 分配の差
分布の違いを説明、分類対象がワンホットではなくソフトラベルの場合は使用可能
https://zhuanlan.zhihu.com/p/340088331
3. フェイスネットトリプレット損失関数
https://github.com/kvsnoufal/Pytorch-FaceNet-DogDataset
ティムとトーチビジョン
https://datawhalecina.github.io/thorough-pytorch/index.html
https://datawhalecina.github.io/thorough-pytorch/%E7%AC%AC%E5%85%AD%E7%AB%A0/ 6.3%20%E6%A8%A1%E5%9E%8B%E5%BE%AE%E8%B0%83-timm.html
トーチビジョン
import torchvision.models as models
resnet18 = models.resnet18()
# resnet18 = models.resnet18(pretrained=False) 等价于与上面的表达式
alexnet = models.alexnet()
vgg16 = models.vgg16()
squeezenet = models.squeezenet1_0()
densenet = models.densenet161()
inception = models.inception_v3()
googlenet = models.googlenet()
shufflenet = models.shufflenet_v2_x1_0()
mobilenet_v2 = models.mobilenet_v2()
mobilenet_v3_large = models.mobilenet_v3_large()
mobilenet_v3_small = models.mobilenet_v3_small()
resnext50_32x4d = models.resnext50_32x4d()
wide_resnet50_2 = models.wide_resnet50_2()
mnasnet = models.mnasnet1_0()
試み 1: 分類モデル、年齢ごとに 1 ~ 191 のカテゴリに分割
主な参考文献:犬種分類
クロスエントロピー損失を使用し、それを分類モデルとしてトレーニングします。
import glob
import os
import cv2
import numpy as np
import torch
from torch import nn, optim
from torchvision import datasets,transforms
from torch.utils.data import DataLoader
import torch
import torchvision.models as models
from PIL import Image
import torchvision.transforms as transforms
from tqdm import tqdm
from dog_age2 import Net
def VGG16_predict(img_path):
'''
Use pre-trained VGG-16 model to obtain index corresponding to
predicted ImageNet class for image at specified path
Args:
img_path: path to an image
Returns:
Index corresponding to VGG-16 model's prediction
'''
# define VGG16 model
VGG16 = models.vgg16(pretrained=True)
# check if CUDA is available
use_cuda = torch.cuda.is_available()
# move model to GPU if CUDA is available
if use_cuda:
VGG16 = VGG16.cuda()
## Load and pre-process an image from the given img_path
## Return the *index* of the predicted class for that image
# Image Resize to 256
image = Image.open(img_path)
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
image_transforms = transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean, std)])
image_tensor = image_transforms(image)
image_tensor.unsqueeze_(0)
if use_cuda:
image_tensor = image_tensor.cuda()
output = VGG16(image_tensor)
_, classes = torch.max(output, dim=1)
return classes.item() # predicted class index
### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
## TODO: Complete the function.
class_dog=VGG16_predict(img_path)
return class_dog >= 151 and class_dog <=268 # true/false
def resnet50_predict(img_path):
resnet50 = models.resnet50(pretrained=True)
use_cuda = torch.cuda.is_available()
if use_cuda:
resnet50.cuda()
image = Image.open(img_path)
mean=[0.485, 0.456, 0.406]
std=[0.229, 0.224, 0.225]
image_transforms = transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean,std)])
image_tensor = image_transforms(image)
image_tensor.unsqueeze_(0)
if use_cuda:
image_tensor=image_tensor.cuda()
resnet50.eval()
output = resnet50(image_tensor)
_,classes = torch.max(output,dim=1)
return classes.item()
def resnet50_dog_detector(image_path):
class_idx = resnet50_predict(image_path)
return class_idx >= 151 and class_idx <=268
def get_train_set_info(dir):
dog_files_train = glob.glob(dir + '\\*.jpg')
mean = np.array([0.,0.,0.])
std = np.array([0.,0.,0.])
for i in tqdm(range(len(dog_files_train))):
image=cv2.imread(dog_files_train[i])
image = cv2.cvtColor(image,cv2.COLOR_BGR2RGB)
image = image/255.0
mean[0] += np.mean(image[:,:,0])
mean[1] += np.mean(image[:,:,1])
mean[2] += np.mean(image[:,:,2])
std[0] += np.std(image[:,:,0])
std[1] += np.std(image[:,:,1])
std[2] += np.std(image[:,:,2])
mean = mean/len(dog_files_train)
std = std/len(dog_files_train)
return mean,std
from PIL import ImageFile
def train(n_epochs, loaders, model, optimizer, criterion, use_cuda, save_path):
"""returns trained model"""
# initialize tracker for minimum validation loss
valid_loss_min = np.Inf
for epoch in range(1, n_epochs + 1):
# initialize variables to monitor training and validation loss
train_loss = 0.0
valid_loss = 0.0
###################
# train the model #
###################
model.train()
for batch_idx, (data, target) in enumerate(tqdm(loaders['train'])):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
## find the loss and update the model parameters accordingly
## record the average training loss, using something like
## train_loss = train_loss + ((1 / (batch_idx + 1)) * (loss.data - train_loss))
optimizer.zero_grad()
output = model(data)
loss = criterion(output, target)
loss.backward()
optimizer.step()
train_loss = train_loss + ((1 / (batch_idx + 1)) * (loss.data - train_loss))
######################
# validate the model #
######################
correct = 0.
correct2 = 0
correct3 = 0
correct4 = 0
total = 0.
model.eval()
for batch_idx, (data, target) in enumerate(tqdm(loaders['valid'])):
# move to GPU
if use_cuda:
data, target = data.cuda(), target.cuda()
## update the average validation loss
output = model(data)
loss = criterion(output, target)
valid_loss = valid_loss + ((1 / (batch_idx + 1)) * (loss.data - valid_loss))
pred = output.data.max(1, keepdim=True)[1]
# compare predictions to true label
correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
correct2 += np.sum(np.squeeze(np.abs(pred.cpu().numpy() - (target.data.view_as(pred).cpu().numpy())) < 5))
correct3 += np.sum(np.squeeze(np.abs(pred.cpu().numpy() - (target.data.view_as(pred).cpu().numpy())) < 10))
correct4 += np.sum(np.squeeze(np.abs(pred.cpu().numpy() - (target.data.view_as(pred).cpu().numpy()))))
total += data.size(0)
# print training/validation statistics
print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
epoch,
train_loss,
valid_loss
))
print('Test Accuracy: %2d%% (%2d/%2d)' % (
100. * correct / total, correct, total))
print('Test Accuracy: %2d%% (%2d/%2d)' % (
100. * correct2 / total, correct2, total))
print('Test Accuracy: %2d%% (%2d/%2d)' % (
100. * correct3 / total, correct3, total))
print('Test Accuracy: %2d' % (
correct4 / total))
## TODO: save the model if validation loss has decreased
if valid_loss_min > valid_loss:
print('Saving Model...')
valid_loss_min = valid_loss
torch.save(model.state_dict(), save_path)
# return trained model
return model
if __name__ == "__main__":
# 1. vgg16 和 resnet50 的识别能力
dir = r'D:\commit\trainset\trainset'
# dog_files = glob.glob(dir + '\\*.jpg')
#
# dog_files_short = dog_files[:100]
#
# dog_percentage_dog = 0
# dog_percentage_dog2 = 0
# for i in tqdm(range(100)):
# dog_percentage_dog += int(dog_detector(dog_files_short[i]))
# dog_percentage_dog2 += int(resnet50_dog_detector(dog_files_short[i]))
#
# print(' Dog Percentage in Dog Dataset:{}% {} %'.format( dog_percentage_dog, dog_percentage_dog2)) # 98%, 97%
# 2. 训练数据的均值和方差
# mean, std = get_train_set_info(dir)
# print(mean, std) # [0.595504 0.54956806 0.51172713] [0.2101685 0.21753638 0.22078435]
# 3. 训练
mean_train_set = [0.595504, 0.54956806, 0.51172713]
std_train_set = [0.2101685, 0.21753638, 0.22078435]
train_dir = r'D:\commit\trainset\trainset2'
valid_dir = r'D:\commit\valset\valset2'
test_dir = r'D:\commit\valset\valset2'
train_transforms = transforms.Compose([transforms.Resize([256, 256]),
transforms.ColorJitter(brightness=0.5, contrast=0.2, saturation=0.2, hue=0.1),
transforms.RandomHorizontalFlip(p=0.5),
transforms.ToTensor(),
transforms.Normalize(mean_train_set, std_train_set)])
valid_test_transforms = transforms.Compose([transforms.Resize([256, 256]),
#transforms.CenterCrop(256),
transforms.ToTensor(),
transforms.Normalize(mean_train_set, std_train_set)])
train_dataset = datasets.ImageFolder(train_dir, transform=train_transforms)
valid_dataset = datasets.ImageFolder(valid_dir, transform=valid_test_transforms)
#test_dataset = datasets.ImageFolder(test_dir, transform=valid_test_transforms)
# num_workers=8, pin_memory=True 很重要,训练速度明显
trainloader = DataLoader(train_dataset, batch_size=32, shuffle=True, num_workers=16, pin_memory=True)
validloader = DataLoader(valid_dataset, batch_size=32, shuffle=False,num_workers=8, pin_memory=True)
#testloader = DataLoader(test_dataset, batch_size=32, shuffle=False)
loaders_scratch = {
}
loaders_scratch['train'] = trainloader
loaders_scratch['valid'] = validloader
#loaders_scratch['test'] = testloader
use_cuda = torch.cuda.is_available()
# instantiate the CNN
num_class = 191
# model_scratch = Net(num_class)
model_scratch = models.resnet50(pretrained=True)
for param in model_scratch.parameters():
param.requires_grad = True
# model_scratch.classifier = nn.Sequential(nn.Linear(1024, 512),
# nn.ReLU(),
# nn.Dropout(0.2),
# nn.Linear(512, 133))
#
# model_scratch.load_state_dict(torch.load('model_transfer.pt', map_location='cuda:0'))
model_scratch.classifier = nn.Sequential(nn.Linear(1024, 512),
nn.ReLU(),
nn.Dropout(0.2),
nn.Linear(512, num_class))
# move tensors to GPU if CUDA is available
if use_cuda:
model_scratch.cuda()
criterion_scratch = nn.CrossEntropyLoss()
optimizer_scratch = optim.Adam(model_scratch.parameters(), lr=0.0005)
print('training !')
# epoch
ImageFile.LOAD_TRUNCATED_IMAGES = True
model_scratch = train(100, loaders_scratch, model_scratch, optimizer_scratch,
criterion_scratch, use_cuda, 'model_scratch2.pt')
# load the model that got the best validation accuracy
# model_scratch.load_state_dict(torch.load('model_scratch.pt'))
効果がない。
試み 2: 回帰モデル
モデル.py
import torch
import torch.nn as nn
from torchinfo import summary
import timm
class base_net(nn.Module):
def __init__(self, input_features, num_features=64):
super().__init__()
self.num_features = num_features
self.conv = nn.Sequential(
nn.Conv2d(input_features, num_features, kernel_size=3, padding=3//2),
#nn.BatchNorm2d(num_features),
nn.ReLU(inplace=True),
nn.Conv2d(num_features, num_features*2, kernel_size=3, padding=3//2),
#nn.BatchNorm2d(num_features*2),
nn.ReLU(inplace=True),
nn.Conv2d(num_features*2, num_features, kernel_size=3, padding=3 // 2),
#nn.BatchNorm2d(num_features),
nn.ReLU(inplace=True),
nn.Conv2d(num_features, num_features, kernel_size=3, padding=3 // 2),
#nn.BatchNorm2d(num_features),
nn.ReLU(inplace=True),
nn.Conv2d(num_features, num_features, kernel_size=3, padding=3//2),
)
def forward(self, x):
x = self.conv(x)
return x
class Predictor(nn.Module):
""" The header to predict age (regression branch) """
def __init__(self, num_features, num_classes=1):
super().__init__()
self.conv = nn.Sequential(
nn.Conv2d(num_features, num_features // 4, kernel_size=3, padding=3 // 2),
nn.BatchNorm2d(num_features // 4),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(num_features // 4, num_features // 8, kernel_size=3, padding=3 // 2),
nn.BatchNorm2d(num_features // 8),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(num_features // 8, num_features // 16, kernel_size=3, padding=3 // 2),
)
self.gap = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Conv2d(num_features//16, num_classes, kernel_size=1, bias=True)
#self.dp = nn.Dropout(0.5)
def forward(self, x):
x = self.conv(x)
x = self.gap(x)
#x = self.dp(x)
x = self.fc(x)
x = x.squeeze(-1).squeeze(-1).squeeze(-1)
return x
class Classifier(nn.Module):
""" The header to predict gender (classification branch) """
def __init__(self, num_features, num_classes=100):
super().__init__()
self.conv = nn.Sequential(
nn.Conv2d(num_features, num_features // 4, kernel_size=3, padding=3 // 2),
nn.BatchNorm2d(num_features // 4),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(num_features // 4, num_features // 8, kernel_size=3, padding=3 // 2),
nn.BatchNorm2d(num_features // 8),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(num_features // 8, num_features // 16, kernel_size=3, padding=3 // 2),
)
self.gap = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Conv2d(num_features//16, num_classes, kernel_size=1, bias=True)
self.dp = nn.Dropout(0.4)
def forward(self, x):
x = self.conv(x)
x = self.gap(x)
x = self.dp(x)
x = self.fc(x)
x = x.squeeze(-1).squeeze(-1)
# x = nn.functional.softmax(x, dim=1)
return x
#https://github.com/NICE-FUTURE/predict-gender-and-age-from-camera/tree/master
class Model(nn.Module):
""" A model to predict age and gender """
def __init__(self, timm_pretrained=True):
super().__init__()
self.backbone = timm.create_model("resnet18", pretrained=timm_pretrained)
self.predictor = Predictor(self.backbone.num_features)
# self.classifier = Classifier(self.backbone.num_features)
def forward(self, x):
x = self.backbone.forward_features(x) # shape: B, D, H, W
age = self.predictor(x)
#gender = self.classifier(x)
return age
class Model2(nn.Module):
""" A model to predict age and gender """
def __init__(self, timm_pretrained=True):
super().__init__()
self.backbone = timm.create_model("resnet18", pretrained=timm_pretrained) #base_net(3, 64) #
# self.predictor = Predictor(self.backbone.num_features)
self.classifier = Classifier(self.backbone.num_features) # 100类概率
def forward(self, x):
x = self.backbone.forward_features(x) # shape: B, D, H, W
#x = self.backbone.forward(x) # shape: B, D, H, W
prob = self.classifier(x)
#gender = self.classifier(x)
return prob
class Model3(nn.Module):
""" A model to predict age and gender """
def __init__(self, timm_pretrained=False):
super().__init__()
self.backbone = base_net(3, 64) # timm.create_model("resnet18", pretrained=timm_pretrained) #
# self.predictor = Predictor(self.backbone.num_features)
self.classifier = Classifier(self.backbone.num_features) # 100类概率
def forward(self, x):
#x = self.backbone.forward_features(x) # shape: B, D, H, W
x = self.backbone.forward(x) # shape: B, D, H, W
prob = self.classifier(x)
#gender = self.classifier(x)
return prob
if __name__ == "__main__":
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# device = 'cpu'
print(device)
modelviz = Model2().to(device)
# 打印模型结构
print(modelviz)
summary(modelviz, input_size=(2, 3, 256, 256), col_names=["kernel_size", "output_size", "num_params", "mult_adds"])
# for p in modelviz.parameters():
# if p.requires_grad:
# print(p.shape)
input = torch.rand(2, 3, 256, 256).to(device)
out = modelviz(input)
from ptflops import get_model_complexity_info
macs, params = get_model_complexity_info(modelviz, (3, 256, 256), verbose=True, print_per_layer_stat=True)
print(macs, params)
params = float(params[:-3])
macs = float(macs[:-4])
print(macs * 2, params) # 8个图像的 FLOPs, 这里的结果 和 其他方法应该一致
print('out:', out.shape, out)
モデルをトレーニングします。
import glob
import os.path
import cv2
import numpy as np
import rawpy
import torch
import torch.optim as optim
from torch import nn
from torch.utils.data import DataLoader
from torchvision import transforms
from tqdm import tqdm
from datasets import BatchDataset
from model import Model, Model2
import torchvision
if __name__ == "__main__":
# 1.当前版本信息
print(torch.__version__)
print(torch.version.cuda)
print(torch.backends.cudnn.version())
print(torch.cuda.get_device_name(0))
np.random.seed(0)
torch.manual_seed(0)
torch.cuda.manual_seed_all(0)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
# 2. 设置device信息 和 创建model
# os.environ['CUDA_VISIBLE_DEVICES'] = '2,3'
# device = torch.device("cuda:2" if torch.cuda.is_available() else "cpu")
model = Model()
gpus = [2,3]
model = nn.DataParallel(model, device_ids=gpus)
device = torch.device('cuda:2')
model = model.cuda(device=gpus[0])
# 3. dataset 和 data loader, num_workers设置线程数目,pin_memory设置固定内存
img_size = 256
transform1 = transforms.Compose([
transforms.ToTensor(),
transforms.Resize([img_size, img_size]),
transforms.RandomHorizontalFlip(p=0.5),
transforms.ColorJitter(brightness=0.4, contrast=0.2, saturation=0.2, hue=0.1),
#transforms.RandomPerspective(distortion_scale=0.6, p=1.0),
transforms.RandomRotation(degrees=(-90, 90)),
])
transform2 = transforms.Compose([
transforms.ToTensor(),
transforms.Resize([img_size, img_size]),
])
train_dataset = BatchDataset('train', transform1)
train_dataset_loader = DataLoader(train_dataset, batch_size=32*4, shuffle=True, num_workers=8, pin_memory=True)
eval_dataset = BatchDataset('eval', transform2)
eval_dataset_loader = DataLoader(eval_dataset, batch_size=8, shuffle=True, num_workers=8, pin_memory=True)
print('load dataset !', len(train_dataset), len(eval_dataset))
# 4. 损失函数 和 优化器
age_criterion = nn.MSELoss()
gender_criterion = nn.CrossEntropyLoss().to(device)
loss_fn = nn.L1Loss().to(device)
loss_fn2 = nn.SmoothL1Loss().to(device)
learning_rate = 1 * 1e-4
#optimizer = optim.Adam(model.parameters(), lr=learning_rate)
optimizer = optim.SGD(model.parameters(), lr=learning_rate, momentum=0.9)
lr_step = 50
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, lr_step, gamma=0.5)
# 5. hyper para 设置
epochs = 800
save_epoch = 100
save_model_dir = 'saved_model_age'
eval_epoch = 100
save_sample_dir = 'saved_sample_age'
if not os.path.exists(save_model_dir):
os.makedirs(save_model_dir)
# 6. 是否恢复模型
resume = 1
last_epoch = 12
if resume and last_epoch > 1:
model.load_state_dict(torch.load(
save_model_dir + '/checkpoint_%04d.pth' % (last_epoch),
map_location=device))
print('resume ' , save_model_dir + '/checkpoint_%04d.pth' % (last_epoch))
# 7. 训练epoch
f1 = open('traininfo1.txt', 'a')
f2 = open('evalinfo1.txt', 'a')
for epoch in range(last_epoch + 1, epochs + 1):
print('current epoch:', epoch, 'current lr:', optimizer.state_dict()['param_groups'][0]['lr'])
if epoch < last_epoch + 101:
save_epoch = 2
eval_epoch = 2
else:
save_epoch = 10
eval_epoch = 10
# 8. train loop
model.train()
g_loss = []
g_mae = []
for data in tqdm(train_dataset_loader):
image, age, filename = data
# print(image.shape, age, filename)
image = image.to(device)
age = age.to(device)
pred_age = model(image)
#print(image.shape, pred_age.shape)
loss = loss_fn(age, pred_age)
#loss = age_criterion(age, pred_age)
#print('dd:', age.detach().cpu().numpy().reshape(-1), pred_age.detach().cpu().numpy().reshape(-1))
optimizer.zero_grad()
loss.backward()
optimizer.step()
# training result
g_loss.append(loss.item())
mae = np.sum(np.abs(age.detach().cpu().numpy().reshape(-1) - pred_age.detach().cpu().numpy().reshape(-1))) / len(age)
g_mae.append(mae)
#print( loss.item(), mae)
#print(len(g_loss), len(g_mae))
mean_loss = np.mean(np.array(g_loss))
mean_mae = np.mean(np.array(g_mae))
print(f'epoch{
epoch:04d} ,train loss: {
mean_loss},train mae: {
mean_mae}')
f1.write("%d, %.6f, %.4f\n" % (epoch, mean_loss, mean_mae))
# 9. save model
if epoch % save_epoch == 0:
save_model_path = os.path.join(save_model_dir, f'checkpoint_{
epoch:04d}.pth')
torch.save(model.state_dict(), save_model_path)
# 10. eval test and save some samples if needed
if epoch % eval_epoch == 0:
model.eval()
maes = []
with torch.no_grad():
for data in tqdm(eval_dataset_loader):
image, age, filename = data
image = image.to(device)
age = age.to(device)
out = model(image)
mae = loss_fn(out, age)
#print( age.detach().cpu().numpy().reshape(-1), out.detach().cpu().numpy().reshape(-1), mae.item())
maes.append(mae.item())
print('eval dataset mae: ', np.array(maes).mean())
f2.write("%d, %.6f\n" % (epoch, np.array(maes).mean()))
scheduler.step() # 更新学习率
効果は悪くない、エバルマエは22くらいまで到達できる
試み 3: 分類モデル
1) データの不均衡に対処するには、各グループがトレーニング用に 1 エポックのデータセットを取得するのに 50 個かかる、5 つの年齢のデータ セットとは何ですか。 2) 分類は、クロス エントロピー損失に加えて確率です
。 、プラス予想損失
効果的ではない
試み 4: KLDivLoss フィッティング年齢分布
年齢の mae 損失に加えて、
年齢分布の損失もあり、これは KLDivLoss を使用して実装されます。
たとえば、ラベル =21 の年齢設定分布は、21 歳付近の年齢が 0 ではなく、その他は 0 です。
prob = model(image)
pred_age = torch.sum(prob * torch.arange(0, 100).reshape(1, -1).to(device), axis=1) * 2 + 1
#print(prob.shape, label.shape)
loss1 = loss_kl(prob.log(), label) # label是一个分布
loss2 = loss_fn(age, pred_age)
loss = loss1 + loss2 / 10
試み 5: 最初に犬の顔を抽出し、次にモデルをトレーニングします
直接トレーニングは過剰適合しやすいため、写真内の他の特徴がモデルのトレーニングを妨げていると思われるため、犬の顔を抽出した後のトレーニング効果はより良くなりますか? 犬の顔を抽出するにはどうすればよいですか?
主に以下のウェアハウスを使用します
https://github.com/metinozkan/DogAndCat-Face-Opencv
import glob
import os
import cv2
files = glob.glob(r'D:\commit\testset\testset' + '\\*.jpg')
for file in files:
#file = r'D:\commit\trainset\trainset\02e5218a80b44139ab07c547e1d6c4b9.jpg'
img=cv2.imread(file)#picture path
height, width, channel = img.shape
yuz_cascade=cv2.CascadeClassifier('dog_face.xml')#used haarcascade Classifier
#kedi_cascade=cv2.CascadeClassifier('haarcascade_frontalcatface.xml path')#used haarcascade Classifier
griton = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)#Picture conversion gray tone with haarcascade
it = yuz_cascade.detectMultiScale(griton,1.1,4)#search for the object you want in photos
#kedi=kedi_cascade.detectMultiScale(griton,1.1,4)
kopeksay=0#increases the number of found objects
kedisay=0
#objects in the rectangle
wh = 0
i = 0
if len(it) == 0:
x, y, w, h = 0,0,width,height
print(file, 'not changed ')
else:
for (x, y, w, h) in it:
if w* h > wh:
wh = w*h
j = i
i += 1
(x, y, w, h) = it[j]
T = 20
# save
img2 = img[ max(y-T, 0): min(y + h+T, height), max(x-T, 0) : min(x + w + T,width)]
cv2.imwrite(os.path.join(r'D:\commit\testset\testset3', os.path.basename(file)), img2)
# show
show_fig = 0
if show_fig:
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 3)
cv2.rectangle(img, (max(x-T, 0), max(y-T, 0)), (min(x + w + T,width) , min(y + h+T, height)), (0, 255, 255), 3)
kopeksay=kopeksay+1
# for (x, y, w, h) in kedi:
# cv2.rectangle(img, (x, y), (x + w,y + h), (0, 10, 0), 3)
# kedisay=kedisay+1
print("kopek->",kopeksay)#number of found objects
print("kedi-->",kedisay)
cv2.imshow('yuzler', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
最後に、主に 2 と 5 に従って最適化されます。予報
import glob
import os.path
import cv2
import numpy as np
import rawpy
import torch
import torch.optim as optim
from PIL import Image
from torch import nn
from torch.utils.data import DataLoader
from torchvision import transforms
from tqdm import tqdm
from skimage.metrics import peak_signal_noise_ratio as compare_psnr
from skimage.metrics import structural_similarity as compare_ssim
from datasets import BatchDataset, get_images
from model import UNetSeeInDark, Model, Model2
if __name__ == "__main__":
img_size = 256
transform2 = transforms.Compose([
transforms.ToTensor(),
transforms.Resize([img_size, img_size]),
])
model = Model()
gpus = [0]
# model = nn.DataParallel(model, device_ids=gpus)
device = torch.device('cuda:0')
print(device)
m_path = 'saved_model_age/checkpoint_0014.pth'
#m_path = 'saved_model_res18_reg/checkpoint_0010.pth'
checkpoint = torch.load(m_path, map_location=device)
model.load_state_dict({
k.replace('module.', ''): v for k, v in checkpoint.items()})
#model.load_state_dict(torch.load(m_path, map_location=device))
model = model.cuda(device=gpus[0])
model.eval()
files = glob.glob("testset\\testset\\*.jpg")
# image_dir = 'valset\\valset'
# file_txt = 'annotations\\annotations\\val.txt'
# files = get_images(image_dir, file_txt)
print(len(files))
f = open('predict_res50_14.txt', 'w')
st = ''
ret = []
for file in files:
# file, label = file
image = Image.open(file).convert('RGB')
# image = cv2.imread(file, 1).astype(np.float32) / 255
image = np.array(image)
input = transform2(image).unsqueeze(0).to(device)
#print(input.shape)
out = model(input)
out = out.detach().cpu().numpy().reshape(-1)
pred_age = out[0]
#pred_age = np.sum(out * np.arange(0, 100).reshape(1, -1)) * 2 + 1
#print(int(label), pred_age, np.abs(pred_age -int(label)))
#ret.append([int(label), pred_age, pred_age -int(label), np.abs(pred_age -int(label))])
#print(out)
st = os.path.basename(file)+'\t%.2f\n' % (pred_age.item())
f.write(st)
# ret = np.array(ret)
# print(ret)
# print(np.mean(ret, axis=0))
#np.savetxt('ret54.txt', ret+2, fmt='%.1f', delimiter=' ')