pytorch模型部署和数据归一化的问题
%matplotlib inline
# 引入必要的库
from __future__ import print_function, division
import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy
数据的归一化问题
均值和标准差
在分类、聚类算法中，需要使用距离来度量相似性的时候、或者使用PCA技术进行降维的时候，新的数据由于对方差进行了归一化，这时候每个维度的量纲其实已经等价了，每个维度都服从均值为0、方差1的正态分布，在计算距离的时候，每个维度都是去量纲化的，避免了不同量纲的选取对距离计算产生的巨大影响。
pytorch训练集的图片做了归一化处理:
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
具体的运算:
# 图像归一化处理
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
img = img/255
img = (img - mean)/std
# 加载数据集
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
data_dir = 'data/mask'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
data_transforms[x])
for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
shuffle=True, num_workers=4)
for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# 可视化数据集中的图片
def visualize_model(model, num_images=6):
was_training = model.training
model.eval()
images_so_far = 0
fig = plt.figure()
with torch.no_grad():
for i, (inputs, labels) in enumerate(dataloaders['val']):
inputs = inputs.to(device)
labels = labels.to(device)
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
print(preds)
for j in range(inputs.size()[0]):
images_so_far += 1
ax = plt.subplot(num_images//2, 2, images_so_far)
ax.axis('off')
ax.set_title('predicted: {}'.format(class_names[preds[j]]))
imshow(inputs.cpu().data[j])
if images_so_far == num_images:
model.train(mode=was_training)
return
model.train(mode=was_training)
def imshow(inp, title=None):
"""Imshow for Tensor."""
inp = inp.numpy().transpose((1, 2, 0))
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
inp = std * inp + mean
inp = np.clip(inp, 0, 1)
plt.imshow(inp)
if title is not None:
plt.title(title)
plt.pause(0.001) # pause a bit so that plots are updated
模型方式
对于包含模型和权重的使用 model = torch.load()
对于只有权重的 如:
PATH = './mask.pth'
torch.save(model_ft.state_dict(), PATH)
保存的
需要先定义模型,再加载权重
# 加载模型的权重
model_ft = models.resnet18(pretrained=False)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 3)
PATH = './mask.pth'
model_ft.load_state_dict(torch.load(PATH))
PATH = './mask502.pth'
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model_ft= torch.load(PATH, map_location=device)
model_ft=model_ft.to(device)
# 把模型设定为 eval模式(评估模式)
print(model_ft)
# 可视化检验训练集
model_ft.eval()
visualize_model(model_ft)
MobileNetV2(
(features): Sequential(
(0): ConvBNReLU(
(0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
(2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(2): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(3): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=144, bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(4): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(144, 144, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=144, bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(144, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(5): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(6): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(7): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(8): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(9): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(10): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(11): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(12): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(13): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(14): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(576, 576, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=576, bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(576, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(15): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(16): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(17): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(960, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(18): ConvBNReLU(
(0): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(classifier): Sequential(
(0): Dropout(p=0.2, inplace=False)
(1): Linear(in_features=1280, out_features=3, bias=True)
)
)
/usr/local/lib/python3.6/site-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torchvision.models.mobilenet.MobileNetV2' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/usr/local/lib/python3.6/site-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.container.Sequential' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/usr/local/lib/python3.6/site-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torchvision.models.mobilenet.ConvBNReLU' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/usr/local/lib/python3.6/site-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.conv.Conv2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/usr/local/lib/python3.6/site-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.batchnorm.BatchNorm2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/usr/local/lib/python3.6/site-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.activation.ReLU6' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/usr/local/lib/python3.6/site-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torchvision.models.mobilenet.InvertedResidual' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/usr/local/lib/python3.6/site-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.dropout.Dropout' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/usr/local/lib/python3.6/site-packages/torch/serialization.py:649: SourceChangeWarning: source code of class 'torch.nn.modules.linear.Linear' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
tensor([0, 0, 0, 2])
tensor([1, 2, 2, 0])
output_5_3.png
from PIL import Image
img_path = './data/mask/val/NOMASK/10678.jpg'
img_path = './data/mask/val/MASK/1580887710.6345747.jpg'
img = Image.open(img_path)
#（1）此处为使用PIL进行测试的代码
transform_valid = transforms.Compose([
transforms.Resize((224, 224), interpolation=2),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]
)
img_ = transform_valid(img).unsqueeze(0) #拓展维度
img_ = img_.to(device)
outputs = model_ft(img_)
print(outputs)
#输出概率最大的类别
_, indices = torch.max(outputs,1)
percentage = torch.nn.functional.softmax(outputs, dim=1)[0] * 100
perc = percentage[int(indices)].item()
result = class_names[indices]
print('predicted:', result)
tensor([[-0.9913, 2.2950, -1.5086]], grad_fn=<AddmmBackward>)
predicted: MASK
import cv2
img_path = './data/mask/val/MASK/1580887710.6345747.jpg'
img_path = './data/mask/val/NOMASK/10678.jpg'
img = cv2.imread(img_path)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = cv2.resize(img, (224, 224))
# 图像归一化处理
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])
img = img/255
img = (img - mean)/std
# 图像归一化后转成 tensor
img_ = torch.from_numpy(img).float().permute(2, 0, 1).unsqueeze(0)
# 推理计算
img_ = img_.to(device)
model_ft.eval()
outputs = model_ft(img_)
print(outputs)
#输出概率最大的类别
_, indices = torch.max(outputs,1)
percentage = torch.nn.functional.softmax(outputs, dim=1)[0] * 100
perc = percentage[int(indices)].item()
result = class_names[indices]
print('predicted:', result)
tensor([[-2.5533, 0.5445, 1.8401]], grad_fn=<AddmmBackward>)
predicted: NOMASK
网友评论