PyTorch一小时掌握之图像识别实战篇

概述

今天我们要来做一个进阶的花分类问题. 不同于之前做过的鸢尾花, 这次我们会分析 102 中不同的花. 是不是很上头呀.

 

预处理

导包

常规操作, 没什么好解释的. 缺模块的同学自行pip -install.

import numpy as np
import time
from matplotlib import pyplot as plt
import json
import copy
import os
import torch
from torch import nn
from torch import optim
from torchvision import transforms, models, datasets

数据读取与预处理

数据预处理部分:
数据增强: torchvision 中 transforms 模块自带功能, 用于扩充数据样本
数据预处理: torchvision 中 transforms 也帮我们实现好了
数据分批: DataLoader 模块直接读取 batch 数据

# ----------------1. 数据读取与预处理------------------

# 路径
data_dir = './flower_data/'
train_dir = data_dir + '/train'
valid_dir = data_dir + '/valid'

# 制作数据源
data_transforms = {
  'train': transforms.Compose([transforms.RandomRotation(45),  #随机旋转，-45到45度之间随机选
      transforms.CenterCrop(224),  #从中心开始裁剪
      transforms.RandomHorizontalFlip(p=0.5),  #随机水平翻转 选择一个概率概率
      transforms.RandomVerticalFlip(p=0.5),  #随机垂直翻转
      transforms.ColorJitter(brightness=0.2, contrast=0.1, saturation=0.1, hue=0.1),  #参数1为亮度, 参数2为对比度，参数3为饱和度，参数4为色相
      transforms.RandomGrayscale(p=0.025),  #概率转换成灰度率, 3通道就是R=G=B
      transforms.ToTensor(),
      transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])  #均值, 标准差
  ]),
  'valid': transforms.Compose([transforms.Resize(256),
      transforms.CenterCrop(224),
      transforms.ToTensor(),
      transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
  ]),
}

batch_size = 8

image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'valid']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True) for x in ['train', 'valid']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'valid']}
class_names = image_datasets['train'].classes

# 调试输出
print(image_datasets)
print(dataloaders)
print(dataset_sizes)
print(class_names)

# 读取标签对应的实际名字
with open('cat_to_name.json', 'r') as f:
  cat_to_name = json.load(f)

print(cat_to_name)

输出结果:
{'train': Dataset ImageFolder
Number of datapoints: 6552
Root location: ./flower_data/train
StandardTransform
Transform: Compose(
RandomRotation(degrees=(-45, 45), resample=False, expand=False)
CenterCrop(size=(224, 224))
RandomHorizontalFlip(p=0.5)
RandomVerticalFlip(p=0.5)
ColorJitter(brightness=[0.8, 1.2], contrast=[0.9, 1.1], saturation=[0.9, 1.1], hue=[-0.1, 0.1])
RandomGrayscale(p=0.025)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
), 'valid': Dataset ImageFolder
Number of datapoints: 818
Root location: ./flower_data/valid
StandardTransform
Transform: Compose(
Resize(size=256, interpolation=PIL.Image.BILINEAR)
CenterCrop(size=(224, 224))
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)}
{'train': <torch.utils.data.dataloader.DataLoader object at 0x000001B718A277F0>, 'valid': <torch.utils.data.dataloader.DataLoader object at 0x000001B718A27898>}
{'train': 6552, 'valid': 818}
['1', '10', '100', '101', '102', '11', '12', '13', '14', '15', '16', '17', '18', '19', '2', '20', '21', '22', '23', '24', '25', '26', '27', '28', '29', '3', '30', '31', '32', '33', '34', '35', '36', '37', '38', '39', '4', '40', '41', '42', '43', '44', '45', '46', '47', '48', '49', '5', '50', '51', '52', '53', '54', '55', '56', '57', '58', '59', '6', '60', '61', '62', '63', '64', '65', '66', '67', '68', '69', '7', '70', '71', '72', '73', '74', '75', '76', '77', '78', '79', '8', '80', '81', '82', '83', '84', '85', '86', '87', '88', '89', '9', '90', '91', '92', '93', '94', '95', '96', '97', '98', '99']
{'21': 'fire lily', '3': 'canterbury bells', '45': 'bolero deep blue', '1': 'pink primrose', '34': 'mexican aster', '27': 'prince of wales feathers', '7': 'moon orchid', '16': 'globe-flower', '25': 'grape hyacinth', '26': 'corn poppy', '79': 'toad lily', '39': 'siam tulip', '24': 'red ginger', '67': 'spring crocus', '35': 'alpine sea holly', '32': 'garden phlox', '10': 'globe thistle', '6': 'tiger lily', '93': 'ball moss', '33': 'love in the mist', '9': 'monkshood', '102': 'blackberry lily', '14': 'spear thistle', '19': 'balloon flower', '100': 'blanket flower', '13': 'king protea', '49': 'oxeye daisy', '15': 'yellow iris', '61': 'cautleya spicata', '31': 'carnation', '64': 'silverbush', '68': 'bearded iris', '63': 'black-eyed susan', '69': 'windflower', '62': 'japanese anemone', '20': 'giant white arum lily', '38': 'great masterwort', '4': 'sweet pea', '86': 'tree mallow', '101': 'trumpet creeper', '42': 'daffodil', '22': 'pincushion flower', '2': 'hard-leaved pocket orchid', '54': 'sunflower', '66': 'osteospermum', '70': 'tree poppy', '85': 'desert-rose', '99': 'bromelia', '87': 'magnolia', '5': 'english marigold', '92': 'bee balm', '28': 'stemless gentian', '97': 'mallow', '57': 'gaura', '40': 'lenten rose', '47': 'marigold', '59': 'orange dahlia', '48': 'buttercup', '55': 'pelargonium', '36': 'ruby-lipped cattleya', '91': 'hippeastrum', '29': 'artichoke', '71': 'gazania', '90': 'canna lily', '18': 'peruvian lily', '98': 'mexican petunia', '8': 'bird of paradise', '30': 'sweet william', '17': 'purple coneflower', '52': 'wild pansy', '84': 'columbine', '12': "colt's foot", '11': 'snapdragon', '96': 'camellia', '23': 'fritillary', '50': 'common dandelion', '44': 'poinsettia', '53': 'primula', '72': 'azalea', '65': 'californian poppy', '80': 'anthurium', '76': 'morning glory', '37': 'cape flower', '56': 'bishop of llandaff', '60': 'pink-yellow dahlia', '82': 'clematis', '58': 'geranium', '75': 'thorn apple', '41': 'barbeton daisy', '95': 'bougainvillea', '43': 'sword lily', '83': 'hibiscus', '78': 'lotus lotus', '88': 'cyclamen', '94': 'foxglove', '81': 'frangipani', '74': 'rose', '89': 'watercress', '73': 'water lily', '46': 'wallflower', '77': 'passion flower', '51': 'petunia'}

数据可视化

虽然我也不知道这些都是什么花, 但是还是一起来看一下. 有知道的大佬可以评论区留个言.

# ----------------2. 展示下数据------------------
def im_convert(tensor):
  """ 展示数据"""

  image = tensor.to("cpu").clone().detach()
  image = image.numpy().squeeze()
  image = image.transpose(1, 2, 0)
  image = image * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
  image = image.clip(0, 1)

  return image


def im_convert(tensor):
  """ 展示数据"""

  image = tensor.to("cpu").clone().detach()
  image = image.numpy().squeeze()
  image = image.transpose(1, 2, 0)
  image = image * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
  image = image.clip(0, 1)

  return image

fig=plt.figure(figsize=(20, 12))
columns = 4
rows = 2

dataiter = iter(dataloaders['valid'])
inputs, classes = dataiter.next()

for idx in range (columns*rows):
  ax = fig.add_subplot(rows, columns, idx+1, xticks=[], yticks=[])
  ax.set_title(cat_to_name[str(int(class_names[classes[idx]]))])
  plt.imshow(im_convert(inputs[idx]))
plt.show()

输出结果:

 

主体

加载参数

# ----------------3. 加载models中提供的模型------------------

# 直接使用训练好的权重当做初始化参数
model_name = "resnet"  # 可选的比较多 ['resnet', 'alexnet', 'vgg', 'squeezenet', 'densenet', 'inception']

# 是否使用人家训练好的特征来做
feature_extract = True

# 是否使用GPU训练
train_on_gpu = torch.cuda.is_available()

if not train_on_gpu:
  print('CUDA is not available.  Training on CPU ...')
else:
  print('CUDA is not available.  Training on CPU ...')

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

def set_parameter_requires_grad(model, feature_extracting):
  if feature_extracting:
      for param in model.parameters():
          param.requires_grad = False


model_ft = models.resnet152()
print(model_ft)

输出结果:
CUDA is not available. Training on CPU ...
ResNet(
(conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(layer1): Sequential(
(0): Bottleneck(
(conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer2): Sequential(
(0): Bottleneck(
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(3): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(4): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(5): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(6): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(7): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer3): Sequential(
(0): Bottleneck(
(conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(3): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(4): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(5): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(6): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(7): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(8): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(9): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(10): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(11): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(12): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(13): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(14): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(15): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(16): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(17): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(18): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(19): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(20): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(21): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(22): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(23): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(24): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(25): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(26): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(27): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(28): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(29): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(30): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(31): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(32): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(33): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(34): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(35): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(layer4): Sequential(
(0): Bottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
(fc): Linear(in_features=2048, out_features=1000, bias=True)
)

建立模型

# ----------------4. 参考PyTorch官网例子------------------

def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):
  # 选择合适的模型，不同模型的初始化方法稍微有点区别
  model_ft = None
  input_size = 0

  if model_name == "resnet":
      """ Resnet152
      """
      model_ft = models.resnet152(pretrained=use_pretrained)
      set_parameter_requires_grad(model_ft, feature_extract)
      num_ftrs = model_ft.fc.in_features
      model_ft.fc = nn.Sequential(nn.Linear(num_ftrs, 102),
                                 nn.LogSoftmax(dim=1))
      input_size = 224

  elif model_name == "alexnet":
      """ Alexnet
      """
      model_ft = models.alexnet(pretrained=use_pretrained)
      set_parameter_requires_grad(model_ft, feature_extract)
      num_ftrs = model_ft.classifier[6].in_features
      model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
      input_size = 224

  elif model_name == "vgg":
      """ VGG11_bn
      """
      model_ft = models.vgg16(pretrained=use_pretrained)
      set_parameter_requires_grad(model_ft, feature_extract)
      num_ftrs = model_ft.classifier[6].in_features
      model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
      input_size = 224

  elif model_name == "squeezenet":
      """ Squeezenet
      """
      model_ft = models.squeezenet1_0(pretrained=use_pretrained)
      set_parameter_requires_grad(model_ft, feature_extract)
      model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1))
      model_ft.num_classes = num_classes
      input_size = 224

  elif model_name == "densenet":
      """ Densenet
      """
      model_ft = models.densenet121(pretrained=use_pretrained)
      set_parameter_requires_grad(model_ft, feature_extract)
      num_ftrs = model_ft.classifier.in_features
      model_ft.classifier = nn.Linear(num_ftrs, num_classes)
      input_size = 224

  elif model_name == "inception":
      """ Inception v3
      Be careful, expects (299,299) sized images and has auxiliary output
      """
      model_ft = models.inception_v3(pretrained=use_pretrained)
      set_parameter_requires_grad(model_ft, feature_extract)
      # Handle the auxilary net
      num_ftrs = model_ft.AuxLogits.fc.in_features
      model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes)
      # Handle the primary net
      num_ftrs = model_ft.fc.in_features
      model_ft.fc = nn.Linear(num_ftrs,num_classes)
      input_size = 299

  else:
      print("Invalid model name, exiting...")
      exit()

  return model_ft, input_size

设置哪些层需要训练

# ----------------5. 设置哪些层需要训练------------------

model_ft, input_size = initialize_model(model_name, 102, feature_extract, use_pretrained=True)

# GPU计算
model_ft = model_ft.to(device)

# 模型保存
filename='checkpoint.pth'

# 是否训练所有层
params_to_update = model_ft.parameters()
print("Params to learn:")
if feature_extract:
  params_to_update = []
  for name,param in model_ft.named_parameters():
      if param.requires_grad == True:
          params_to_update.append(param)
          print("\t",name)
else:
  for name,param in model_ft.named_parameters():
      if param.requires_grad == True:
          print("\t",name)

优化器设置

# ----------------6. 优化器设置------------------

# 优化器设置
optimizer_ft = optim.Adam(params_to_update, lr=1e-2)
scheduler = optim.lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)  # 学习率每7个epoch衰减成原来的1/10

# 最后一层已经LogSoftmax()了，所以不能nn.CrossEntropyLoss()来计算了
# nn.CrossEntropyLoss()相当于logSoftmax()和nn.NLLLoss()整合
criterion = nn.NLLLoss()

训练模块

# ----------------7. 训练模块------------------

def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False, filename=filename):
  since = time.time()
  best_acc = 0
  """
  checkpoint = torch.load(filename)
  best_acc = checkpoint['best_acc']
  model.load_state_dict(checkpoint['state_dict'])
  optimizer.load_state_dict(checkpoint['optimizer'])
  model.class_to_idx = checkpoint['mapping']
  """
  model.to(device)

  val_acc_history = []
  train_acc_history = []
  train_losses = []
  valid_losses = []
  LRs = [optimizer.param_groups[0]['lr']]

  best_model_wts = copy.deepcopy(model.state_dict())

  for epoch in range(num_epochs):
      print('Epoch {}/{}'.format(epoch, num_epochs - 1))
      print('-' * 10)

      # 训练和验证
      for phase in ['train', 'valid']:
          if phase == 'train':
              model.train()  # 训练
          else:
              model.eval()  # 验证

          running_loss = 0.0
          running_corrects = 0

          # 把数据都取个遍
          for inputs, labels in dataloaders[phase]:
              inputs = inputs.to(device)
              labels = labels.to(device)

              # 清零
              optimizer.zero_grad()
              # 只有训练的时候计算和更新梯度
              with torch.set_grad_enabled(phase == 'train'):
                  if is_inception and phase == 'train':
                      outputs, aux_outputs = model(inputs)
                      loss1 = criterion(outputs, labels)
                      loss2 = criterion(aux_outputs, labels)
                      loss = loss1 + 0.4 * loss2
                  else:  # resnet执行的是这里
                      outputs = model(inputs)
                      loss = criterion(outputs, labels)

                  _, preds = torch.max(outputs, 1)

                  # 训练阶段更新权重
                  if phase == 'train':
                      loss.backward()
                      optimizer.step()

              # 计算损失
              running_loss += loss.item() * inputs.size(0)
              running_corrects += torch.sum(preds == labels.data)

          epoch_loss = running_loss / len(dataloaders[phase].dataset)
          epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)

          time_elapsed = time.time() - since
          print('Time elapsed {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
          print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))

          # 得到最好那次的模型
          if phase == 'valid' and epoch_acc > best_acc:
              best_acc = epoch_acc
              best_model_wts = copy.deepcopy(model.state_dict())
              state = {
                  'state_dict': model.state_dict(),
                  'best_acc': best_acc,
                  'optimizer': optimizer.state_dict(),
              }
              torch.save(state, filename)
          if phase == 'valid':
              val_acc_history.append(epoch_acc)
              valid_losses.append(epoch_loss)
              scheduler.step(epoch_loss)
          if phase == 'train':
              train_acc_history.append(epoch_acc)
              train_losses.append(epoch_loss)

      print('Optimizer learning rate : {:.7f}'.format(optimizer.param_groups[0]['lr']))
      LRs.append(optimizer.param_groups[0]['lr'])
      print()

  time_elapsed = time.time() - since
  print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
  print('Best val Acc: {:4f}'.format(best_acc))

  # 训练完后用最好的一次当做模型最终的结果
  model.load_state_dict(best_model_wts)
  return model, val_acc_history, train_acc_history, valid_losses, train_losses, LRs

开始训练

# ----------------8. 开始训练------------------

# 训练
model_ft, val_acc_history, train_acc_history, valid_losses, train_losses, LRs  = \
  train_model(model_ft, dataloaders, criterion, optimizer_ft, num_epochs=20, is_inception=(model_name=="inception"))

# 再继续训练所有层
for param in model_ft.parameters():
  param.requires_grad = True

# 再继续训练所有的参数，学习率调小一点
optimizer = optim.Adam(params_to_update, lr=1e-4)
scheduler = optim.lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)

# 损失函数
criterion = nn.NLLLoss()

# Load the checkpoint

checkpoint = torch.load(filename)
best_acc = checkpoint['best_acc']
model_ft.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
#model_ft.class_to_idx = checkpoint['mapping']

model_ft, val_acc_history, train_acc_history, valid_losses, train_losses, LRs  = train_model(model_ft, dataloaders, criterion, optimizer, num_epochs=10, is_inception=(model_name=="inception"))

输出结果:
Epoch 0/9
----------
Time elapsed 3m 8s
train Loss: 1.8128 Acc: 0.8065
Time elapsed 3m 17s
valid Loss: 4.6786 Acc: 0.6993
Optimizer learning rate : 0.0010000

Epoch 1/9
----------
Time elapsed 6m 26s
train Loss: 1.5370 Acc: 0.8268
Time elapsed 6m 34s
valid Loss: 4.3483 Acc: 0.7017
Optimizer learning rate : 0.0010000

Epoch 2/9
----------
Time elapsed 9m 44s
train Loss: 1.3812 Acc: 0.8367
Time elapsed 9m 52s
valid Loss: 4.0840 Acc: 0.7127
Optimizer learning rate : 0.0010000

Epoch 3/9
----------
Time elapsed 13m 2s
train Loss: 1.4777 Acc: 0.8312
Time elapsed 13m 10s
valid Loss: 4.2493 Acc: 0.7078
Optimizer learning rate : 0.0010000

Epoch 4/9
----------
Time elapsed 16m 22s
train Loss: 1.3351 Acc: 0.8434
Time elapsed 16m 31s
valid Loss: 3.6103 Acc: 0.7396
Optimizer learning rate : 0.0010000

Epoch 5/9
----------
Time elapsed 19m 42s
train Loss: 1.2934 Acc: 0.8466
Time elapsed 19m 51s
valid Loss: 3.3350 Acc: 0.7494
Optimizer learning rate : 0.0010000

Epoch 6/9
----------
Time elapsed 23m 2s
train Loss: 1.3289 Acc: 0.8379
Time elapsed 23m 11s
valid Loss: 3.9728 Acc: 0.7164
Optimizer learning rate : 0.0010000

Epoch 7/9
----------
Time elapsed 26m 22s
train Loss: 1.3739 Acc: 0.8321
Time elapsed 26m 31s
valid Loss: 3.7483 Acc: 0.7237
Optimizer learning rate : 0.0010000

Epoch 8/9
----------
Time elapsed 29m 43s
train Loss: 1.2110 Acc: 0.8495
Time elapsed 29m 52s
valid Loss: 3.7712 Acc: 0.7164
Optimizer learning rate : 0.0010000

Epoch 9/9
----------
Time elapsed 33m 2s
train Loss: 1.2643 Acc: 0.8452
Time elapsed 33m 11s
valid Loss: 3.7012 Acc: 0.7311
Optimizer learning rate : 0.0010000

Training complete in 33m 11s
Best val Acc: 0.749389

 

测试

测试网络效果

# ----------------9. 测试网络效果------------------

probs, classes = predict(image_path, model)
print(probs)
print(classes)

输出结果:
[ 0.01558163 0.01541934 0.01452626 0.01443549 0.01407339]
['70', '3', '45', '62', '55']

测试训练好的模型

# ----------------10. 测试训练好的模型------------------

model_ft, input_size = initialize_model(model_name, 102, feature_extract, use_pretrained=True)

# GPU模式
model_ft = model_ft.to(device)

# 保存文件的名字
filename = 'seriouscheckpoint.pth'

# 加载模型
checkpoint = torch.load(filename)
best_acc = checkpoint['best_acc']
model_ft.load_state_dict(checkpoint['state_dict'])

测试数据预处理

注意:

1. 测试数据处理方法需要跟训练时一致才可以
2. crop 操作的目的是保证输入的大小是一致的
3. 标准化也是必须的, 用跟训练数据相同的 mean 和 std
4. 训练数据是在 0~1 上进行标准化, 所以测试数据也需要先归一化
5. PyTorch 中的颜色是第一个维度, 跟很多工具包都不一样, 需要转换

# ----------------11. 测试数据预处理------------------

def process_image(image_path):
  # 读取测试数据
  img = Image.open(image_path)
  # Resize,thumbnail方法只能进行缩小，所以进行了判断
  if img.size[0] > img.size[1]:
      img.thumbnail((10000, 256))
  else:
      img.thumbnail((256, 10000))
  # Crop操作
  left_margin = (img.width - 224) / 2
  bottom_margin = (img.height - 224) / 2
  right_margin = left_margin + 224
  top_margin = bottom_margin + 224
  img = img.crop((left_margin, bottom_margin, right_margin,
                  top_margin))
  # 相同的预处理方法
  img = np.array(img) / 255
  mean = np.array([0.485, 0.456, 0.406])  # provided mean
  std = np.array([0.229, 0.224, 0.225])  # provided std
  img = (img - mean) / std

  # 注意颜色通道应该放在第一个位置
  img = img.transpose((2, 0, 1))

  return img


def imshow(image, ax=None,  """展示数据"""
  if ax is None:
      fig, ax = plt.subplots()

  # 颜色通道还原
  image = np.array(image).transpose((1, 2, 0))

  # 预处理还原
  mean = np.array([0.485, 0.456, 0.406])
  std = np.array([0.229, 0.224, 0.225])
  image = std * image + mean
  image = np.clip(image, 0, 1)

  ax.imshow(image)
  ax.set_title(title)

  return ax

image_path = 'image_06621.jpg'
img = process_image(image_path)
imshow(img)

# 得到一个batch的测试数据
dataiter = iter(dataloaders['valid'])
images, labels = dataiter.next()

model_ft.eval()

if train_on_gpu:
  output = model_ft(images.cuda())
else:
  output = model_ft(images)

_, preds_tensor = torch.max(output, 1)

preds = np.squeeze(preds_tensor.numpy()) if not train_on_gpu else np.squeeze(preds_tensor.cpu().numpy())

展示预测结果

# ----------------12. 展示预测结果------------------

fig=plt.figure(figsize=(20, 20))
columns =4
rows = 2

for idx in range (columns*rows):
  ax = fig.add_subplot(rows, columns, idx+1, xticks=[], yticks=[])
  plt.imshow(im_convert(images[idx]))
  ax.set_title("{} ({})".format(cat_to_name[str(preds[idx])], cat_to_name[str(labels[idx].item())]),
               color=("green" if cat_to_name[str(preds[idx])]==cat_to_name[str(labels[idx].item())] else "red"))
plt.show()

输出结果:

到此这篇关于PyTorch一小时掌握之图像识别实战篇的文章就介绍到这了,更多相关PyTorch图像识别内容请搜索服务器之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持服务器之家！

原文链接：https://iamarookie.blog.csdn.net/article/details/114309226