import numpy as np
import matplotlib.pyplot as plt
import os
import torch
import torch.nn as nn
import torchvision
from torchvision import models,transforms,datasets
import time
import json
# 判断是否存在GPU设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print('Using gpu: %s ' % torch.cuda.is_available())
Using gpu: False
Jeremy Howard 提供了数据的下载,链接为:http://files.fast.ai/data/dogscats.zip
在他整理的数据集中,猫和狗的图片放在单独的文件夹中, 同时还提供了一个Validation数据。如果没有GPU设备,请减少用做训练的图像数据量即可。
因为这个代码需要在colab上跑,速度会相对较慢。因此,我们重新整理了数据,制作了新的数据集,训练集包含1800张图(猫的图片900张,狗的图片900张),测试集包含2000张图。下载地址为:http://fenggao-image.stor.sinaapp.com/dogscats.zip
import wget
#引入基本的库
url='http://fenggao-image.stor.sinaapp.com/dogscats.zip'
file_name=wget.download(url)
print(file_name)
import zipfile
import os
src_path='dogscats.zip'
target_path='dogscats'
if(not os.path.isdir(target_path+"/Images")):
z = zipfile.ZipFile(src_path, 'r')
z.extractall(path=target_path)
z.close()
else:
print("文件已解压")
``
注意:这里要变化一下,如果直接用! wget +地址来下载的话,报错
datasets 是 torchvision 中的一个包,可以用做加载图像数据。它可以以多线程(multi-thread)的形式从硬盘中读取数据,使用 mini-batch 的形式,在网络训练中向 GPU 输送。在使用CNN处理图像时,需要进行预处理。图片将被整理成 224 × 224 × 3 224\times 224 \times 3 224×224×3 的大小,同时还将进行归一化处理。
torchvision 支持对输入数据进行一些复杂的预处理/变换 (normalization, cropping, flipping, jittering 等)。
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
vgg_format = transforms.Compose([
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize,
])
data_dir = './dogscats'
dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), vgg_format)
for x in ['train', 'valid']}
dset_sizes = {x: len(dsets[x]) for x in ['train', 'valid']}
dset_classes = dsets['train'].classes
print(dsets[‘train’].classes)#分的文件夹的名字下的类别
print(dsets[‘train’].class_to_idx)#按顺序为这些类别定义索引为0,1,2,…
print(dsets[‘train’].imgs[:5])#返回从文件下中得到的图片的路径以及其类别
print('dset_sizes: ', dset_sizes)#返回该文件夹的内的图片数量
# 通过下面代码可以查看 dsets 的一些属性
print(dsets['train'].classes)
print(dsets['train'].class_to_idx)
print(dsets['train'].imgs[:5])
print('dset_sizes: ', dset_sizes)
torch.utils.data.DataLoader主要是对数据进行batch的划分,
batch_size批训练集的大小
num_workers:多线程来读数据
shuffle:是否打乱数据
使用DataLoader的好处是,可以快速的迭代数据。
loader_train = torch.utils.data.DataLoader(dsets['train'], batch_size=64, shuffle=True, num_workers=6)
loader_valid = torch.utils.data.DataLoader(dsets['valid'], batch_size=5, shuffle=False, num_workers=6)
'''
valid 数据一共有2000张图,每个batch是5张,因此,下面进行遍历一共会输出到 400
同时,把第一个 batch 保存到 inputs_try, labels_try,分别查看
'''
count = 1
for data in loader_valid:
print(count, end='\n')
if count == 1:
inputs_try,labels_try = data
count +=1
print(labels_try)
print(inputs_try.shape)
# 显示图片的小程序
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 = np.clip(std * inp + mean, 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
# 显示 labels_try 的5张图片,即valid里第一个batch的5张图片
out = torchvision.utils.make_grid(inputs_try)
imshow(out, title=[dset_classes[x] for x in labels_try])
torchvision中集成了很多在 ImageNet (120万张训练数据) 上预训练好的通用的CNN模型,可以直接下载使用。
在本课程中,我们直接使用预训练好的 VGG 模型。同时,为了展示 VGG 模型对本数据的预测结果,还下载了 ImageNet 1000 个类的 JSON 文件。
在这部分代码中,对输入的5个图片利用VGG模型进行预测,同时,使用softmax对结果进行处理,随后展示了识别结果。可以看到,识别结果是比较非常准确的。
import wget
url='https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json'
file_name=wget.download(url)
print(file_name)
imagenet_class_index.json
这里也是一样的下载格式
model_vgg = models.vgg16(pretrained=True)
with open('./imagenet_class_index.json') as f:
class_dict = json.load(f)
dic_imagenet = [class_dict[str(i)][1] for i in range(len(class_dict))]
inputs_try , labels_try = inputs_try.to(device), labels_try.to(device)
model_vgg = model_vgg.to(device)
outputs_try = model_vgg(inputs_try)
print(outputs_try)
print(outputs_try.shape)
'''
可以看到结果为5行,1000列的数据,每一列代表对每一种目标识别的结果。
但是我也可以观察到,结果非常奇葩,有负数,有正数,
为了将VGG网络输出的结果转化为对每一类的预测概率,我们把结果输入到 Softmax 函数
'''
m_softm = nn.Softmax(dim=1)
probs = m_softm(outputs_try)
vals_try,pred_try = torch.max(probs,dim=1)
print( 'prob sum: ', torch.sum(probs,1))
print( 'vals_try: ', vals_try)
print( 'pred_try: ', pred_try)
print([dic_imagenet[i] for i in pred_try.data])
imshow(torchvision.utils.make_grid(inputs_try.data.cpu()),
title=[dset_classes[x] for x in labels_try.data.cpu()])
VGG 模型如下图所示,注意该网络由三种元素组成:
卷积层(CONV)是发现图像中局部的 pattern
全连接层(FC)是在全局上建立特征的关联
池化(Pool)是给图像降维以提高特征的 invariance
VGG
我们的目标是使用预训练好的模型,因此,需要把最后的 nn.Linear 层由1000类,替换为2类。为了在训练中冻结前面层的参数,需要设置 required_grad=False。这样,反向传播训练梯度时,前面层的权重就不会自动更新了。训练中,只会更新最后一层的参数。
print(model_vgg)
model_vgg_new = model_vgg;
for param in model_vgg_new.parameters():
param.requires_grad = False
model_vgg_new.classifier._modules['6'] = nn.Linear(4096, 2)
model_vgg_new.classifier._modules['7'] = torch.nn.LogSoftmax(dim = 1)
model_vgg_new = model_vgg_new.to(device)
print(model_vgg_new.classifier)
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(18): ReLU(inplace=True)
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(25): ReLU(inplace=True)
(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): ReLU(inplace=True)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=1000, bias=True)
)
)
Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=2, bias=True)
(7): LogSoftmax()
)
包括三个步骤:第1步,创建损失函数和优化器;第2步,训练模型;第3步,测试模型。
'''
第一步:创建损失函数和优化器
损失函数 NLLLoss() 的 输入 是一个对数概率向量和一个目标标签.
它不会为我们计算对数概率,适合最后一层是log_softmax()的网络.
'''
criterion = nn.NLLLoss()
# 学习率
lr = 0.001
# 随机梯度下降
optimizer_vgg = torch.optim.SGD(model_vgg_new.classifier[6].parameters(),lr = lr)
'''
第二步:训练模型
'''
def train_model(model,dataloader,size,epochs=1,optimizer=None):
model.train()
for epoch in range(epochs):
running_loss = 0.0
running_corrects = 0
count = 0
for inputs,classes in dataloader:
inputs = inputs.to(device)
classes = classes.to(device)
outputs = model(inputs)
loss = criterion(outputs,classes)
optimizer = optimizer
optimizer.zero_grad()
loss.backward()
optimizer.step()
_,preds = torch.max(outputs.data,1)
# statistics
running_loss += loss.data.item()
running_corrects += torch.sum(preds == classes.data)
count += len(inputs)
print('Training: No. ', count, ' process ... total: ', size)
epoch_loss = running_loss / size
epoch_acc = running_corrects.data.item() / size
print('Loss: {:.4f} Acc: {:.4f}'.format(
epoch_loss, epoch_acc))
# 模型训练
train_model(model_vgg_new,loader_train,size=dset_sizes['train'], epochs=1,
optimizer=optimizer_vgg
运行结果:
def test_model(model,dataloader,size):
model.eval()
predictions = np.zeros(size)
all_classes = np.zeros(size)
all_proba = np.zeros((size,2))
i = 0
running_loss = 0.0
running_corrects = 0
for inputs,classes in dataloader:
inputs = inputs.to(device)
classes = classes.to(device)
outputs = model(inputs)
loss = criterion(outputs,classes)
_,preds = torch.max(outputs.data,1)
# statistics
running_loss += loss.data.item()
running_corrects += torch.sum(preds == classes.data)
predictions[i:i+len(classes)] = preds.to('cpu').numpy()
all_classes[i:i+len(classes)] = classes.to('cpu').numpy()
all_proba[i:i+len(classes),:] = outputs.data.to('cpu').numpy()
i += len(classes)
print('Testing: No. ', i, ' process ... total: ', size)
epoch_loss = running_loss / size
epoch_acc = running_corrects.data.item() / size
print('Loss: {:.4f} Acc: {:.4f}'.format(
epoch_loss, epoch_acc))
return predictions, all_proba, all_classes
predictions, all_proba, all_classes = test_model(model_vgg_new,loader_valid,size=dset_sizes['valid']
主观分析就是把预测的结果和相对应的测试图像输出出来看看,一般有四种方式:
随机查看一些预测正确的图片
随机查看一些预测错误的图片
预测正确,同时具有较大的probability的图片
预测错误,同时具有较大的probability的图片
最不确定的图片,比如说预测概率接近0.5的图片
predictions, all_proba, all_classes = test_model(model_vgg_new,loader_valid,size=dset_sizes['valid'])
# 单次可视化显示的图片个数
n_view = 8
correct = np.where(predictions==all_classes)[0]
from numpy.random import random, permutation
idx = permutation(correct)[:n_view]
print('random correct idx: ', idx)
loader_correct = torch.utils.data.DataLoader([dsets['valid'][x] for x in idx],
batch_size = n_view,shuffle=True)
for data in loader_correct:
inputs_cor,labels_cor = data
# Make a grid from batch
out = torchvision.utils.make_grid(inputs_cor)
imshow(out, title=[l.item() for l in labels_cor])
'''
torch.utils.data.DataLoader主要是对数据进行batch的划分,
batch_size批训练集的大小
num_workers:多线程来读数据
shuffle:是否打乱数据
'''
#使用DataLoader的好处是,可以快速的迭代数据。
loader_train = torch.utils.data.DataLoader(dsets['train'], batch_size=64, shuffle=True, num_workers=6)
loader_valid = torch.utils.data.DataLoader(dsets['valid'], batch_size=5, shuffle=False, num_workers=6)
loader_test = torch.utils.data.DataLoader(dsets['test'], batch_size=5, shuffle=False, num_workers=6)
'''
valid 数据一共有2000张图,每个batch是5张,因此,下面进行遍历一共会输出到 400
同时,把第一个 batch 保存到 inputs_try, labels_try,分别查看
'''
count = 1
for data in loader_valid:
print(count, end='\n')
if count == 1:#第一个batch保存到inputs_try,labels_try
inputs_try,labels_try = data
count +=1
print(labels_try)
print(inputs_try.shape)#
'''
第一步:创建损失函数和优化器
'''
criterion = nn.NLLLoss()
# 学习率
lr = 0.001
# 随机梯度下降
optimizer_vgg = torch.optim.SGD(model_vgg_new.classifier[6].parameters(),lr = lr)
'''
第二步:训练模型
'''
def train_model(model,dataloader,size,epochs=1,optimizer=None):
model.train()
for epoch in range(epochs):
running_loss = 0.0
running_corrects = 0
count = 0
for inputs,classes in dataloader:
inputs = inputs.to(device)
classes = classes.to(device)
outputs = model(inputs)
loss = criterion(outputs,classes)
optimizer = optimizer
optimizer.zero_grad()
loss.backward()
optimizer.step()
_,preds = torch.max(outputs.data,1)
# statistics
running_loss += loss.data.item()
running_corrects += torch.sum(preds == classes.data)
count += len(inputs)
print('Training: No. ', count, ' process ... total: ', size)
epoch_loss = running_loss / size
epoch_acc = running_corrects.data.item() / size
print('Loss: {:.4f} Acc: {:.4f}'.format(
epoch_loss, epoch_acc))
# 模型训练
#导入loader_train数据集进行训练
train_model(model_vgg_new,loader_train,size=dset_sizes['train'], epochs=1,
optimizer=optimizer_vgg)
通过本次使用VGG模型进行猫狗大战实验的练习以及AI研习社猫狗大战练习,发现python是真的很强大啊,开始写代码之前要先想想需要解决的问题是啥,属于哪一类,应该用啥方法,需要用到哪些库,用法,查查查吧,强大功能自然少不了丰富的资源知识,学无止境!