做李宏毅作业3的时候,运行了baseline,简单的4个卷积层加批标准化层加最大池化层,最后加一个全连接层,用crossentropyloss去做一个多分类问题。能优化的地方一个是对数据集加强,用transform对已经有标签的图片进行一些随机的变换,每次训练的同一个图片都是有略微差别的,加了这个后分数确实提高一点了。后面就是在全连接层前面加了一个dropout层,分数也有提升。再往下的话看别人的说法,就是去使用ResNet残差神经网络,Test Time Augmentation(TTA)TTA是在test阶段的数据增强,即在预测的时候将原图变换出来的多张图片分别进行分类,再综合分类结果的方法。还有Cross Validation + Ensemble,机器学习里常用的k折交叉验证,这里也派上用场,这里是通过k折,将数据拆分成k份从而训练出k个相对独立的模型,再采用Ensemble方法提升精度。Ensemble说穿了也很简单,就是把多个模型输出的结果做一个整合,有很多方法可选,我用的是输出平均。不过很多优化都还没有实现,回头有时间补上。还有就是两个坑点,这个代码pytorch版本不够新运行不动,还有colab上的baseline是基于linux和unix的,dataset的getitem取lable的时候,分割文件名用的'/',在window环境运行下会识别不出来。
_exp_name = "sample"
# Import necessary packages.
import numpy as np
import pandas as pd
import torch
import os
import torch.nn as nn
import torchvision.transforms as transforms
from PIL import Image
# "ConcatDataset" and "Subset" are possibly useful when doing semi-supervised learning.
from torch.utils.data import ConcatDataset, DataLoader, Subset, Dataset
from torchvision.datasets import DatasetFolder, VisionDataset
# This is for the progress bar.
from tqdm.auto import tqdm
import random
myseed = 6666 # set a random seed for reproducibility
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
np.random.seed(myseed)
torch.manual_seed(myseed)
if torch.cuda.is_available():
torch.cuda.manual_seed_all(myseed)
# Normally, We don't need augmentations in testing and validation.
# All we need here is to resize the PIL image and transform it into Tensor.
test_tfm = transforms.Compose([
transforms.Resize((128, 128)),
transforms.ToTensor(),
])
# However, it is also possible to use augmentation in the testing phase.
# You may use train_tfm to produce a variety of images and then test using ensemble methods
train_tfm = transforms.Compose([
# Resize the image into a fixed shape (height = width = 128)
transforms.Resize((128, 128)),
# You may add some transforms here.
transforms.RandomHorizontalFlip(),#随机将图片水平翻转
transforms.RandomRotation(15),#随机旋转图片
transforms.GaussianBlur(3, 0.1),
transforms.ColorJitter(brightness=0.5, hue=0.3),
transforms.RandomInvert(p=0.5),
# ToTensor() should be the last one of the transforms.
transforms.ToTensor(),
])
class FoodDataset(Dataset):
def __init__(self,path,tfm=test_tfm,files = None):
super(FoodDataset).__init__()
self.path = path
self.files = sorted([os.path.join(path,x) for x in os.listdir(path) if x.endswith(".jpg")])
if files != None:
self.files = files
self.transform = tfm
def __len__(self):
return len(self.files)
def __getitem__(self,idx):
fname = self.files[idx]
im = Image.open(fname)
im = self.transform(im)
try:
label = int(os.path.split(fname)[-1].split("_")[0])
except:
label = -1 # test has no label
return im,label
class Classifier(nn.Module):
def __init__(self):
super(Classifier, self).__init__()
# torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding)
# torch.nn.MaxPool2d(kernel_size, stride, padding)
# input 維度 [3, 128, 128]
self.cnn = nn.Sequential(
nn.Conv2d(3, 64, 3, 1, 1), # [64, 128, 128]
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(2, 2, 0), # [64, 64, 64]
nn.Conv2d(64, 128, 3, 1, 1), # [128, 64, 64]
nn.BatchNorm2d(128),
nn.ReLU(),
nn.MaxPool2d(2, 2, 0), # [128, 32, 32]
nn.Conv2d(128, 256, 3, 1, 1), # [256, 32, 32]
nn.BatchNorm2d(256),
nn.ReLU(),
nn.MaxPool2d(2, 2, 0), # [256, 16, 16]
nn.Conv2d(256, 512, 3, 1, 1), # [512, 16, 16]
nn.BatchNorm2d(512),
nn.ReLU(),
nn.MaxPool2d(2, 2, 0), # [512, 8, 8]
nn.Conv2d(512, 512, 3, 1, 1), # [512, 8, 8]
nn.BatchNorm2d(512),
nn.ReLU(),
nn.MaxPool2d(2, 2, 0), # [512, 4, 4]
nn.Conv2d(512, 256, 3, 1, 1), # [256, 4, 4]
nn.BatchNorm2d(256),
nn.ReLU(),
)
self.fc = nn.Sequential(
nn.Dropout(0.5),
nn.Linear(256*4*4, 1024),
nn.ReLU(),
nn.Linear(1024, 512),
nn.ReLU(),
nn.Linear(512, 11)
)
def forward(self, x):
out = self.cnn(x)
out = out.view(out.size()[0], -1)
return self.fc(out)
# "cuda" only when GPUs are available.
device = "cuda" if torch.cuda.is_available() else "cpu"
# Initialize a model, and put it on the device specified.
model = Classifier().to(device)
# The number of batch size.
batch_size = 128
# The number of training epochs.
n_epochs = 20
# If no improvement in 'patience' epochs, early stop.
patience = 5
# For the classification task, we use cross-entropy as the measurement of performance.
criterion = nn.CrossEntropyLoss()
# Initialize optimizer, you may fine-tune some hyperparameters such as learning rate on your own.
optimizer = torch.optim.Adam(model.parameters(), lr=0.0003, weight_decay=1e-5)
# Construct train and valid datasets.
# The argument "loader" tells how torchvision reads the data.
train_set = FoodDataset("./train", tfm=train_tfm)
train_loader = DataLoader(train_set, batch_size=batch_size, shuffle=True, num_workers=0, pin_memory=True)
valid_set = FoodDataset("./valid", tfm=test_tfm)
valid_loader = DataLoader(valid_set, batch_size=batch_size, shuffle=True, num_workers=0, pin_memory=True)
# Initialize trackers, these are not parameters and should not be changed
stale = 0
best_acc = 0
for epoch in range(n_epochs):
# ---------- Training ----------
# Make sure the model is in train mode before training.
model.train()
# These are used to record information in training.
train_loss = []
train_accs = []
for batch in tqdm(train_loader):
# A batch consists of image data and corresponding labels.
imgs, labels = batch
#imgs = imgs.half()
#print(imgs.shape,labels.shape)
# Forward the data. (Make sure data and model are on the same device.)
logits = model(imgs.to(device))
# Calculate the cross-entropy loss.
# We don't need to apply softmax before computing cross-entropy as it is done automatically.
loss = criterion(logits, labels.to(device))
# Gradients stored in the parameters in the previous step should be cleared out first.
optimizer.zero_grad()
# Compute the gradients for parameters.
loss.backward()
# Clip the gradient norms for stable training.
grad_norm = nn.utils.clip_grad_norm_(model.parameters(), max_norm=10)
# Update the parameters with computed gradients.
optimizer.step()
# Compute the accuracy for current batch.
acc = (logits.argmax(dim=-1) == labels.to(device)).float().mean()
# Record the loss and accuracy.
train_loss.append(loss.item())
train_accs.append(acc)
train_loss = sum(train_loss) / len(train_loss)
train_acc = sum(train_accs) / len(train_accs)
# Print the information.
print(f"[ Train | {epoch + 1:03d}/{n_epochs:03d} ] loss = {train_loss:.5f}, acc = {train_acc:.5f}")
# ---------- Validation ----------
# Make sure the model is in eval mode so that some modules like dropout are disabled and work normally.
model.eval()
# These are used to record information in validation.
valid_loss = []
valid_accs = []
# Iterate the validation set by batches.
for batch in tqdm(valid_loader):
# A batch consists of image data and corresponding labels.
imgs, labels = batch
#imgs = imgs.half()
# We don't need gradient in validation.
# Using torch.no_grad() accelerates the forward process.
with torch.no_grad():
logits = model(imgs.to(device))
# We can still compute the loss (but not the gradient).
loss = criterion(logits, labels.to(device))
# Compute the accuracy for current batch.
acc = (logits.argmax(dim=-1) == labels.to(device)).float().mean()
# Record the loss and accuracy.
valid_loss.append(loss.item())
valid_accs.append(acc)
#break
# The average loss and accuracy for entire validation set is the average of the recorded values.
valid_loss = sum(valid_loss) / len(valid_loss)
valid_acc = sum(valid_accs) / len(valid_accs)
# Print the information.
print(f"[ Valid | {epoch + 1:03d}/{n_epochs:03d} ] loss = {valid_loss:.5f}, acc = {valid_acc:.5f}")
# update logs
if valid_acc > best_acc:
with open(f"./{_exp_name}_log.txt","a"):
print(f"[ Valid | {epoch + 1:03d}/{n_epochs:03d} ] loss = {valid_loss:.5f}, acc = {valid_acc:.5f} -> best")
else:
with open(f"./{_exp_name}_log.txt","a"):
print(f"[ Valid | {epoch + 1:03d}/{n_epochs:03d} ] loss = {valid_loss:.5f}, acc = {valid_acc:.5f}")
# save models
if valid_acc > best_acc:
print(f"Best model found at epoch {epoch}, saving model")
torch.save(model.state_dict(), f"{_exp_name}_best.ckpt") # only save best to prevent output memory exceed error
best_acc = valid_acc
stale = 0
else:
stale += 1
if stale > patience:
print(f"No improvment {patience} consecutive epochs, early stopping")
break
# Construct test datasets.
# The argument "loader" tells how torchvision reads the data.
test_set = FoodDataset("./test", tfm=test_tfm)
test_loader = DataLoader(test_set, batch_size=batch_size, shuffle=False, num_workers=0, pin_memory=True)
model_best = Classifier().to(device)
model_best.load_state_dict(torch.load(f"{_exp_name}_best.ckpt"))
model_best.eval()
prediction = []
with torch.no_grad():
for data,_ in tqdm(test_loader):
test_pred = model_best(data.to(device))
test_label = np.argmax(test_pred.cpu().data.numpy(), axis=1)
prediction += test_label.squeeze().tolist()
# create test csv
def pad4(i):
return "0"*(4-len(str(i)))+str(i)
df = pd.DataFrame()
df["Id"] = [pad4(i) for i in range(len(test_set))]
df["Category"] = prediction
df.to_csv("submission.csv",index = False)