寒假PyTorch工具第九天

课程记录

从学习率机制到tensorboard

---

课程代码

无

---

作业

1.   可视化任意网络模型训练的Loss，及Accuracy曲线图，Train与Valid必须在同一个图中

2.   采用make_grid，对任意图像训练输入数据进行批量可视化

作业参考: 

1. 准确率曲线

未在服务器跑, 只读

# -*- coding:utf-8 -*-
"""
@brief      : 监控loss, accuracy, weights, gradients
"""
import os
import numpy as np
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
from torch.utils.tensorboard import SummaryWriter
import torch.optim as optim
from matplotlib import pyplot as plt
from model.lenet import LeNet
from tools.my_dataset import RMBDataset
from tools.common_tools2 import set_seed

set_seed()  # 设置随机种子
rmb_label = {"1": 0, "100": 1}

# 参数设置
MAX_EPOCH = 10
BATCH_SIZE = 16
LR = 0.01
log_interval = 10
val_interval = 1

# ============================ step 1/5 数据 ============================

split_dir = os.path.join("..", "data", "rmb_split")
train_dir = os.path.join(split_dir, "train")
valid_dir = os.path.join(split_dir, "valid")

norm_mean = [0.485, 0.456, 0.406]
norm_std = [0.229, 0.224, 0.225]

train_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.RandomCrop(32, padding=4),
    transforms.RandomGrayscale(p=0.8),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

valid_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

# 构建MyDataset实例
train_data = RMBDataset(data_dir=train_dir, transform=train_transform)
valid_data = RMBDataset(data_dir=valid_dir, transform=valid_transform)

# 构建DataLoder
train_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)

# ============================ step 2/5 模型 ============================

net = LeNet(classes=2)
net.initialize_weights()

# ============================ step 3/5 损失函数 ============================
criterion = nn.CrossEntropyLoss()  # 选择损失函数

# ============================ step 4/5 优化器 ============================
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9)  # 选择优化器
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)  # 设置学习率下降策略

# ============================ step 5/5 训练 ============================
train_curve = list()
valid_curve = list()

iter_count = 0

# 构建 SummaryWriter
writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")

for epoch in range(MAX_EPOCH):

    loss_mean = 0.
    correct = 0.
    total = 0.

    net.train()
    for i, data in enumerate(train_loader):

        iter_count += 1

        # forward
        inputs, labels = data
        outputs = net(inputs)

        # backward
        optimizer.zero_grad()
        loss = criterion(outputs, labels)
        loss.backward()

        # update weights
        optimizer.step()

        # 统计分类情况
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).squeeze().sum().numpy()

        # 打印训练信息
        loss_mean += loss.item()
        train_curve.append(loss.item())
        if (i + 1) % log_interval == 0:
            loss_mean = loss_mean / log_interval
            print("Training:Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, i + 1, len(train_loader), loss_mean, correct / total))
            loss_mean = 0.

        # 记录数据，保存于event file
        writer.add_scalars("Loss", {"Train": loss.item()}, iter_count)
        writer.add_scalars("Accuracy", {"Train": correct / total}, iter_count)

    # 每个epoch，记录梯度，权值
    for name, param in net.named_parameters():
        writer.add_histogram(name + '_grad', param.grad, epoch)
        writer.add_histogram(name + '_data', param, epoch)

    scheduler.step()  # 更新学习率

    # validate the model
    if (epoch + 1) % val_interval == 0:

        correct_val = 0.
        total_val = 0.
        loss_val = 0.
        net.eval()
        with torch.no_grad():
            for j, data in enumerate(valid_loader):
                inputs, labels = data
                outputs = net(inputs)
                loss = criterion(outputs, labels)

                _, predicted = torch.max(outputs.data, 1)
                total_val += labels.size(0)
                correct_val += (predicted == labels).squeeze().sum().numpy()

                loss_val += loss.item()

            valid_curve.append(loss.item())
            print("Valid:\t Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, j + 1, len(valid_loader), loss_val, correct / total))

            # 记录数据，保存于event file
            writer.add_scalars("Loss", {"Valid": np.mean(valid_curve)}, iter_count)
            writer.add_scalars("Accuracy", {"Valid": correct / total}, iter_count)

train_x = range(len(train_curve))
train_y = train_curve

train_iters = len(train_loader)
valid_x = np.arange(1, len(valid_curve) + 1) * train_iters * val_interval  # 由于valid中记录的是epochloss，需要对记录点进行转换到iterations
valid_y = valid_curve

plt.plot(train_x, train_y, label='Train')
plt.plot(valid_x, valid_y, label='Valid')

plt.legend(loc='upper right')
plt.ylabel('loss value')
plt.xlabel('Iteration')
plt.show()

2. 批量可视化

未在服务器跑, 只读

# -*- coding:utf-8 -*-
"""
@brief      : 卷积核和特征图的可视化
"""
import torch.nn as nn
from PIL import Image
import torchvision.transforms as transforms
from torch.utils.tensorboard import SummaryWriter
import torchvision.utils as vutils
from tools.common_tools import set_seed
import torchvision.models as models

set_seed(1)  # 设置随机种子


# ----------------------------------- kernel visualization -----------------------------------
# flag = 0
flag = 1
if flag:
    writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")

    alexnet = models.alexnet(pretrained=True)

    kernel_num = -1
    vis_max = 1

    for sub_module in alexnet.modules():
        if isinstance(sub_module, nn.Conv2d):
            kernel_num += 1
            if kernel_num > vis_max:
                break
            kernels = sub_module.weight
            c_out, c_int, k_w, k_h = tuple(kernels.shape)

            for o_idx in range(c_out):
                kernel_idx = kernels[o_idx, :, :, :].unsqueeze(1)   # make_grid需要 BCHW，这里拓展C维度
                kernel_grid = vutils.make_grid(kernel_idx, normalize=True, scale_each=True, nrow=c_int)
                writer.add_image('{}_Convlayer_split_in_channel'.format(kernel_num), kernel_grid, global_step=o_idx)

            kernel_all = kernels.view(-1, 3, k_h, k_w)  # 3, h, w
            kernel_grid = vutils.make_grid(kernel_all, normalize=True, scale_each=True, nrow=8)  # c, h, w
            writer.add_image('{}_all'.format(kernel_num), kernel_grid, global_step=322)

            print("{}_convlayer shape:{}".format(kernel_num, tuple(kernels.shape)))

    writer.close()


# ----------------------------------- feature map visualization -----------------------------------
# flag = 0
flag = 1
if flag:
    writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")

    # 数据
    path_img = "./lena.png"     # your path to image
    normMean = [0.49139968, 0.48215827, 0.44653124]
    normStd = [0.24703233, 0.24348505, 0.26158768]

    norm_transform = transforms.Normalize(normMean, normStd)
    img_transforms = transforms.Compose([
        transforms.Resize((224, 224)),
        transforms.ToTensor(),
        norm_transform
    ])

    img_pil = Image.open(path_img).convert('RGB')
    if img_transforms is not None:
        img_tensor = img_transforms(img_pil)
    img_tensor.unsqueeze_(0)    # chw --> bchw

    # 模型
    alexnet = models.alexnet(pretrained=True)

    # forward
    convlayer1 = alexnet.features[0]
    fmap_1 = convlayer1(img_tensor)

    # 预处理
    fmap_1.transpose_(0, 1)  # bchw=(1, 64, 55, 55) --> (64, 1, 55, 55)
    fmap_1_grid = vutils.make_grid(fmap_1, normalize=True, scale_each=True, nrow=8)

    writer.add_image('feature map in conv1', fmap_1_grid, global_step=322)
    writer.close()