print('Epoch {}/{}'.format(epoch, num_epochs - 1))

这行代码用于打印当前的训练轮数。它使用了格式化字符串`'Epoch {}/{}'`，其中`{}`是占位符，用于将变量的值填入字符串中。

`epoch`表示当前的训练轮数，`num_epochs - 1`表示总共的训练轮数减去1（因为索引从0开始）。

通过调用`print()`函数，将格式化字符串作为参数传入，可以在控制台输出当前的训练轮数信息。这对于实时跟踪训练过程、观察训练的进展情况非常有帮助。

相关问题

下面代码转化为paddle2.2.2代码 ：from __future__ import division import os, time, scipy.io import torch import torch.nn as nn import torch.optim as optim import numpy as np import glob import cv2 import argparse from PIL import Image from skimage.measure import compare_psnr,compare_ssim from tensorboardX import SummaryWriter from models import RViDeNet from utils import * parser = argparse.ArgumentParser(description='Pretrain denoising model') parser.add_argument('--gpu_id', dest='gpu_id', type=int, default=0, help='gpu id') parser.add_argument('--num_epochs', dest='num_epochs', type=int, default=33, help='num_epochs') parser.add_argument('--patch_size', dest='patch_size', type=int, default=128, help='patch_size') parser.add_argument('--batch_size', dest='batch_size', type=int, default=1, help='batch_size') args = parser.parse_args() os.environ["CUDA_VISIBLE_DEVICES"] = str(args.gpu_id) save_dir = './pretrain_model' if not os.path.isdir(save_dir): os.makedirs(save_dir) gt_paths1 = glob.glob('./data/SRVD_data/raw_clean/MOT17-02_raw/*.tiff') gt_paths2 = glob.glob('./data/SRVD_data/raw_clean/MOT17-09_raw/*.tiff') gt_paths3 = glob.glob('./data/SRVD_data/raw_clean/MOT17-10_raw/*.tiff') gt_paths4 = glob.glob('./data/SRVD_data/raw_clean/MOT17-11_raw/*.tiff') gt_paths = gt_paths1 + gt_paths2 + gt_paths3 + gt_paths4 ps = args.patch_size # patch size for training batch_size = args.batch_size # batch size for training

把原始代码转换为PaddlePaddle 2.2.2 的代码如下：

import os
import time
import argparse
import glob
import cv2
import numpy as np
from PIL import Image
from skimage.measure import compare_psnr, compare_ssim
from tensorboardX import SummaryWriter
from models import RViDeNet
from utils import *

import paddle
from paddle import nn
from paddle.optimizer import optim

paddle.set_device('gpu')
parser = argparse.ArgumentParser(description='Pretrain denoising model')
parser.add_argument('--gpu_id', dest='gpu_id', type=int, default=0, help='gpu id')
parser.add_argument('--num_epochs', dest='num_epochs', type=int, default=33, help='num_epochs')
parser.add_argument('--patch_size', dest='patch_size', type=int, default=128, help='patch_size')
parser.add_argument('--batch_size', dest='batch_size', type=int, default=1, help='batch_size')
args = parser.parse_args()

save_dir = './pretrain_model'
if not os.path.isdir(save_dir):
    os.makedirs(save_dir)

gt_paths1 = glob.glob('./data/SRVD_data/raw_clean/MOT17-02_raw/*.tiff')
gt_paths2 = glob.glob('./data/SRVD_data/raw_clean/MOT17-09_raw/*.tiff')
gt_paths3 = glob.glob('./data/SRVD_data/raw_clean/MOT17-10_raw/*.tiff')
gt_paths4 = glob.glob('./data/SRVD_data/raw_clean/MOT17-11_raw/*.tiff')
gt_paths = gt_paths1 + gt_paths2 + gt_paths3 + gt_paths4

ps = args.patch_size  # patch size for training
batch_size = args.batch_size # batch size for training
num_epochs = args.num_epochs

train_dataset = DatasetDenoising(gt_paths, ps=ps)
train_loader = paddle.io.DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=4)

model = RViDeNet()
model.train()

optimizer = optim.Adam(learning_rate=1e-4, parameters=model.parameters())

writer = SummaryWriter()

for epoch in range(num_epochs):
    epoch_start_time = time.time()
    epoch_loss = 0
    for i, (noisy_patches, gt_patches) in enumerate(train_loader()):
        noisy_patches = paddle.to_tensor(noisy_patches)
        gt_patches = paddle.to_tensor(gt_patches)

        output = model(noisy_patches)
        loss = nn.functional.mse_loss(output, gt_patches)

        optimizer.clear_grad()
        loss.backward()
        optimizer.step()

        epoch_loss += loss

    epoch_time = time.time() - epoch_start_time
    epoch_loss = epoch_loss / len(train_loader)
    print("Epoch [{}/{}] Loss: {:.5f} [{:.2f}s]".format(epoch + 1, num_epochs, epoch_loss, epoch_time))

    writer.add_scalar("Loss/train", epoch_loss, epoch + 1)

    if (epoch + 1) % 10 == 0:
        model_path = os.path.join(save_dir, 'RViDeNet_epoch{}.pdparams'.format(epoch + 1))
        paddle.save(model.state_dict(), model_path)
        print("Saving model to: {}".format(model_path))

writer.close()

帮我把这段代码从tensorflow框架改成pytorch框架： import tensorflow as tf import os import numpy as np import matplotlib.pyplot as plt os.environ["CUDA_VISIBLE_DEVICES"] = "0" base_dir = 'E:/direction/datasetsall/' train_dir = os.path.join(base_dir, 'train_img/') validation_dir = os.path.join(base_dir, 'val_img/') train_cats_dir = os.path.join(train_dir, 'down') train_dogs_dir = os.path.join(train_dir, 'up') validation_cats_dir = os.path.join(validation_dir, 'down') validation_dogs_dir = os.path.join(validation_dir, 'up') batch_size = 64 epochs = 50 IMG_HEIGHT = 128 IMG_WIDTH = 128 num_cats_tr = len(os.listdir(train_cats_dir)) num_dogs_tr = len(os.listdir(train_dogs_dir)) num_cats_val = len(os.listdir(validation_cats_dir)) num_dogs_val = len(os.listdir(validation_dogs_dir)) total_train = num_cats_tr + num_dogs_tr total_val = num_cats_val + num_dogs_val train_image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1. / 255) validation_image_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1. / 255) train_data_gen = train_image_generator.flow_from_directory(batch_size=batch_size, directory=train_dir, shuffle=True, target_size=(IMG_HEIGHT, IMG_WIDTH), class_mode='categorical') val_data_gen = validation_image_generator.flow_from_directory(batch_size=batch_size, directory=validation_dir, target_size=(IMG_HEIGHT, IMG_WIDTH), class_mode='categorical') sample_training_images, _ = next(train_data_gen) model = tf.keras.models.Sequential([ tf.keras.layers.Conv2D(16, 3, padding='same', activation='relu', input_shape=(IMG_HEIGHT, IMG_WIDTH, 3)), tf.keras.layers.MaxPooling2D(), tf.keras.layers.Conv2D(32, 3, padding='same', activation='relu'), tf.keras.layers.MaxPooling2D(), tf.keras.layers.Conv2D(64, 3, padding='same', activation='relu'), tf.keras.layers.MaxPooling2D(), tf.keras.layers.Flatten(), tf.keras.layers.Dense(256, activation='relu'), tf.keras.layers.Dense(2, activation='softmax') ]) model.compile(optimizer='adam', loss=tf.keras.losses.BinaryCrossentropy(from_logits=True), metrics=['accuracy']) model.summary() history = model.fit_generator( train_data_gen, steps_per_epoch=total_train // batch_size, epochs=epochs, validation_data=val_data_gen, validation_steps=total_val // batch_size ) # 可视化训练结果 acc = history.history['accuracy'] val_acc = history.history['val_accuracy'] loss = history.history['loss'] val_loss = history.history['val_loss'] epochs_range = range(epochs) model.save("./model/timo_classification_128_maxPool2D_dense256.h5")

import torch import torch.nn as nn import torch.optim as optim from torch.utils.data import DataLoader from torchvision import datasets, transforms import os BATCH_SIZE = 64 EPOCHS = 50 IMG_HEIGHT = 128 IMG_WIDTH = 128 train_transforms = transforms.Compose([ transforms.Resize((IMG_HEIGHT,IMG_WIDTH)), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize([0.5,0.5,0.5], [0.5,0.5,0.5])]) test_transforms = transforms.Compose([ transforms.Resize((IMG_HEIGHT,IMG_WIDTH)), transforms.ToTensor(), transforms.Normalize([0.5,0.5,0.5], [0.5,0.5,0.5])]) base_dir = 'E:/direction/datasetsall/' train_dir = os.path.join(base_dir, 'train_img/') validation_dir = os.path.join(base_dir, 'val_img/') train_cats_dir = os.path.join(train_dir, 'down') train_dogs_dir = os.path.join(train_dir, 'up') validation_cats_dir = os.path.join(validation_dir, 'down') validation_dogs_dir = os.path.join(validation_dir, 'up') train_dataset = datasets.ImageFolder(train_dir, transform=train_transforms) train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True) test_dataset = datasets.ImageFolder(validation_dir, transform=test_transforms) test_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=False) device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") model = nn.Sequential( nn.Conv2d(3, 16, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2), nn.Conv2d(16, 32, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2), nn.Conv2d(32, 64, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2), nn.Flatten(), nn.Linear(64 * (IMG_HEIGHT // 8) * (IMG_WIDTH // 8), 256), nn.ReLU(), nn.Linear(256, 2), nn.Softmax(dim=1) ) model.to(device) criterion = nn.CrossEntropyLoss() optimizer = optim.Adam(model.parameters(), lr=0.001) for epoch in range(EPOCHS): train_loss = 0.0 train_acc = 0.0 model.train() for images, labels in train_loader: images = images.to(device) labels = labels.to(device) optimizer.zero_grad() outputs = model(images) loss = criterion(outputs, labels) loss.backward() optimizer.step() train_loss += loss.item() * images.size(0) _, preds = torch.max(outputs, 1) train_acc += torch.sum(preds == labels.data) train_loss = train_loss / len(train_loader.dataset) train_acc = train_acc / len(train_loader.dataset) print('Epoch: {} \tTraining Loss: {:.6f} \tTraining Accuracy: {:.6f}'.format(epoch+1, train_loss,train_acc)) with torch.no_grad(): test_loss = 0.0 test_acc = 0.0 model.eval() for images, labels in test_loader: images = images.to(device) labels = labels.to(device) outputs = model(images) loss = criterion(outputs, labels) test_loss += loss.item() * images.size(0) _, preds = torch.max(outputs, 1) test_acc += torch.sum(preds == labels.data) test_loss = test_loss / len(test_loader.dataset) test_acc = test_acc / len(test_loader.dataset) print('Test Loss: {:.6f} \tTest Accuracy: {:.6f}'.format(test_loss,test_acc))