tf.image.extract_patches
时间: 2023-04-23 19:03:04 浏览: 67
tf.image.extract_patches是TensorFlow中的一个函数,用于从输入张量中提取补丁(patch)。补丁是指输入张量中的一小块区域,可以用于图像处理、卷积神经网络等领域。该函数可以根据给定的参数,从输入张量中提取指定大小和步幅的补丁,并将它们展平成一维张量返回。
相关问题
self.patch_embed = PatchEmbed3D(patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim, norm_layer=norm_layer if self.patch_norm else None) # num_patches = self.patch_embed.num_patches patches_resolution = self.patch_embed.patches_resolution self.patches_resolution = patches_resolution self.num_Ttokens = num_frames // patch_size[0]
这段代码是一个类的初始化函数,它包含了以下几个步骤:
1. 初始化一个三维的 Patch Embedding 层,这一层会将输入的视频序列分割成一个个小的 patch,并将每个 patch 转换成一个低维度的向量表示,方便后续的处理。
2. 计算 patch 的数量和分辨率,这些信息会在后续的处理中用到。
3. 计算 T 轴上 patch 的数量,这个数量等于视频序列的长度除以 patch_size[0],其中 patch_size[0] 表示每个 patch 在 T 轴上的长度。这个数量会在 Transformer 中用到,用于计算 Attention Mask。
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:
```python
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()
```
相关推荐
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![dat](https://img-home.csdnimg.cn/images/20210720083646.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)