-
cnn
这是一个经过自己整理的卷积神经网络的代码，对0-9数据集进行分类的代码，使用tensorflow框架完成的，主要使用的语言是Python，可以直接运行，初学者可以用于学习交流。(This is a self compiled convolutional neural network code, 0-9 data sets for classification of code, using the tensorflow framework to complete, the main language is Python, can be run directly, beginners can be used for learning exchanges.)
- 2017-11-12 10:51:39下载
- 积分：1
-
inpaint-object-remover-python
实现基于样本块的图像修复，是Criminisi经典图像修复算法。(Criminisi algorithm about exemplar-based inpainting)
- 2020-11-06 14:49:50下载
- 积分：1
-
官方Python上位机
说明： 实现 MPU6050 DMP解算欧拉角后的姿态显示上位机。(The mpu6050 DMP is used to calculate the Euler angle.)
- 2020-04-05 21:18:54下载
- 积分：1
-
黑夜变白ToDayGAN-master
能然黑夜的图片变成白天，效果很逼真，很牛(If the picture of night turns into day, the effect is very vivid and cattle.)
- 2020-12-19 21:29:10下载
- 积分：1
-
python环境的小测试，包含一个制图模块pythonTestCode
对python环境的小测试，包含一个制图模块(A small test of Python environment, including a mapping module)
- 2020-06-23 06:00:02下载
- 积分：1
-
gabor.py
说明： Gabor特征提取，使用python，输出为一个直方图。用于kcf的目标跟踪(Gabor feature extraction, using python, output as a histogram. Target tracking for KCF)
- 2019-04-15 11:14:23下载
- 积分：1
-
图像超分辨率
说明： 图像超分辨率技术源码；
基于深度学习的图像超分辨率重建的流程如下[2]：
1.首先找到一组原始图像Image1;
2.将这组图片降低分辨率为一组图像Image2
3.通过各种神经网络结构，将Image2超分辨率重建为Image3(Image3和Image1分辨率一样)
4.通过PSNR等方法比较Image1和Image3，验证超分辨率重建的效果，根据效果调节神经网络中的节点和参数
5.反复执行以上直到第4步的结果比较满意(Image super-resolution technology source code;
The process of image super-resolution reconstruction based on deep learning is as follows [2]:
1. First find a set of original images image1;
2. Reduce the resolution of this group of pictures to a group of image2
3. Through various neural network structures, the super-resolution of image2 is reconstructed into image3 (the resolution of image3 is the same as that of image1)
4. Compare image1 and image3 by PSNR and other methods to verify the effect of super-resolution reconstruction, and adjust the nodes and parameters of neural network according to the effect
5. Repeat the above until the result of step 4 is satisfactory)
- 2020-03-19 14:46:10下载
- 积分：1
-
keshe
说明： 文章管理系统
实现用户登录、注册和退出界面
实现对文章的增、删、查、改等功能
实现对文章的保存
用户信息保存到json文件中(Article management system)
- 2020-12-27 10:05:57下载
- 积分：1
-
Python
PYTHON核心教程，PYTHON开发必读(PYTHON core curriculum, PYTHON development of reading)
- 2020-06-25 01:40:02下载
- 积分：1
-
LSTM入门正弦波序列预测
LSTM入门学习，正弦波序列预测
for i, input_t in enumerate(input.chunk(input.size(1), dim=1)):
h_t, c_t = self.lstm1(input_t, (h_t, c_t))
h_t2, c_t2 = self.lstm2(h_t, (h_t2, c_t2))
output = self.linear(h_t2) # output.shape:[batch,1]
outputs = [output] # outputs.shape:[[batch,1],...[batch,1]], list composed of n [batch,1],
for i in range(future): # if we should predict the future
h_t, c_t = self.lstm1(output, (h_t, c_t))
h_t2, c_t2 = self.lstm2(h_t, (h_t2, c_t2))
output = self.linear(h_t2) # output.shape:[batch,1]
outputs = [output] # outputs.shape:[[batch,1],...[batch,1]], list composed of n [batch,1],
outputs = torch.stack(outputs, 1).squeeze(2) # shape after stack:[batch, n, 1], shape after squeeze: [batch,n]
return outputs
- 2021-06-30 00:31:01下载
- 积分：1
