Neural network case
Neural network case
Learning objectives
Able to use TF Keras get datasetConstruction of multilayer neural networkBe able to complete network training and evaluation
The MNIST dataset using handwritten digits is shown in the figure above. The dataset contains 60000 samples for training and 10000 samples for testing. The image is a fixed ...
Posted by dabas on Sun, 20 Feb 2022 10:10:24 +0100
Summary of six common methods of visual deep learning model architecture
Visualization helps to explain and understand the internal structure of deep learning model. Through the visualization of the model calculation diagram, we can find out how the neural network is calculated. The visualization of the model mainly includes the following aspects:How many layers does the model haveInput and output shapes of each lay ...
Posted by zonkd on Sun, 20 Feb 2022 05:26:17 +0100
Use torch functions. to_ When Tensor() converts an array into Tensor, you need to pay attention to whether the dimension is correct
When deep learning multi band data training, the model has been unable to converge.
torch.functions.to_tensor() function
Here is to_tensor function source code
def to_tensor(pic):
"""Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor.
This function does not support torchscript.
See :class:`~torchvision.transforms.ToTensor` ...
Posted by georgebates on Sun, 20 Feb 2022 03:49:36 +0100
Data processing algorithm_ 2015 dataset
background
Download address: https://rrc.cvc.uab.es/?ch=4&com=downloads
Note: this data is open source data, but you need to register an account. You can download it simply by registering;
Introduction: it is used for text detection task. The data includes 1000 training samples and 500 test samples;
Required data display
Firstly, the d ...
Posted by basdog22 on Sat, 19 Feb 2022 16:57:28 +0100
Several ways of cutting / Intercepting pictures in Python+opencv
preface
In computer vision tasks, such as image classification, image data set is essential. The pictures collected by yourself often have a lot of noise or useless information, which will affect the model training. Therefore, the image needs to be cropped to prevent the useless information at the edge of the image from affecting the mod ...
Posted by jlive on Sat, 19 Feb 2022 16:52:33 +0100
Deep learning based on Keras -- the construction and training of LeNet
Deep learning based on Keras (II) -- construction and training of LeNet
LeNet is a very efficient convolutional neural network for handwritten character recognition. Although the network is small, it contains the basic modules of deep learning: convolution layer, pooling layer and full connection layer. It is also the basis of other deep l ...
Posted by tracivia on Sat, 19 Feb 2022 16:48:25 +0100
Plane data classification of deep learning single hidden layer
Teacher Wu began to build a hidden neural network.
1, Importing datasets and drawing
Two files are required before importing the dataset. Please refer to [data]
import numpy as np
import pandas as pd
from matplotlib import pyplot as plot
from testCases import *
import sklearn
from sklearn import datasets
from sklearn import linear_model
from ...
Posted by jlgray48 on Sat, 19 Feb 2022 05:58:59 +0100
Animation line draft coloring project
Reprint AI Studio project link https://aistudio.baidu.com/aistudio/projectdetail/3483236
Animation line draft coloring project
Task description
The purpose of this project is to input an animation line draft, and then color the line draft with one key
Data set introduction
From this website https://www.kaggle.com/ktaebum/anime-sket ...
Posted by mushroom on Sat, 19 Feb 2022 02:51:07 +0100
Inception and code implementation
preface
During this period of time, I have benefited a lot from watching the explanation of in-depth learning by up Master Liu Er of station b. Let me know what Inception is and how to embed the structure into the model. Here is the video address:
https://www.bilibili.com/video/BV1Y7411d7Ys?p=11&share_source=copy_web
Interested fri ...
Posted by eskick on Fri, 18 Feb 2022 22:03:59 +0100
Linear regression
Univariate linear regression
Model description
For the model affected by a single variable, we usually abstract it into the form of univariate primary function, and we assume a hypothetical function H( θ)=θ 0+ θ 1x
Cost function
When we make a hypothetical function, we need to determine θ 0 and θ 1 the values o ...
Posted by Tanus on Fri, 18 Feb 2022 04:07:40 +0100