Article directory foreword 1. What is a decision tree? 2. Experimental principle Third, the specific implementation 1. Find the information entropy of each feature 2. Find the information gain of each feature and find the eigenvalue with the largest information gain 3. Implement the network structure of the decision tree and save it 4. In …
Code implementation: CBAM.PyTorch reference article: [Add attention mechanism (CBAM) to pytorch, take ResNet as an example to] to pytorch, take ResNet as an example to](/qq_38410428/article/details/103694759?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-2.control&dist_request_id=&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-2.control) interpret yolo theory: yolov5l.yaml ; yolo.py Mainly change .yaml, yolo.py, commom.py these three files ① .yaml [yolov5] provides four kinds of s, m, l, and x, and CBAM should be …
Add attention mechanism (CBAM) to pytorch, taking yolov5 as an example Read More »
Day1 – [data preprocessing] Original: https://github.com/Avik-Jain/100-Days-Of-ML-Code Translation: https://github.com/MLEveryday/100-Days-Of-ML-Code Code: import numpy as np import pandas as pd from sklearn.preprocessing import Imputer from sklearn.preprocessing import LabelEncoder, OneHotEncoder from sklearn.cross_validation import train_test_split from sklearn.preprocessing import StandardScaler # step 2: Import dataset data_set = pd.read_csv('datasets/Data.csv') print(data_set) X = data_set.iloc[ :, :3].values # Extract all data except the last …
See [“How to do deep learning traffic sign recognition with 98% accuracy? “] At the time of this article, I discovered udacity’s [autonomous driving] course. It’s a pity that there is a fee, but the course project is available on github, so just do the project directly, and there is no class. Let’s start with …
[Autopilot] Build a Traffic Sign Recognition Program Read More »
1. Environment configuration version information: When installing [tensorflow] -gpu, special attention should be paid to the adaptation information of tensorflow-gpu, Python, CUDA, and cuDNN versions. If the version does not match, the installation of tensorflow-gpu will fail . The software version information selected in this installation tutorial is: ubuntu18.04 + Anaconda3 .5.3.1 + Python3.6.12 + …
The ubuntu system uses Anaconda to install the tensorflow-gpu environment Read More »
The object returned by state_dict inside the module class is just a copy, so modifying the value inside does not affect the real parameters in the model. We can use the [tensor] .copy_() method to assign values. Simple example: a = torch.tensor([[1,2], [3,4]]) b = torch.tensor([[7,8],[9,10]]) a.copy_(b) print(a) print(b)
Today’s article will introduce KNN (k-nearest neighbor algorithm), which is a simple classification algorithm whose idea is to classify by measuring the distance between different feature values . You may not understand it this way, so let’s give a brief overview of it through a simple example. Taking the picture below as an example, we …
Python implements KNN algorithm (formula derivation + source code) Read More »
Building and deploying [machine learning] models has never been easier. Now, there are many frameworks and libraries that help us build machine learning models with just a few lines of code, PyCaret is one of the best tools out there, and the recently very popular Streamlit can be used to quickly create and deploy web …
PyCaret and Streamlit Rapidly create and deploy data science applications Read More »
What is image distance? how to calculate image distance What is the Hu invariant pitch of an image Calculate Hu distance using OpenCV Calculate similarity between two images 1. What is the image distance? Image moments are weighted averages of image pixel intensities. Let us choose a simple example to understand. For simplicity, let us …
The previous 7 notes introduced the classification problem, and this time I will introduce the clustering problem. The difference between classification and clustering is that the former belongs to a supervised learning algorithm, and the labels of the samples are known; the latter belongs to unsupervised learning, and the labels of the samples are not …