- 博客(24)
- 收藏
- 关注
原创 backup all conda envs all at once and uninstall conda
bash script to backup all conda environment lists #!bin/bash NOW=$(date "+%Y-%m-%d") CONDA_BASE=$(conda info --base) CONDA_FUNCTION="etc/profile.d/conda.sh" CONDA="$CONDA_BASE/$CONDA_FUNCTION" source $CONDA mkdir ./condaenvs-$NOW ENVS=$(conda env list |
2020-12-31 19:53:29 105
原创 CrowPi 2 image and fixes
Crowpi 2 github Crowpi 2 image google drive link
2020-12-30 20:20:24 126
原创 Set Python3 as default python
First, execute python to check the default python on your raspberry Pi. Press Ctrl-Z to exit. If it is python3, you can skip this section. If it is python2, you need execute the following commands to set default python to python3. Enter directory /usr/bin
2020-12-27 20:22:24 358
原创 all the important error logs in cmake
pip install ./cmake_example Traceback (most recent call last): File “/home/jerry/anaconda3/bin/pip”, line 7, in from pip._internal.cli.main import main File “/usr/lib/python3/dist-packages/pip/init.py”, line 29, in from pip.utils import get_installed_d.
2020-12-26 23:01:31 80
原创 Dog robot MPC Cotroller using Pybullet
https://github.com/google-research/motion_imitation
2020-12-26 03:41:10 259
原创 Study a linux standard Cmake file: CMakeLists.txt
cmake_minimum_required(VERSION 2.8.4) project(kalman) set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11") find_package(Eigen3 REQUIRED) include_directories(${EIGEN3_INCLUDE_DIR}) set(SOURCE_FILES kalman.cpp kalman-test.cpp) add_executable(kalman-test $
2020-12-26 01:55:00 163
原创 Matrix Basics in Lpzrobot
/* compile this with g++ -Wall -lm -L. -lselforg -o example matrixexample.cpp or use the Makefile*/ #include <iostream> #include <math.h> #include <selforg/matrix.h> using namespace matrix; using namespace std; int main(){ /////////.
2020-12-22 20:14:42 124 1
原创 Save and load data from CSV to Eigen data
#include <iostream> #include <eigen3/Eigen/Dense> #include <fstream> #include <vector> using namespace Eigen; using namespace std; void saveData(string filename, MatrixXd matrix){ //dynamic, doubles const static IOFormat CSV
2020-12-22 18:54:31 465
原创 Intro to Eigen (eigen3/Eigen/...) C++
#include <eigen3/Eigen/Core> #include <iostream> #include <eigen3/Eigen/Dense> using namespace Eigen; using namespace std; int main(){ Matrix <float, 4 , 3> matrixA; matrixA.setOnes(); cout<< matrixA <<
2020-12-22 18:15:08 224
原创 Trail
/** track options */ TrackRobot* TrackOpt = new TrackRobot(false,false,false, track_rob); TrackOpt->conf.displayTraceDur = 2000; TrackOpt->conf.displayTraceThickness = 0.01; // 0.01 or 0. agent->setTrackOptions( *TrackOpt )
2020-12-19 00:47:45 108 1
原创 Github Useful Command
add & commit You can propose changes (add it to the Index) using git add <filename> git add * This is the first step in the basic git workflow. To actually commit these changes use...
2020-12-18 04:24:24 272
原创 Python Statement
d = {'k1':1,'k2':2,'k3':3} for item in d: print(item) >> k1 >> k2 >> k3 # Create a dictionary view object d.items() # Dictionary unpacking for k,v in d.items(): v = v+1 print(k) print(v) >> k1 >> 2 >> k.
2020-12-15 23:51:59 460
原创 Python3 basics
a = 10 type(a) a = 'I said :"stupid! ' type(a) >> str print('Use \n to print a new line') s = 'Hello World' # Grab everything but the last letter s[:-1] # Concatenate strings! s + ' concatenate me!' #We can use the multiplication symbol to create r
2020-12-15 02:37:17 254
原创 2020-12-07
3 If you look into the original ResNet Paper (http://openaccess.thecvf.com/content_cvpr_2016/papers/He_Deep_Residual_Learning_CVPR_2016_paper.pdf) they use strided convolutions to downsample the image. The main path is downsampled automatically using these
2020-12-07 21:12:23 151
原创 Paper -- DenseNet:Densely Connected Convolutional Network
Abstracts: DenseNet breaks away from the fixed thinking of deepening the number of network layers (ResNet) and widening the network structure (Inception) to improve network performance. From the perspective of features, through feature reuse and bypass (By
2020-12-07 18:45:52 296
原创 Paper--Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
An article on batch processing, detailing the specific advantages of using BN 1. The relationship between weight initialization and preprocessing methods in neural networks If you have done the dnn experiment, you may find that preprocessing the data, such
2020-12-07 17:33:19 216
原创 Paper -- Deep Residual Learning for Image Recognition
Now, Residual Connections are everywhere: Not only in image recognition, they’re in transformers. Problem: people knew if you can increase depth pof a neural network, you can make it perform better, make it generalize better, you can reach lower training
2020-12-07 12:22:44 138
原创 2020-12-06
We need to report testset performance Why validation set is not enough and we need a seperate test set? We don’t strictly need a test set, it might be okay if some cases to have training and validation sets onluy, the purpose of the test set is to help us
2020-12-07 06:38:44 200
原创 Pytorch -- Fashion MNIST using feedforward neural networks
Classifying images from Fashion MNIST using feedforward neural networks import torch import torchvision import numpy as np import matplotlib.pyplot as plt import torch.nn as nn import torch.nn.functional as F from torchvision.datasets import FashionMNIST f
2020-12-04 06:50:50 226
原创 Pytorch MNIST Multi-layer
import torch import torchvision import numpy as np import matplotlib.pyplot as plt import torch.nn as nn import torch.nn.functional as F from torchvision.datasets import MNIST from torchvision.transforms import ToTensor from torchvision.utils import make_g
2020-12-04 05:18:37 207
原创 Pytorch MNIST Classification with Logistic Regression Code
Image Classification with Logistic Regression Code # Uncomment and run the commands below if imports fail # !conda install numpy pytorch torchvision cpuonly -c pytorch -y # !pip install matplotlib --upgrade --quiet !pip install jovian --upgrade --quiet #
2020-12-03 23:32:29 194
原创 Pytorch-logistic-regression
Working with MNIST & Logistic Regression in PyTorch # Imports import torch import torchvision from torchvision.datasets import MNIST # Download training dataset dataset = MNIST(root='data/', download=True) When this statement is executed for the firs
2020-12-03 23:19:11 600
原创 personal-introduction-ios-app
ViewController.swift import UIKit import WebKit class ViewController: UIViewController, WKNavigationDelegate { var webView: WKWebView! override func loadView() { webView = WKWebView() webView.navigationDelegate = self
2020-12-03 19:56:33 118
原创 Laplace Approximation:
Laplace Approximation: Fit a Gaussian to p(w|D) log p(w|D) = log p(w,D) +const wrt. w Quadratic in w if Gaussian Find mode and fund 2nd derivative “Energy” E(w) = -log( p(w,D) ) w* = argmin E(w) (L2 regularization term or MAP fit) Hessian Hi
2020-12-03 00:54:30 640
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人