Train your own datasets using Faster RCNN
Using Faster RCNN to train your own dataset, the process is not smooth and you walk through pits several times, so record the process. Code version used: faster-rcnn.pytorch 1. Source and environment configuration The original Github version uses Pytorch==0.4.0, but there are many errors in thiUTF-8...
Posted by chatmaster on Thu, 13 May 2021 05:05:36 +0930
Through the configuration of xml file, some parameters of mmd2.0 can be quickly set, trained and tested
introduction When using MMDetection 1.0 originally, in order to avoid the trouble of modifying various configuration files every time when training a new model, colleagues wrote a config.xml file and modified each file of MMDetection to read the corresponding parameters in the configuration XMUTF-8...
Posted by mikerh9 on Thu, 13 May 2021 07:24:06 +0930
slowfast trains its own dataset
Little mood: today, I just finished the new crown vaccine in school, and I wrote this blog after I came back. I hope that I can help my colleagues and quickly reproduce this model, which can help you save learning time and avoid stepping on the pit. Then, for the outbreak in Hefei, I hope everyUTF-8...
Posted by Ravenous on Sun, 16 May 2021 07:00:41 +0930
Deep learning + pytorch self study notes
background I am a senior now and have been admitted by Tsinghua University. As the initial direction of graduate students will involve in-depth learning, the tutor said that they will use Python for defect detection, involving precision measurement, advanced manufacturing and other related fielUTF-8...
Posted by perfume on Sun, 16 May 2021 08:50:56 +0930
Successful record of TX2 installing ROS system
preface Because of the tutor project, we need to transplant the algorithm developed on the computer to the TX2 smart box (the product of Bianyi intelligence is selected, which is packaged on the basis of TX2 and can be applied in the harsh industrial environment). Therefore, we need to installUTF-8...
Posted by Fitzlegend on Mon, 17 May 2021 07:30:51 +0930
Rtx3070 + ubuntu18.04 + cuda11.1 + cudnn8.0.4 + tensorflow 1.15.4 + pytorch1.7.0 + yolov3 environment configuration
Rtx3070 + ubuntu18.04 + cuda11.1 + cudnn8.0.4 + tensorflow 1.15.4 + pytorch1.7.0 + yolov3 environment configuration 1, VMware + Ubuntu 18.04 installation (1) Install virtual machine 16Pro virtual machine download 16Pro version cracking key 16 ZF3R0-FHED2-M80TY-8QYGC-NPKYFYF390-0HF8P-M81RQ-2DXQEUTF-8...
Posted by crackerjax on Wed, 19 May 2021 04:45:48 +0930
Raspberry pie runs Yolo fast to enable bf16 acceleration
Optimization of Yolo fast for raspberry pie preface The main optimization is as follows 1. Change raspbian pie system to Raspbian-64 bit 2. Enable bf16s acceleration of ncnn Part 1 - installing Raspbian-64 bit system 1, Download images and tools 1. Image download Raspberry pie 64 bit image fileUTF-8...
Posted by slick101 on Thu, 20 May 2021 03:19:10 +0930
mmclassification image classification model training and testing
1. Model training 1.1 using the pre training model Because the imagenet is very large, I choose to use cifar for model training first. The cifar model is as follows Links: links: https://github.com/open-mmlab/mmclassification/blob/master/docs/model_zoo.md Download link: link: https://download.UTF-8...
Posted by marconi8 on Thu, 20 May 2021 04:55:58 +0930
keras functional model
Keras's functional model is Model, which is a generalized model with inputs and outputs. The tf.keras.Sequential model is a simple stack of layers and cannot represent any model.The Keras functional API allows you to build complex model topologies.For example: Multiple input model, Multiple ouUTF-8...
Posted by tbare on Sat, 22 May 2021 04:54:18 +0930
PyTorch Foundation: Dataset, Dataloader, torch vision of data loading and preprocessing
PyTorch Foundation: data loading and preprocessing PyTorch passed torch.utils.data encapsulates the common data loading, which can easily realize multi thread data pre reading and batch loading. also torchvision has implemented common image data sets in advance, including CIFAR-10, ImageNet, COUTF-8...
Posted by sri2002 on Mon, 24 May 2021 03:30:24 +0930