textRCNN intensive reading and reproduction

title: textRCNN intensive reading and reproduction date: 2022-03-03 20:16:16 tags: paper intensive readingReappearancepytorch Thesis address: Recurrent Convolutional Neural Networks for Text Classification | Papers With Code Model architecture Bidirectional cyclic neural network and maximum pooling layer. The embedding mentioned in the pa ...

Posted by gooney0 on Thu, 03 Mar 2022 14:36:24 +0100

torch.nn.Sequential and torch nn. ModuleList

Original address: Explain ModuleList and Sequential in PyTorch in detail torch.nn.Module() import torch.nn as nn import torch.nn.functional as F class Model(nn.Module): def __init__(self): super(Model, self).__init__() self.conv1 = nn.Conv2d(3, 32, 3) self.conv2 = nn.Conv2d(32, 10, 1) def forward(self, x): x = F.relu(self.conv1( ...

Posted by outatime88 on Wed, 02 Mar 2022 01:25:50 +0100

Deep learning environment configuration under Ubuntu 20.04 system (subsystem) (pytoch + GPU)

Deep learning environment configuration under Ubuntu 20.04 system (subsystem) (pytoch + GPU) 🍀 Previous sequence (pit avoidance) Last time I installed Ubuntu in the virtual machine and installed Nvidia driver , enter the command Ubuntu drivers devices, and you can see that there are no recommended drivers, as shown below: Finally, sudo ap ...

Posted by geaser_geek on Tue, 01 Mar 2022 16:03:51 +0100

Pytrch deep learning and graph Neural Network Practice Series_ 04 Pytorch quick start

1 tensor data operation 1.1 torch.reshape() implements data dimension change import torch a = torch.tensor([[1,2],[3,4]]) print(torch.reshape(a,(1,-1))) # It is transformed into a tensor with only one row of data, and the parameter - 1 indicates automatic calculation # tensor([[1, 2, 3, 4]]) print(a.reshape((1,-1))) # # It is transformed into ...

Posted by schme16 on Tue, 01 Mar 2022 14:19:48 +0100

[secretly kill the little partner Pytorch20 days - day13-nn.functional and nn.Module]

1, NN Functional and NN Module Earlier, we introduced the structure operation of Pytorch's tensor and some common API s in mathematical operation. Using these tensor API s, we can construct neural network related components (such as activation function, model layer, loss function). Most of the functional components related to Pytorch and neu ...

Posted by godsent on Sun, 27 Feb 2022 10:39:22 +0100

Using the transformers library fine tuning

explain According to the official website Working with documents , use transformers for fine tuning. I basically follow the documents. Note: the example on the official website basically saves the model or data set into the local cache through a line of code, but it needs to climb the wall. We can also download the model and data set locall ...

Posted by Gibbs on Sun, 27 Feb 2022 09:52:41 +0100

DETR code learning notes

Last DETR code learning notes (I) After recording the backbone of DETR and the part before the data enters the encoder, this article begins to introduce the transformer part of DETR, generally the transformer and Attention is All You Need  The proposed framework is basically consistent, but there are some differences in data. The first part is ...

Posted by Rolando_Garro on Sat, 26 Feb 2022 06:18:27 +0100

SOLOV2 training and teaching

Github: https://github.com/WXinlong/SOLO My operating system is Ubuntu 18 04. This paper will be divided into the following parts: Create datasetModify configmodel trainingVisual Mask resultsModel evaluationInference predictionReasoning optimization First, install some basic libraries. Please refer to the official installation instructions $ ...

Posted by gillypogi on Fri, 25 Feb 2022 13:06:47 +0100

GAN animation character avatar generation

GAN animation character avatar generation 1. Introduction A simple DCGAN network is built to generate the avatars of animation characters. The avatar data set of animation characters is taken from kaggle, and the website is as follows link 2. Network structure data setgenerator Discriminator 2.1 data set The data size is 64x64x3, and the ...

Posted by RHolm on Thu, 24 Feb 2022 09:05:11 +0100

PointPillars point cloud detection in OpenPCDet reasoning code explanation

The implementation and explanation of PointPillars' paper and training code have been analyzed in detail in the previous article. Please refer to the previous blog: PointPillars paper analysis and OpenPCDet code analysis_ Nnnathan blog - CSDN blog. This blog will analyze the reasoning code of PointPillars model in OpenPCDet in detail and test ...

Posted by RobM on Thu, 24 Feb 2022 08:59:10 +0100