SlowFast - getting started 1 - action recognition - deployment and testing

SlowFast - deployment and testing brief introduction GitHub: https://github.com/facebookresearch/SlowFast The official operation example diagram is like this. The features are: the recognized action is atomic action; Each person may be recognized multiple actions at the same time. Installation deployment Deployment platform: Polar cha ...

Added by hey_suburbia on Mon, 10 Jan 2022 20:38:24 +0200

[learning day5] regularization + weight decay

Main sources: Mr. Li Mu's pytorch hands-on learning and deep learning (bow and thank you) Record what you have learned every day. Welcome to discuss~ (the dust has finally settled in the senior year, and I am fully engaged in learning during the holiday!) 1. What is regularization? Regularization can be translated as regularization or nor ...

Added by e39m5 on Mon, 10 Jan 2022 15:50:40 +0200

Pytorch tutorials [detailed explanation of pytorch official tutorial in Chinese and English] - 5 Build Model

article Pytorch tutorials [pytorch official tutorial in Chinese and English] - 4 Transforms This paper introduces the use of Transforms for data conversion. Next, let's see how to build a model. Original link: Build the Neural Network — PyTorch Tutorials 1.10.1+cu102 documentation BUILD THE NEURAL NETWORK Neural networks comprise of layers/ ...

Added by czambran on Thu, 06 Jan 2022 14:08:13 +0200

reconstruction_mesh.py code reading

Triangle, plane normal, vertex normal In Direct3D, triangles are the basic units that make up a solid, because a triangle is exactly a plane and rendering efficiency is highest in triangle faces. A triangle consists of three points, which are traditionally referred to as Vertex. A triangle plane can be divided into positive and negative sides ...

Added by joseph on Thu, 06 Jan 2022 04:23:15 +0200

[deep learning calculation] access, initialization and sharing of model parameters

Access, initialization and sharing of model parameters In (a concise implementation of linear regression), we initialize the parameters of the model through the init module. We also introduced a simple way to access model parameters. This section will explain in depth how to access and initialize model parameters, and how to share the same ...

Added by ssj4gogita4 on Thu, 06 Jan 2022 01:42:16 +0200

yolov5 deploys jetson nano (Universal) nanny level teaching

The whole process of Jetson nano from configuration environment to yolov5 successful reasoning detection 1, Burn image Official image download address on the official website: https://developer.nvidia.com/embedded/downloads You may not be able to download it, so I provided Baidu cloud link to download it. The download address is as foll ...

Added by sunsun on Tue, 04 Jan 2022 06:07:01 +0200

Implementation of classical network lenet + pytoch

Introduction to LeNet neural network LeNet neural network was proposed by Yan LeCun, one of the three giants of deep learning. He is also the father of convolutional neural networks (CNN). LeNet is mainly used for handwritten character recognition and classification, and has been used in American banks. The implementation of LeNet establishes ...

Added by cookiemonster4470 on Tue, 04 Jan 2022 05:14:21 +0200

Python Basics - Super (XXX, self)__ init__ () learning and understanding

On many occasions, especially when writing neural network code, I often see the following code examples: Definition of neural network under TensorFlow framework: class BertIntentModel(object): def __init__(self): super(BertIntentModel, self).__init__() self.dict_path = '/Users/vocab.txt' self.config_path = '/Users/bert_config_rbt3.jso ...

Added by homchz on Tue, 04 Jan 2022 03:44:57 +0200

python tips003 -- collapse of DataLoader_ FN parameter usage details

background Recently, I was looking at the source code of sensors transformers and found a data loader in a module collate_ FN, I didn't understand what it meant at that time. Later, I checked it and found it very interesting, so let's share it. dataloader dataloader must know that it provides an iterator for data. Basic working mechanism: ...

Added by andygrant on Tue, 04 Jan 2022 03:29:17 +0200

About register in PyTorch_ forward_ The hook() function failed to execute the problem in which the hook function

About register in PyTorch_ forward_ The hook() function failed to execute the problem in which the hook function Hook is a very useful feature in PyTorch. Using it, we can easily obtain and change the value and gradient of variables in the middle layer of the network without changing the structure of network input and output. This function is ...

Added by Pobega on Mon, 03 Jan 2022 21:36:54 +0200