Yu-Hsun (lymanblue) Lin, profile picture
Uploaded byYu-Hsun (lymanblue) Lin
PPTX, PDF3,647 views

PyTorch Tutorial for NTU Machine Learing Course 2017

This document is a comprehensive tutorial on PyTorch, covering its core concepts, modules, and installation instructions. It details the building blocks of neural networks, including tensors, automatic differentiation, and the specific PyTorch libraries for neural networks and optimization. The tutorial also includes practical guidelines for using the library, including examples for defining and building networks.

Embed presentation

Downloaded 262 times
PyTorch Tutorial -NTU Machine Learning Course- Lyman Lin 林裕訓 Nov. 03, 2017 lymanblue[at]gmail.com
What is PyTorch? • Developed by Facebook – Python first – Dynamic Neural Network – This tutorial is for PyTorch 0.2.0 • Endorsed by Director of AI at Tesla
Installation • PyTorch Web: http://pytorch.org/
Packages of PyTorch Package Description torch a Tensor library like Numpy, with strong GPU support torch.autograd a tape based automatic differentiation library that supports all differentiable Tensor operations in torch torch.nn a neural networks library deeply integrated with autograd designed for maximum flexibility torch.optim an optimization package to be used with torch.nn with standard optimization methods such as SGD, RMSProp, LBFGS, Adam etc. torch.multiprocessing python multiprocessing, but with magical memory sharing of torch Tensors across processes. Useful for data loading and hogwild training. torch.utils DataLoader, Trainer and other utility functions for convenience torch.legacy(.nn/.optim) legacy code that has been ported over from torch for backward compatibility reasons This Tutorial
Outline • Neural Network in Brief • Concepts of PyTorch • Multi-GPU Processing • RNN • Transfer Learning • Comparison with TensorFlow
Neural Network in Brief • Supervised Learning – Learning a function f, that f(x)=y Data Label X1 Y1 X2 Y2 … … Trying to learn f(.), that f(x)=y
Neural Network in Brief WiData Neural Network Big Data Batch N Batch 1 Batch 2 Batch 3 … 1 Epoch N=Big Data/Batch Size
Neural Network in Brief WiData Label’ Neural Network Forward Big Data Batch N Batch 1 Batch 2 Batch 3 … 1 Epoch Forward Process: from data to label N=Big Data/Batch Size
Neural Network in Brief WiData Label’ Neural Network LabelLoss Forward Big Data Batch N Batch 1 Batch 2 Batch 3 … 1 Epoch Forward Process: from data to label N=Big Data/Batch Size
Neural Network in Brief Wi-> Wi+1Data Label’ Neural Network LabelLoss Optimizer Backward Forward Big Data Batch N Batch 1 Batch 2 Batch 3 … 1 Epoch Forward Process: from data to label Backward Process: update the parameters N=Big Data/Batch Size
Neural Network in Brief Wi-> Wi+1Data Label’ Neural Network LabelLoss Optimizer Backward Forward W Forward Backward Inside the Neural Network W W W W… Data Label’ Gradient
Neural Network in Brief Wi-> Wi+1Data Label’ Neural Network LabelLoss Optimizer Backward Forward W Forward Backward Inside the Neural Network W W W W… Data Gradient Data in the Neural Network - Tensor (n-dim array) - Gradient of Functions Label’
Concepts of PyTorch • Modules of PyTorch Wi-> Wi+1Data Label’ Neural Network LabelLoss Optimizer Backward Forward Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
Concepts of PyTorch • Modules of PyTorch • Similar to Numpy Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
Concepts of PyTorch • Modules of PyTorch • Operations – z=x+y – torch.add(x,y, out=z) – y.add_(x) # in-place Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
Concepts of PyTorch • Modules of PyTorch • Numpy Bridge • To Numpy – a = torch.ones(5) – b = a.numpy() • To Tensor – a = numpy.ones(5) – b = torch.from_numpy(a) Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
Concepts of PyTorch • Modules of PyTorch • CUDA Tensors • Move to GPU – x = x.cuda() – y = y.cuda() – x+y Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
Concepts of PyTorch • Modules of PyTorch Wi-> Wi+1Data Label’ Neural Network LabelLoss Optimizer Backward Forward Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
Neural Network in Brief Wi-> Wi+1Data Label’ Neural Network LabelLoss Optimizer Backward Forward W Forward Backward Inside the Neural Network W W W W… Data Gradient Data in the Neural Network - Tensor (n-dim array) - Gradient of Functions Label’
Concepts of PyTorch • Modules of PyTorch • Variable Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing Tensor data For Current Backward Process Handled by PyTorch Automatically
Concepts of PyTorch • Modules of PyTorch • Variable • x = Variable(torch.ones(2, 2), requires_grad=True) • print(x) • y = x + 2 • z = y * y * 3 • out = z.mean() • out.backward() • print(x.grad) Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network Define modules (must have) Build network (must have)
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have) [Channel, H, W]: 1x32x32->6x28x28
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have) [Channel, H, W]: 6x28x28
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have) [Channel, H, W]: 6x28x28 -> 6x14x14
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have) [Channel, H, W]: 6x14x14 -> 16x10x10
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have) [Channel, H, W]: 16x10x10
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have) [Channel, H, W]: 16x10x10 -> 16x5x5
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Flatten the Tensor Define modules (must have) Build network (must have) 16x5x5 Tensor: [Batch N, Channel, H, W]
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have)
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have)
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have)
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have)
• http://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html#define-the-network conv1 x relu pooling conv2 relu pooling fc1 relu fc2 relu fc3 Define modules (must have) Build network (must have)
Concepts of PyTorch • Modules of PyTorch • NN Modules (torch.nn) – Modules built on Variable – Gradient handled by PyTorch • Common Modules – Convolution layers – Linear layers – Pooling layers – Dropout layers – Etc… Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D – Example: – torch.nn.conv2d(in_channels=3, out_channels=16, kernel_size=3, padding=1)
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d Win Cin *: convolution
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d k k Win Cin Cin * 1st kernel *: convolution
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d k k Win Cin Cin Hout Wout 1 * 1st kernel = *: convolution
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d k k Win Cin Cin Hout Wout 1 * 1st kernel = *: convolution k=3d=1 s=1, moving step size p=1
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d k k Win Cin Cin Hout Wout 1 * 1st kernel = *: convolution k=3d=1 p=1 p=1 s=1, moving step size
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d k k Win Cin Cin Hout Wout 1 * 1st kernel = *: convolution k=3d=1 p=1 k=3 p=1 s=1, moving step size
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d k k Win Cin Cin Hout Wout 1 * 1st kernel = *: convolution k=3d=1 p=1 k=3 s=1 p=1 s=1, moving step size
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d k k Win Cin Cin Hout Wout 1 * 1st kernel Cout-th kernel k k Cin Hout Wout 1 * = = *: convolution … …
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d k k Win Cin Cin Hout Wout 1 * 1st kernel Cout-th kernel k k Cin Hout Wout 1 * = = Hout Wout Cout *: convolution … …
NN Modules • Convolution Layer – N-th Batch (N), Channel (C) – torch.nn.Conv1d: input [N, C, W] # moving kernel in 1D – torch.nn.Conv2d: input [N, C, H, W] # moving kernel in 2D – torch.nn.Conv3d: input [N, C, D, H, W] # moving kernel in 3D Hin Input for Conv2d k k Win Cin Cin * 1st kernel Cout-th kernel k k Cin * *: convolution … # of parameters
NN Modules • Linear Layer – torch.nn.Linear(in_features=3, out_features=5) – y=Ax+b
NN Modules • Dropout Layer – torch.nn.Dropout(p) – Random zeros the input with probability p – Output are scaled by 1/(1-p) If dropout here
NN Modules • Pooling Layer – torch.nn.AvgPool2d(kernel_size=2, stride=2, padding=0) – torch.nn.MaxPool2d(kernel_size=2, stride=2, padding=0) k=2d=1 k=2 p=0 s=2, moving step size s=2, moving step size
Concepts of PyTorch • Modules of PyTorch • NN Modules (torch.nn) – Modules built on Variable – Gradient handled by PyTorch • Common Modules – Convolution layers – Linear layers – Pooling layers – Dropout layers – Etc… Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
Concepts of PyTorch • Modules of PyTorch • Optimizer (torch.optim) – SGD – Adagrad – Adam – RMSprop – … – 9 Optimizers (PyTorch 0.2) • Loss (torch.nn) – L1Loss – MSELoss – CrossEntropy – … – 18 Loss Functions (PyTorch 0.2) Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
http://pytorch.org/tutorials/beginner/pytorch_with_examples.html#pytorch-optim Define modules (must have) Build network (must have) What We Build?
http://pytorch.org/tutorials/beginner/pytorch_with_examples.html#pytorch-optim Define modules (must have) Build network (must have) What We Build? … … … D_in=1000 H=100 D_out=100 y_pred
http://pytorch.org/tutorials/beginner/pytorch_with_examples.html#pytorch-optim Define modules (must have) Build network (must have) What We Build? … … … D_in=1000 H=100 D_out=100 y_pred Optimizer and Loss Function Construct Our Model Don’t Update y (y are labels here)
http://pytorch.org/tutorials/beginner/pytorch_with_examples.html#pytorch-optim Define modules (must have) Build network (must have) … … … D_in=1000 H=100 D_out=100 y_pred Optimizer and Loss Function Reset Gradient Backward Update Step Construct Our Model What We Build? Don’t Update y (y are labels here)
Concepts of PyTorch • Modules of PyTorch • Basic Method – torch.nn.DataParallel – Recommend by PyTorch • Advanced Methods – torch.multiprocessing – Hogwild (async) Data: - Tensor - Variable (for Gradient) Function: - NN Modules - Optimizer - Loss Function - Multi-Processing
Multi-GPU Processing • torch.nn.DataParallel – gpu_id = '6,7‘ – os.environ['CUDA_VISIBLE_DEVICES'] = gpu_id – net = torch.nn.DataParallel(model, device_ids=[0, 1, 2]) – output = net(input_var) • Important Notes: – Device_ids must start from 0 – (batch_size/GPU_size) must be integer
Saving Models • First Approach (Recommend by PyTorch) • # save only the model parameters • torch.save(the_model.state_dict(), PATH) • # load only the model parameters • the_model = TheModelClass(*args, **kwargs) • the_model.load_state_dict(torch.load(PATH)) • Second Approach • torch.save(the_model, PATH) # save the entire model • the_model = torch.load(PATH) # load the entire model http://pytorch.org/docs/master/notes/serialization.html#recommended-approach-for-saving-a-model
Recurrent Neural Network (RNN) http://pytorch.org/tutorials/beginner/former_torchies/nn_tutorial.html#example-2-recurrent-net self.i2h input_size=50+20=70 input hidden output
Recurrent Neural Network (RNN) http://pytorch.org/tutorials/beginner/former_torchies/nn_tutorial.html#example-2-recurrent-net self.i2h input_size=50+20=70 input hidden output Same module (i.e. same parameters) among the time
Transfer Learning • Freeze the parameters of original model – requires_grad = False • Then add your own modules http://pytorch.org/docs/master/notes/autograd.html#excluding-subgraphs-from-backward
Comparison with TensorFlow Properties TensorFlow PyTorch Graph Static Dynamic (TensorFlow Fold) Dynamic Ramp-up Time - Win Graph Creation and Debugging - Win Feature Coverage Win Catch up quickly Documentation Tie Tie Serialization Win (support other lang.) - Deployment Win (Cloud & Mobile) - Data Loading - Win Device Management Win Need .cuda() Custom Extensions - Win Summarized from https://awni.github.io/pytorch-tensorflow/
Remind: Platform & Final Project Thank You~!

More Related Content

PPTX
[Update] PyTorch Tutorial for NTU Machine Learing Course 2017
byYu-Hsun (lymanblue) Lin
 
PDF
Deep Learning with PyTorch
byMayur Bhangale
 
PDF
Pytorch for tf_developers
byAbdul Muneer
 
PDF
PyTorch crash course
byNader Karimi
 
PPTX
Introduction to PyTorch
byJun Young Park
 
PDF
Intro to TensorFlow and PyTorch Workshop at Tubular Labs
byKendall
 
PDF
PyTorch for Deep Learning Practitioners
byBayu Aldi Yansyah
 
PDF
"PyTorch Deep Learning Framework: Status and Directions," a Presentation from...
byEdge AI and Vision Alliance
 
[Update] PyTorch Tutorial for NTU Machine Learing Course 2017
byYu-Hsun (lymanblue) Lin
 
Deep Learning with PyTorch
byMayur Bhangale
 
Pytorch for tf_developers
byAbdul Muneer
 
PyTorch crash course
byNader Karimi
 
Introduction to PyTorch
byJun Young Park
 
Intro to TensorFlow and PyTorch Workshop at Tubular Labs
byKendall
 
PyTorch for Deep Learning Practitioners
byBayu Aldi Yansyah
 
"PyTorch Deep Learning Framework: Status and Directions," a Presentation from...
byEdge AI and Vision Alliance
 

What's hot

PDF
TensorFlow Dev Summit 2018 Extended: TensorFlow Eager Execution
byTaegyun Jeon
 
PDF
Overview of Chainer and Its Features
bySeiya Tokui
 
PDF
Introduction to Chainer 11 may,2018
byPreferred Networks
 
PPTX
Chainer v3
bySeiya Tokui
 
PPTX
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
byAltoros
 
PDF
TensorFlow example for AI Ukraine2016
byAndrii Babii
 
PDF
Chainer ui v0.3 and imagereport
byPreferred Networks
 
PDF
Comparison of deep learning frameworks from a viewpoint of double backpropaga...
byKenta Oono
 
PDF
CUDA and Caffe for deep learning
byAmgad Muhammad
 
PDF
Common Design of Deep Learning Frameworks
byKenta Oono
 
PDF
Scaling Deep Learning with MXNet
byAI Frontiers
 
PDF
Introduction to Chainer
byPreferred Networks
 
PDF
Introduction to Chainer
bySeiya Tokui
 
PDF
Learning stochastic neural networks with Chainer
bySeiya Tokui
 
PDF
OpenPOWER Workshop in Silicon Valley
byGanesan Narayanasamy
 
PDF
Introduction to Deep Learning with Python
byindico data
 
PDF
Rajat Monga at AI Frontiers: Deep Learning with TensorFlow
byAI Frontiers
 
PDF
Deep learning for molecules, introduction to chainer chemistry
byKenta Oono
 
PDF
Introduction to Chainer
byShunta Saito
 
PDF
IIBMP2019 講演資料「オープンソースで始める深層学習」
byPreferred Networks
 
TensorFlow Dev Summit 2018 Extended: TensorFlow Eager Execution
byTaegyun Jeon
 
Overview of Chainer and Its Features
bySeiya Tokui
 
Introduction to Chainer 11 may,2018
byPreferred Networks
 
Chainer v3
bySeiya Tokui
 
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
byAltoros
 
TensorFlow example for AI Ukraine2016
byAndrii Babii
 
Chainer ui v0.3 and imagereport
byPreferred Networks
 
Comparison of deep learning frameworks from a viewpoint of double backpropaga...
byKenta Oono
 
CUDA and Caffe for deep learning
byAmgad Muhammad
 
Common Design of Deep Learning Frameworks
byKenta Oono
 
Scaling Deep Learning with MXNet
byAI Frontiers
 
Introduction to Chainer
byPreferred Networks
 
Introduction to Chainer
bySeiya Tokui
 
Learning stochastic neural networks with Chainer
bySeiya Tokui
 
OpenPOWER Workshop in Silicon Valley
byGanesan Narayanasamy
 
Introduction to Deep Learning with Python
byindico data
 
Rajat Monga at AI Frontiers: Deep Learning with TensorFlow
byAI Frontiers
 
Deep learning for molecules, introduction to chainer chemistry
byKenta Oono
 
Introduction to Chainer
byShunta Saito
 
IIBMP2019 講演資料「オープンソースで始める深層学習」
byPreferred Networks
 

Viewers also liked

PPTX
ENVIRONMENTAL IMPACT ASSESSMENT - EIA
bySakthivel R
 
PDF
Environmental Impact Assessment - University of Winnipeg
byJohn Gunter
 
PPTX
EIA thermal power plant
byvandana bharti
 
PPT
Environmental impact assessment
bySayyid Ina
 
PPTX
Environmental impact assessment
byJini Rajendran
 
PPSX
13 environmental impact assessment
byPrabha Panth
 
PPTX
Environmental impact assessment m5
byBibhabasu Mohanty
 
PPTX
Environmental impact assessment concept
byIntan Ayuna
 
PPTX
Environmental impact assessment (eia) By Mr Allah Dad Khan Visiting Professor...
byMr.Allah Dad Khan
 
PPTX
Environmental Audit and Environmental Impact Assessment
byEffah Effervescence
 
PPT
Seminar on Environmental Impact Assessment
byashwinpand90
 
PPT
environmental impact assessment
byPRAMODA G
 
PPTX
Environmental Impact Assessment in Water Resources Projects
byNational Institute of Technology Hamirpur
 
PPTX
Environmental impact assessment methodology
byJustin Joy
 
PPTX
Developing Guidelines for Public Participation on Environmental Impact Assess...
byEthical Sector
 
PDF
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
byNAVER Engineering
 
PPT
Environmental impact assessment and life cycle assessment and their role in s...
byArvind Kumar
 
PPTX
Environmental impact assessment
byNanyang Technological University, Singapore
 
PPTX
Planning and environmental impact assessment (EIA)
bytesdev
 
PPTX
Environmental impact assessment
byKashmeera N.A.
 
ENVIRONMENTAL IMPACT ASSESSMENT - EIA
bySakthivel R
 
Environmental Impact Assessment - University of Winnipeg
byJohn Gunter
 
EIA thermal power plant
byvandana bharti
 
Environmental impact assessment
bySayyid Ina
 
Environmental impact assessment
byJini Rajendran
 
13 environmental impact assessment
byPrabha Panth
 
Environmental impact assessment m5
byBibhabasu Mohanty
 
Environmental impact assessment concept
byIntan Ayuna
 
Environmental impact assessment (eia) By Mr Allah Dad Khan Visiting Professor...
byMr.Allah Dad Khan
 
Environmental Audit and Environmental Impact Assessment
byEffah Effervescence
 
Seminar on Environmental Impact Assessment
byashwinpand90
 
environmental impact assessment
byPRAMODA G
 
Environmental Impact Assessment in Water Resources Projects
byNational Institute of Technology Hamirpur
 
Environmental impact assessment methodology
byJustin Joy
 
Developing Guidelines for Public Participation on Environmental Impact Assess...
byEthical Sector
 
1시간만에 GAN(Generative Adversarial Network) 완전 정복하기
byNAVER Engineering
 
Environmental impact assessment and life cycle assessment and their role in s...
byArvind Kumar
 
Environmental impact assessment
byNanyang Technological University, Singapore
 
Planning and environmental impact assessment (EIA)
bytesdev
 
Environmental impact assessment
byKashmeera N.A.
 

Similar to PyTorch Tutorial for NTU Machine Learing Course 2017

PPTX
pytorch_tutorial_follow_this_to_start.pptx
bygyungmindenniskim
 
PDF
Dive Into PyTorch
byIllarion Khlestov
 
PDF
pytdddddddddddddddddddddddddddddddddorch.pdf
bydrjigarsoni28
 
PPTX
Pytroch-basic.pptx
byrebeen4
 
PDF
Machine learning with py torch
byRiza Fahmi
 
PPTX
Essentials of PyTorch Tutorial .pptx
bysurajkumartpoint
 
PDF
1-pytorch-CNN-RNN.pdf
byAndrey63387
 
PDF
pytorch-cheatsheet.pdf for ML study with pythroch
byJunZhao68
 
PPTX
2Wisjshsbebe pehele isienew Dorene isksnwnw
byYashAbhayKawdiyaH44
 
PDF
Pytorch A Detailed Overview Agladze Mikhail
byilzobrzan47
 
PDF
01_pytorch_workflow jutedssd huge hhgggdf
bystuartkyeswa4
 
PDF
PyTorch Introduction
byYash Kawdiya
 
PDF
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
byEdureka!
 
PPTX
Deep learning study 3
bySan Kim
 
PPTX
Transfer Leaning Using Pytorch synopsis Minor project pptx
byAnkit Gupta
 
PPTX
Pytorch and Machine Learning for the Math Impaired
byTyrel Denison
 
PDF
Icpp power ai-workshop 2018
byGanesan Narayanasamy
 
PDF
A Tale of Three Deep Learning Frameworks: TensorFlow, Keras, & PyTorch with B...
byDatabricks
 
PPTX
Mastering PyTorch: A Comprehensive Guide for Deep Learning Enthusiasts
byYourTechDiet
 
PDF
implementing _Training_Neural_Network_with_PyTorch .pdf
bykgebre2021
 
pytorch_tutorial_follow_this_to_start.pptx
bygyungmindenniskim
 
Dive Into PyTorch
byIllarion Khlestov
 
pytdddddddddddddddddddddddddddddddddorch.pdf
bydrjigarsoni28
 
Pytroch-basic.pptx
byrebeen4
 
Machine learning with py torch
byRiza Fahmi
 
Essentials of PyTorch Tutorial .pptx
bysurajkumartpoint
 
1-pytorch-CNN-RNN.pdf
byAndrey63387
 
pytorch-cheatsheet.pdf for ML study with pythroch
byJunZhao68
 
2Wisjshsbebe pehele isienew Dorene isksnwnw
byYashAbhayKawdiyaH44
 
Pytorch A Detailed Overview Agladze Mikhail
byilzobrzan47
 
01_pytorch_workflow jutedssd huge hhgggdf
bystuartkyeswa4
 
PyTorch Introduction
byYash Kawdiya
 
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
byEdureka!
 
Deep learning study 3
bySan Kim
 
Transfer Leaning Using Pytorch synopsis Minor project pptx
byAnkit Gupta
 
Pytorch and Machine Learning for the Math Impaired
byTyrel Denison
 
Icpp power ai-workshop 2018
byGanesan Narayanasamy
 
A Tale of Three Deep Learning Frameworks: TensorFlow, Keras, & PyTorch with B...
byDatabricks
 
Mastering PyTorch: A Comprehensive Guide for Deep Learning Enthusiasts
byYourTechDiet
 
implementing _Training_Neural_Network_with_PyTorch .pdf
bykgebre2021
 

Recently uploaded

PDF
DiaryofaWebSDKImplemenation-LaunchDebugging.pdf
bygmuir1066
 
PDF
01-Introduction_to_Computers and app.pdf
byjaveriaafsar575
 
PPTX
Data analysis 2 presentation at ipmc.pptx
byabdualimohammed960
 
PPTX
Integrated matching and rebalancing for ride-hailing services.pptx
byWenjiaShen1
 
PPTX
cloud computing ppt useful for studestns
byNagarajuJajam
 
PDF
Terminals into Throughways: Amtrak Through Service to Long Island
bykrv2009
 
PPTX
Security information presentation and its importance
bybilalkingqwq
 
PDF
High-Performance Loading of Financial Market Data Streams to the Snowflake Pl...
byDataFuze
 
PPTX
CRAFTING A PERSUASIVE STRATEGY PRESENTATION - ORLANDO LIZARRAGA.pptx
byOrlandoLizarragaCerv
 
PPT
Markov chain presentation class05-m.ppt
bydairymilkat10
 
PPTX
PPT presentasi PKL anak smk yang .pptx
bycahyantoananda3
 
PPTX
[DSC Europe 25] Jon Dajci - Bridging TradFi and DeFi: Building the Future of ...
byDataScienceConferenc1
 
PPTX
[DSC Europe 25] Kaja Kandare - LLM as a judge.pptx
byDataScienceConferenc1
 
PPTX
Online Hospital Appointment Management System
byahsanalishigre
 
PPTX
Pakistan Tableau User Group Kickoff Event: Exploring AI Powered Insights usin...
byWaqarAhmedShaikh8
 
PPTX
powerpoint presentation for an ai that helps you invest in funds and do marke...
byfarzaanfk2002
 
PPTX
Talk on Artificial Intelligence_AI Usap Tayo.pptx
byPatrick655831
 
PPTX
[DSC Europe 25] Hans Kleinsman - The Compliance Gearbox: How Tax Tech Mediate...
byDataScienceConferenc1
 
PPTX
[DSC Europe 25] Miodrag Pesovic & Vladislav Radonjic - Federated Data Archite...
byDataScienceConferenc1
 
PDF
OWASP-Top-10-for-Large-Language-Models-2023.pdf
byReynir Orn Bachmann Gudmundsson
 
DiaryofaWebSDKImplemenation-LaunchDebugging.pdf
bygmuir1066
 
01-Introduction_to_Computers and app.pdf
byjaveriaafsar575
 
Data analysis 2 presentation at ipmc.pptx
byabdualimohammed960
 
Integrated matching and rebalancing for ride-hailing services.pptx
byWenjiaShen1
 
cloud computing ppt useful for studestns
byNagarajuJajam
 
Terminals into Throughways: Amtrak Through Service to Long Island
bykrv2009
 
Security information presentation and its importance
bybilalkingqwq
 
High-Performance Loading of Financial Market Data Streams to the Snowflake Pl...
byDataFuze
 
CRAFTING A PERSUASIVE STRATEGY PRESENTATION - ORLANDO LIZARRAGA.pptx
byOrlandoLizarragaCerv
 
Markov chain presentation class05-m.ppt
bydairymilkat10
 
PPT presentasi PKL anak smk yang .pptx
bycahyantoananda3
 
[DSC Europe 25] Jon Dajci - Bridging TradFi and DeFi: Building the Future of ...
byDataScienceConferenc1
 
[DSC Europe 25] Kaja Kandare - LLM as a judge.pptx
byDataScienceConferenc1
 
Online Hospital Appointment Management System
byahsanalishigre
 
Pakistan Tableau User Group Kickoff Event: Exploring AI Powered Insights usin...
byWaqarAhmedShaikh8
 
powerpoint presentation for an ai that helps you invest in funds and do marke...
byfarzaanfk2002
 
Talk on Artificial Intelligence_AI Usap Tayo.pptx
byPatrick655831
 
[DSC Europe 25] Hans Kleinsman - The Compliance Gearbox: How Tax Tech Mediate...
byDataScienceConferenc1
 
[DSC Europe 25] Miodrag Pesovic & Vladislav Radonjic - Federated Data Archite...
byDataScienceConferenc1
 
OWASP-Top-10-for-Large-Language-Models-2023.pdf
byReynir Orn Bachmann Gudmundsson
 

PyTorch Tutorial for NTU Machine Learing Course 2017

Editor's Notes

  • #63 http://pytorch.org/docs/master/notes/autograd.html