handsondeeplearningwithpytorch's Introduction

HandsOnDeepLearningWithPytorch

Repository is arranged chapter wise and each folder includes the code used + the visualization of models use. Dataset used for the models are either available in the shared box folder or downloadable from the torch utility packages such as torchvision, torchtext or torchaudio

Chapters

Introduction
A Simple Neural Network
Deep Learning work flow
Computer Vision
Sequential Data Processing
Generative Networks
Reinforcement Learning
PyTorch In Production

Utilities

Visualization is handled by Netron -
```
pip install netron
```
Environment is handled by Pipenv

Usage

Clone the repository

git clone https://github.com/hhsecond/HandsOnDeepLearningWithPytorch.git && cd HandsOnDeepLearningWithPytorch

Install dependancies. HandsOnDeepLearningWithPytorch is using conda with python3.7
```
conda env create -f environment.yml
```
CD to chapter directores and execute the models

handsondeeplearningwithpytorch's People

Stargazers

Watchers

handsondeeplearningwithpytorch's Issues

Code in section 2 does not work

in numpy_like_fizbuz.py:

Issue seems to be that you set dtype conditional on whether or not cuda is available. however, if cuda is available dtype is set to torch.cuda.FloatTensor
and the line:
w1 = torch.randn(input_size, hidden_size, requires_grad=True).type(dtype)
causes w1 to forget it is a user created variable and it loses the "requires_grad=True" attribute:

Here is an illustration. I am running pytorch 1.0 and python 3.6 (on a device with an attached gpu)

dtype
<class 'torch.cuda.FloatTensor'>
y = torch.zeros(1, 2, requires_grad=True).type(dtype)
y
tensor([[0., 0.]], device='cuda:0', grad_fn=)
y.requires_grad = True
Traceback (most recent call last):
File "", line 1, in
RuntimeError: you can only change requires_grad flags of leaf variables.
y = torch.zeros(1, 2).type(dtype)
y
tensor([[0., 0.]], device='cuda:0')
y.requires_grad = True
y
tensor([[0., 0.]], device='cuda:0', requires_grad=True)

Environment yml - ResolvePackageNotFound error

Trying to install the environment I get a number of packages reported under ResolvePackageNotFound. I am on WIndows 10 and my current conda version is 4.7.5. My reading about this suggests that this could be resolved by removing version information from the specifications - many of these packages already exist on my PC, including Pytorch 1.1.0.

Additional points:
Could these be resolved by specifying >= rather than ==?
Do we really need Python 3.7 or could this work with >= 3.6?
Since I have a GPU and a later version of Pytorch, is it correct to be specifying pytorch-cpu=1.0.1?

(base) >conda env create -f environment.yml
Collecting package metadata (repodata.json): done
Solving environment: failed

ResolvePackageNotFound:
  - pycosat==0.6.3=py37h14c3975_0
  - tk==8.6.8=hbc83047_0
  - ninja==1.8.2=py37h6bb024c_1
  - mkl_random==1.0.2=py37hd81dba3_0
  - libedit==3.1.20170329=h6b74fdf_2
  - openssl==1.1.1b=h7b6447c_1
  - xz==5.2.4=h14c3975_4
  - python==3.7.1=h0371630_7
  - cryptography==2.4.2=py37h1ba5d50_0
  - zstd==1.3.7=h0b5b093_0
  - libgcc-ng==8.2.0=hdf63c60_1
  - freetype==2.9.1=h8a8886c_1
  - pillow==5.4.1=py37h34e0f95_0
  - ncurses==6.1=he6710b0_1
  - cffi==1.11.5=py37he75722e_1
  - pytorch-cpu==1.0.1=py3.7_cpu_2
  - libpng==1.6.36=hbc83047_0
  - jpeg==9b=h024ee3a_2
  - libffi==3.2.1=hd88cf55_4
  - numpy==1.16.2=py37h7e9f1db_0
  - zlib==1.2.11=h7b6447c_3
  - readline==7.0=h7b6447c_5
  - libgfortran-ng==7.3.0=hdf63c60_0
  - ruamel_yaml==0.15.46=py37h14c3975_0
  - libtiff==4.0.10=h2733197_2
  - yaml==0.1.7=had09818_2
  - numpy-base==1.16.2=py37hde5b4d6_0
  - libstdcxx-ng==8.2.0=hdf63c60_1
  - mkl_fft==1.0.10=py37ha843d7b_0
  - sqlite==3.26.0=h7b6447c_0

My conda info:

     active environment : base
    active env location : G:\Anaconda3
            shell level : 1
       user config file : C:\Users\User\.condarc
 populated config files : C:\Users\User\.condarc
          conda version : 4.7.5
    conda-build version : 3.18.6
         python version : 3.6.6.final.0
       virtual packages : __cuda=10.1
       base environment : G:\Anaconda3  (writable)
           channel URLs : https://conda.anaconda.org/conda-forge/win-64
                          https://conda.anaconda.org/conda-forge/noarch
                          https://conda.anaconda.org/ostrokach-forge/win-64
                          https://conda.anaconda.org/ostrokach-forge/noarch
                          https://conda.anaconda.org/anaconda-fusion/win-64
                          https://conda.anaconda.org/anaconda-fusion/noarch
                          https://repo.anaconda.com/pkgs/main/win-64
                          https://repo.anaconda.com/pkgs/main/noarch
                          https://repo.anaconda.com/pkgs/r/win-64
                          https://repo.anaconda.com/pkgs/r/noarch
                          https://repo.anaconda.com/pkgs/msys2/win-64
                          https://repo.anaconda.com/pkgs/msys2/noarch
          package cache : G:\Anaconda3\pkgs
                          C:\Users\User\.conda\pkgs
                          C:\Users\User\AppData\Local\conda\conda\pkgs
       envs directories : G:\Anaconda3\envs
                          C:\Users\User\.conda\envs
                          C:\Users\User\AppData\Local\conda\conda\envs
               platform : win-64
             user-agent : conda/4.7.5 requests/2.22.0 CPython/3.6.6 Windows/10 Windows/10.0.17134
          administrator : False
             netrc file : None
           offline mode : False

Recommend Projects

hhsecond / handsondeeplearningwithpytorch Goto Github PK

handsondeeplearningwithpytorch's Introduction

HandsOnDeepLearningWithPytorch

Chapters

Utilities

Usage

handsondeeplearningwithpytorch's People

Stargazers

Watchers

Forkers

handsondeeplearningwithpytorch's Issues

Code in section 2 does not work

Environment yml - ResolvePackageNotFound error

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent