Han-Yi Wang henrywang1

## softmax.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                henrywang1
                / softmax.ipynb
            
            
              Created
              August 16, 2018 05:38
                — forked from awjuliani/softmax.ipynb
            
              
                A simple ipython notebook that walks through the creation of a softmax regression model using MNIST dataset.
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## steps.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                henrywang1
                / steps.md
            
            
              Last active
              January 9, 2019 08:52
            
              
                Install python2, keras-gpu on Ubuntu 16.04
              
          
    Install nvidia driver

sudo add-apt-repository ppa:graphics-drivers/ppa
sudo apt-get update
sudo apt-get install nvidia-396 nvidia-modprobe
sudo reboot

install CUDA 9.2, cuDNN 7.2.1

copy from: https://gist.github.com/kylemcdonald/3ae0b88a1bf91afc00ba441fe6823a17

  
## share_weight.py
from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms

class Net(nn.Module):
    def __init__(self, share_block):

## command.sh
# Push subtree in local branch to heroku
git push heroku `git subtree split --prefix project-name local-branch-name`:master --force
	from __future__ import print_function
	import argparse
	import torch
	import torch.nn as nn
	import torch.nn.functional as F
	import torch.optim as optim
	from torchvision import datasets, transforms

	class Net(nn.Module):
	def __init__(self, share_block):
	# Push subtree in local branch to heroku
	git push heroku `git subtree split --prefix project-name local-branch-name`:master --force