Daniel Wong wonglkd

## cluster.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              1 star
            
          
                wonglkd
                / cluster.md
            
            
              Last active
              August 30, 2018 14:53
            
              
                Tool Chain
              
          
Brooce for managing jobs
Secure Pipes for managing SSH tunnels (great when you have Bastions)
?? for monitoring
tmux on bastion for session management


## latency.txt
Latency Comparison Numbers
--------------------------
L1 cache reference/hit                       1.5 ns                      4 cycles
Floating-point add/mult/FMA operation        1.5 ns                      4 cycles
L2 cache reference/hit                       5   ns                      12 ~ 17 cycles
Branch mispredict                            6   ns                      15 ~ 20 cycles
L3 cache hit (unshared cache line)          16   ns                      42 cycles
L3 cache hit (shared line in another core)  25   ns                      65 cycles
Mutex lock/unlock                           25   ns
L3 cache hit (modified in another core)     29   ns                      75 cycles

## mnist_rl_generator.py
'''Trains a multi-output deep NN on the MNIST dataset using crossentropy and
   policy gradients (REINFORCE).
The goal of this example is twofold:
* Show how to use policy graidents for training
* Show how to use generators with multioutput models
# Policy graidients
This is a Reinforcement Learning technique [1] that trains the model
following the gradient of the logarithm of action taken scaled by the advantage
(reward - baseline) of that action.
# Generators

## shuffle_weights.py
#!/usr/bin/env python
"""Demonstrate Keras model weight shuffling as fast alternative to re-creating a model."""

from __future__ import print_function

import numpy as np
from keras.layers import Dense
from keras.models import Sequential


## CATCH_Keras_RL.md

      
              3 files
            
          
              63 forks
            
          
              27 comments
            
          
              153 stars
            
          
                EderSantana
                / CATCH_Keras_RL.md
            
            
              Last active
              October 16, 2023 08:32
            
              
                Keras plays catch - a single file Reinforcement Learning example
              
          
    Code for Keras plays catch blog post
Train

python qlearn.py
Test


Generate figures


## Sublime Text 3 Command
ln -s /Applications/Sublime\ Text.app/Contents/SharedSupport/bin/subl /usr/local/bin/subl

## min-char-rnn.py
"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)

## gist:1988097
// swap the keybindings for paste and paste_and_indent
{ "keys": ["super+v"], "command": "paste_and_indent" },
{ "keys": ["super+shift+v"], "command": "paste" }
	Latency Comparison Numbers
	--------------------------
	L1 cache reference/hit 1.5 ns 4 cycles
	Floating-point add/mult/FMA operation 1.5 ns 4 cycles
	L2 cache reference/hit 5 ns 12 ~ 17 cycles
	Branch mispredict 6 ns 15 ~ 20 cycles
	L3 cache hit (unshared cache line) 16 ns 42 cycles
	L3 cache hit (shared line in another core) 25 ns 65 cycles
	Mutex lock/unlock 25 ns
	L3 cache hit (modified in another core) 29 ns 75 cycles
	'''Trains a multi-output deep NN on the MNIST dataset using crossentropy and
	policy gradients (REINFORCE).
	The goal of this example is twofold:
	* Show how to use policy graidents for training
	* Show how to use generators with multioutput models
	# Policy graidients
	This is a Reinforcement Learning technique [1] that trains the model
	following the gradient of the logarithm of action taken scaled by the advantage
	(reward - baseline) of that action.
	# Generators
	#!/usr/bin/env python
	"""Demonstrate Keras model weight shuffling as fast alternative to re-creating a model."""

	from __future__ import print_function

	import numpy as np
	from keras.layers import Dense
	from keras.models import Sequential
	"""
	Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
	BSD License
	"""
	import numpy as np

	# data I/O
	data = open('input.txt', 'r').read() # should be simple plain text file
	chars = list(set(data))
	data_size, vocab_size = len(data), len(chars)
	// swap the keybindings for paste and paste_and_indent
	{ "keys": ["super+v"], "command": "paste_and_indent" },
	{ "keys": ["super+shift+v"], "command": "paste" }