BRERIN (Epoch 39)

Epoch 39 is a roughly fermented gated recurrent network (GRU) that exemplifies the rough parabolic deflection contours of Sense Lab discourse.

jhav:~ jhave$ cd /Users/jhave/Desktop/github/pytorch-poetry-generation/word_language_model

jhav:word_language_model jhave$ source activate ~/py36 
(/Users/jhave/py36) jhav:word_language_model jhave$ python generate_2017-SL-BE_LaptopOPTIMIZED.py --checkpoint=/Users/jhave/Desktop/github/pytorch-poetry-generation/word_language_model/models/2017-08-22T12-35-49/model-GRU-emsize-2500-nhid_2500-nlayers_2-batch_size_20-epoch_39-loss_1.59-ppl_4.90.pt

System will generate 88 word bursts, perpetually, until stopped.

BRERIN 

A Philosobot:
Trained on the collected book-length works of Erin Manning and Brian Massumi

+~+Library: PyTorch+~+

Mode: GRU
Embedding size: 2500
Hidden Layers: 2500
Batch size: 20
Epoch: 39
Loss: 1.59
Perplexity: 4.90.pt

Initializing.
Please be patient.

 


 


Text : Screencast_SL_BE_Epoch39_24-08-2017_16h12_1h04m_model-GRU-emsize-2500-nhid_2500-nlayers_2-batch_size_20-epoch_39-loss_1.59-ppl_4.90


For the tech-minded, let it be noted: this is an overfit model. While overfitting is taboo in science, it is a creator of blossoms in natural language generation. The texture of actual units of source text sutured into a collagen of authenticity.

Specifically: I used all the text sources in the training data. And basically did not care about the relevance or size of test or validation data. And the embedding size is made as large as the gpu will tolerate. Dropout is high so it gets confused.

Basically, for a deep learning expert, the loss and perplexity values are invalid, to put it crudely: bullshit. Yet the texture of the language generated is superior.

Consider the analogy of training a child to read and write: does the wise teacher keep back part of the corpus of knowledge, or does the teacher give all to the student?

Brerin may have many moments of spasmodic incoherence, yet at an idiomatic cadence and vocabulary level the texts recreate the dexterity and delirium intensities of the source fields. In essence, reflecting the vast variational presence of both Erin and Brian. This bot is a homage to their massive resilient oeuvre.

SenseLab (BRERIN – beta testing)

BRERIN 

A Philosobot:
Trained on the collected book-length works 
of Erin Manning and Brian Massumi

+~+Library: PyTorch+~+

Mode: GRU
Embedding size: 2500
Hidden Layers: 2500
Batch size: 20
Epoch: 69
Loss: 0.71
Perplexity: 2.03.pt


Formatted run inside Cathode.

Text file: BRERIN-2h22m-Aug23-2017_TERMINAL


Preliminary run (unformatted)

Txt file output of 1h44m run of 952mb Pytorch GRU model : here


Pytorch 1800 hidden layers 31 epochs

PyTorch Poetry Language Model.
Trained on approx 600,000 lines of poetry
http://bdp.glia.ca

+~+

jhave@jhave-Ubuntu:~/Documents/Github/pytorch-poetry-generation/word_language_model$ python generate_2017-INFINITE-1M.py –cuda –checkpoint=’/home/jhave/Documents/Github/pytorch-poetry-generation/word_language_model/models/2017-06-17T09-22-17/model-LSTM-emsize-1860-nhid_1860-nlayers_2-batch_size_20-epoch_30-loss_6.00-ppl_405.43.pt’

Mode: LSTM
Embedding size: 1860
Hidden Layers: 1860
Batch size: 20
Epoch: 30
Loss: 6.00
Perplexity: 405.43.pt

+~+

jhave@jhave-Ubuntu:~/Documents/Github/pytorch-poetry-generation/word_language_model$ python generate_2017-INFINITE-1M.py –cuda –checkpoint=’/home/jhave/Documents/Github/pytorch-poetry-generation/word_language_model/models/2017-06-17T09-22-17/model-LSTM-emsize-1860-nhid_1860-nlayers_2-batch_size_20-epoch_31-loss_6.00-ppl_405.39.pt’

Mode: LSTM
Embedding size: 1860
Hidden Layers: 1860
Batch size: 20
Epoch: 31
Loss: 6.00
Perplexity: 405.39.pt

+~+

Ridges— Ourselves?

4
K-Town: ideality;
The train lost, “Aye man!
O old beggar, O perfect friend;
The bath-tub before the Bo’s’n resentments; pissing
rimed metaphors in the white pincers
scratching and whiten each of a clarity
in the sky the sacred hoof of eastward,
arc of the pestle through sobered the cliffs to the own world.

+~+

TXT Version:

jhave@jhave-Ubuntu_Screencast 2017-06-26 09_45_14_2017-06-17T09-22-17_model-LSTM-emsize-1860-nhid_1860-nlayers_2-batch_size_20-epoch_31-loss_6.00-ppl_405.39

jhave@jhave-Ubuntu-pytorch-poet_Screencast 2017-06-07 20:16:49_model-LSTM-emsize-1500-nhid_1500-nlayers_2-batch_size_20-epoch_7-loss_6.02-ppl_412.27

+~+

RERITES : May 2017 (Amazon/Blurb/PDF)

RERITES

  • May 2017
  • By Neural Net Software, Jhave

All poems in this book were written by a computer, then edited by a human.
All poems were written in the month of April 25th -May 25th 2017.
The algorithm used were based on Pytorch word language model neural network.


Download PDF

Or buy on Amazon or  Blurb



O wht the heck. Why not one more last deranged excessive epic deep learning poetry binge courtesy of pytorch-for-poetry-generation

Personally I like the coherence of Pytorch, it’s capacity to hold the disembodied recalcitrant veil of absurdity over a somewht stoic normative syntactical model.

Text:

jhave@jhave-Ubuntu-pytorch-poet_Screencast 2017-06-07 20:16:49_model-LSTM-emsize-1500-nhid_1500-nlayers_2-batch_size_20-epoch_7-loss_6.02-ppl_412.27

Code:

https://github.com/jhave/pytorch-poetry-generation

Excerpt:

Jumble, Rub Up The Him-Whose-Penis-Stretches-Down-To-His-Knees. 

 
 The slow-wheeling white Thing withheld in the light of the Whitman? 
 The roof kisses the wounds of blues and yellow species. 
 Far and cold in the soft cornfields bending to the gravel, 
 Or showing diapers in disclosure, Atlantic, Raymond 
 Protract the serried ofercomon, — the throats "I've used to make been sustene, 
 Fanny, the inner man clutched to the keep; 
 Who meant me to sing one step at graves. 
Written by Comments Off on O wht the heck. Why not one more last deranged excessive epic deep learning poetry binge courtesy of pytorch-for-poetry-generation Posted in LSTM, poems, pytorch

Ok that’s it: i’ve had enough. This is the last Wvnt Epic Video. Until a juicy code variant arises.

TEXT:

(tf0p1-py3.5-wvnt) jhave@jhave-Ubuntu_Screencast 2017-06-07 10:58:11_2017-06-07_08-12-11

Excerpt:

weather, 
Gold apply thy unndmight hour. 
    And neither would endure 
Meet excel understood) 
                             

I once had declared clay. 
    Be lines once my God 
      
Written by Comments Off on Ok that’s it: i’ve had enough. This is the last Wvnt Epic Video. Until a juicy code variant arises. Posted in LSTM, poems, wavenet

A few SLOW excerpts

from here

accepting tall any flowers, forever with one question
of boots, neural, dead forgotten the glass
of cloud, start and more, who studied legends
and wanted to ascend
Every inch alone you and this desire
tulips of sounds
watching the witness
On the intensity lolling it.

Summer up warmishment
The girls crack our hearts
she set and quickens, swarms at the edge.
where they could wake? It begins
how much design, anthounces are taught her.
Illusion, mimicry a chalk.
when you’re lonely, black large in the calico,
where the bachelo forking genes
might in dusty confidently,
ignore and suck with the main grove,
the dream in the darkness, found hear
if these wobbles, silver for the man.

Deaf-soot he’s an edging of ships
a border that is the court.
The soul,
aroused, breakfast

who wants shapelesse lava
So long as nothing moved oversized no mountains of an eternity

I fed him into oned
There is to say something a fog and mask at writing
minild, the moon and cair of his screens

It is there learning, loving down, screeching.

mystery, painted Spring.
wings
as mid-afternoon, fetlocks

uncurledding cheaping full of pale
eternal, grabs us. Flowers try

migrating every idea
and whispered at the
morning machine

looking at her skin, burst

from her will.

WVNT regamed (blind, still bland, but intriguing)

The opposite of scarcity is not abundance: saturation inevitably damages, or perhaps it just corrodes or blunts the impassioned pavlov puppy, delivering a dent of tiny deliberate delirious wonder.

Yet technical momentum now propels and impels continuance: how can the incoherence be tamed? Set some new hyperparameters and let the wvnt train for 26 hours.

Over this weekend, I’ve churned out about 100,000 lines. Generating reckless amounts of incoherent poetry threatens more than perspective or contemplation, it totters sanity on the whim of a machine. Teeming bacteria, every epiphany a whiff of redundancy.

$ python train_2017_py3p5_150k_low6_sample4096_SAVE-STARTS_100k.py 
--wavenet_params=wavenet_params_ORIG_dilations2048_skipChannels8192_qc2048_dc32.json 
--data_dir=data/2017

Using default logdir: ./logdir/train/2017-06-01T08-38-45 

_______________________________________________________________________________________________

dilations: 2048 filter_width: 2 residual_channels: 32
dilation_channels: 32 skip_channels: 8192 quantization_channels: 2048

(tf0p1-py3.5-wvnt) jhave@jhave-UbuntuScreencast 2017-06-02 11:08:14_2017-06-01T08-38-45

and faithful wound 
To fruit white, the dread 
One by one another, Image saved-- 
Ay of the visit. What pursued my heart to brink. 


Such the curse of hopes fraught memory;

tf0p1-py3.5-wvnt_jhave-Ubuntu_Screencast 2017-06-02 11:08:14_2017-06-01T08-38-45

Caught a new light bulb,   
All the heart is grown.

TXTs generated in SLOW MODE

There’s a way of calculating the matrices that taxes the strength of evn a magnificient GPU, making production crawl, and the computer difficult to use. Each of the following txt files (4444 letters in each) took about 40-60 minutes  to generate on an Nvidia Maxwell TitanX using cuda8 on Ubuntu 16.4

Txts generated slow seem somehow thicker, as if issued from a more calibrated mentation, yet at the same time it’s math scat, glitch flow. Glisses from disintegrating encyclopedias.

Here are some samples:

I found myself within us wonder.
   You purchase as ease with water over events,
   because the straightforward that I miximally, she
   Don't sports commentation with its ruffled story

tf0p1-py3.5-wvnt_jhave-Ubuntu_SLOW_4444charsx4_2017-06-02-16T08_2017-06-01T08-38-45_model.ckpt-117396 Continue reading

Wvnt Tamed

So the abrasive brash gutter voice of the neural net seemed maybe due to lack of longterm exposure, wider horizons, deeper reading into the glands of embodied organisms, so I set the hyperparameters higher, waited 26 hours and watched the ubuntu HD fill up with models to the point where the OS crashed on reboot and i found myself entering a mysterious cmd line universe called grub… thus to say apprenticing a digital poet is not without perils.


Text: tf0p1-py3.5-wvnt_jhave-Ubuntu_Screencast 2017-05-31 15:19:36_Wavenet_2017-05-30T10-36-56


Text: tf0p1-py3.5-wvnt_jhave-Ubuntu_Screencast 2017-05-31 11:49:04_Wavenet_2017-05-30T10-36-56