removed some files

console_play.py

@@ -7,7 +7,7 @@ CRED_FILE = "./AI-Adventure-2bb65e3a4e2f.json"
 
 
 def play_unconstrained():
-    generator = SimpleGenerator()
+    generator = GPT2Generator()
     prompt = get_story_start("knight")
     context = get_context("knight")
     story_manager = UnconstrainedStoryManager(generator)

generator/gpt2/src/chat.py

@@ -1,86 +0,0 @@
-#!/usr/bin/env python3
-
-import fire
-import json
-import os
-import sys
-import numpy as np
-import tensorflow as tf
-
-import model, sample, encoder
-
-def interact_model(
-    model_name='117M',
-    seed=None,
-    length=20,
-    temperature=1,
-    top_k=0,
-    conversation="""
-you: hi
-her: hey
-you: i'm a human
-her: i'm a robot
-you: you ready?
-her: yes :)
-you: ok let's start chatting
-her: sure, what do you want to talk about?"""
-):
-
-    enc = encoder.get_encoder(model_name)
-    hparams = model.default_hparams()
-    with open(os.path.join('models', model_name, 'hparams.json')) as f:
-        hparams.override_from_dict(json.load(f))
-
-    if length > hparams.n_ctx:
-        raise ValueError("Can't get samples longer than window size: %s" % hparams.n_ctx)
-
-    with tf.Session(graph=tf.Graph()) as sess:
-        np.random.seed(seed)
-        tf.set_random_seed(seed)
-        context = tf.placeholder(tf.int32, [1, None])
-        output = sample.sample_sequence(
-            hparams=hparams, length=length,
-            context=context,
-            batch_size=1,
-            temperature=temperature, top_k=top_k
-        )
-
-        print(conversation)
-
-        while True: 
-            saver = tf.train.Saver()
-            ckpt = tf.train.latest_checkpoint(os.path.join('models', model_name))
-            saver.restore(sess, ckpt)
-            message = None
-            while not message:
-                message = input("you: ")
-            conversation = conversation + "\nyou: " + message
-            conversation = conversation + "\nher: "
-            sys.stdout.write("her: ")
-            sys.stdout.flush()
-
-            #sys.stderr.write("************************"+conversation+"***********************")
-            #sys.stderr.flush()
-            
-            encoded_conversation = enc.encode(conversation)
-            #print(len(encoded_conversation))
-            result = sess.run(output, feed_dict={
-                context: [encoded_conversation]
-            })[:, len(encoded_conversation):]
-            text = enc.decode(result[0])
-            
-            #sys.stderr.write("=============="+text+"=================")
-            #sys.stderr.flush()
-
-            splits = text.split('\n')
-            #line = splits[1] if len(splits)>1 else splits[0]
-            #parts = line.split(': ')
-            #reply = parts[1] if len(parts)>1 else parts[0]
-            reply = splits[0]
-            sys.stdout.write(reply+'\n')
-            sys.stdout.flush()
-            conversation = conversation + reply
-
-if __name__ == '__main__':
-    fire.Fire(interact_model)
-

generator/gpt2/src/generate_unconditional_samples.py

@@ -1,81 +0,0 @@
-#!/usr/bin/env python3
-
-import fire
-import json
-import os
-import numpy as np
-import tensorflow as tf
-
-import model, sample, encoder
-
-def sample_model(
-    model_name='124M',
-    seed=None,
-    nsamples=0,
-    batch_size=1,
-    length=None,
-    temperature=1,
-    top_k=0,
-    top_p=1,
-    models_dir='models',
-):
-    """
-    Run the sample_model
-    :model_name=124M : String, which model to use
-    :seed=None : Integer seed for random number generators, fix seed to
-     reproduce results
-    :nsamples=0 : Number of samples to return, if 0, continues to
-     generate samples indefinately.
-    :batch_size=1 : Number of batches (only affects speed/memory).
-    :length=None : Number of tokens in generated text, if None (default), is
-     determined by model hyperparameters
-    :temperature=1 : Float value controlling randomness in boltzmann
-     distribution. Lower temperature results in less random completions. As the
-     temperature approaches zero, the model will become deterministic and
-     repetitive. Higher temperature results in more random completions.
-    :top_k=0 : Integer value controlling diversity. 1 means only 1 word is
-     considered for each step (token), resulting in deterministic completions,
-     while 40 means 40 words are considered at each step. 0 (default) is a
-     special setting meaning no restrictions. 40 generally is a good value.
-     :models_dir : path to parent folder containing model subfolders
-     (i.e. contains the <model_name> folder)
-    """
-    models_dir = os.path.expanduser(os.path.expandvars(models_dir))
-    enc = encoder.get_encoder(model_name, models_dir)
-    hparams = model.default_hparams()
-    with open(os.path.join(models_dir, model_name, 'hparams.json')) as f:
-        hparams.override_from_dict(json.load(f))
-
-    if length is None:
-        length = hparams.n_ctx
-    elif length > hparams.n_ctx:
-        raise ValueError("Can't get samples longer than window size: %s" % hparams.n_ctx)
-
-    with tf.Session(graph=tf.Graph()) as sess:
-        
-        np.random.seed(seed)
-        tf.set_random_seed(seed)
-
-        output = sample.sample_sequence(
-            hparams=hparams, length=length,
-            start_token=enc.encoder['<|endoftext|>'],
-            batch_size=batch_size,
-            temperature=temperature, top_k=top_k, top_p=top_p
-        )[:, 1:]
-
-        saver = tf.train.Saver()
-        ckpt = tf.train.latest_checkpoint(os.path.join(models_dir, model_name))
-        saver.restore(sess, ckpt)
-
-        generated = 0
-        while nsamples == 0 or generated < nsamples:
-            out = sess.run(output)
-            for i in range(batch_size):
-                generated += batch_size
-                text = enc.decode(out[i])
-                print("=" * 40 + " SAMPLE " + str(generated) + " " + "=" * 40)
-                print(text)
-
-if __name__ == '__main__':
-    fire.Fire(sample_model)
-

generator/gpt2/src/interactive_conditional_samples.py

@@ -1,92 +0,0 @@
-#!/usr/bin/env python3
-
-import fire
-import json
-import os
-import numpy as np
-import tensorflow as tf
-
-import model, sample, encoder
-
-def interact_model(
-    model_name='124M',
-    seed=None,
-    nsamples=1,
-    batch_size=1,
-    length=None,
-    temperature=1,
-    top_k=0,
-    top_p=1,
-    models_dir='models',
-):
-    """
-    Interactively run the model
-    :model_name=124M : String, which model to use
-    :seed=None : Integer seed for random number generators, fix seed to reproduce
-     results
-    :nsamples=1 : Number of samples to return total
-    :batch_size=1 : Number of batches (only affects speed/memory).  Must divide nsamples.
-    :length=None : Number of tokens in generated text, if None (default), is
-     determined by model hyperparameters
-    :temperature=1 : Float value controlling randomness in boltzmann
-     distribution. Lower temperature results in less random completions. As the
-     temperature approaches zero, the model will become deterministic and
-     repetitive. Higher temperature results in more random completions.
-    :top_k=0 : Integer value controlling diversity. 1 means only 1 word is
-     considered for each step (token), resulting in deterministic completions,
-     while 40 means 40 words are considered at each step. 0 (default) is a
-     special setting meaning no restrictions. 40 generally is a good value.
-     :models_dir : path to parent folder containing model subfolders
-     (i.e. contains the <model_name> folder)
-    """
-    models_dir = os.path.expanduser(os.path.expandvars(models_dir))
-    if batch_size is None:
-        batch_size = 1
-    assert nsamples % batch_size == 0
-
-    enc = encoder.get_encoder(model_name, models_dir)
-    hparams = model.default_hparams()
-    with open(os.path.join(models_dir, model_name, 'hparams.json')) as f:
-        hparams.override_from_dict(json.load(f))
-
-    if length is None:
-        length = hparams.n_ctx // 2
-    elif length > hparams.n_ctx:
-        raise ValueError("Can't get samples longer than window size: %s" % hparams.n_ctx)
-
-    with tf.Session(graph=tf.Graph()) as sess:
-        context = tf.placeholder(tf.int32, [batch_size, None])
-        np.random.seed(seed)
-        tf.set_random_seed(seed)
-        output = sample.sample_sequence(
-            hparams=hparams, length=length,
-            context=context,
-            batch_size=batch_size,
-            temperature=temperature, top_k=top_k, top_p=top_p
-        )
-
-        saver = tf.train.Saver()
-        ckpt = tf.train.latest_checkpoint(os.path.join(models_dir, model_name))
-        saver.restore(sess, ckpt)
-
-        while True:
-            raw_text = input("Model prompt >>> ")
-            while not raw_text:
-                print('Prompt should not be empty!')
-                raw_text = raw_input("Model prompt >>> ")
-            context_tokens = enc.encode(raw_text)
-            generated = 0
-            for _ in range(nsamples // batch_size):
-                out = sess.run(output, feed_dict={
-                    context: [context_tokens for _ in range(batch_size)]
-                })[:, len(context_tokens):]
-                for i in range(batch_size):
-                    generated += 1
-                    text = enc.decode(out[i])
-                    print("=" * 40 + " SAMPLE " + str(generated) + " " + "=" * 40)
-                    print(text)
-            print("=" * 80)
-
-if __name__ == '__main__':
-    fire.Fire(interact_model)
-

generator/gpt2/src/sample.py

@@ -1,6 +1,6 @@
 import tensorflow as tf
 
-import model
+from generator.gpt2.src import model
 
 def penalize_used(logits, output):
 

generator/gpt2/src/testing_seed.py

@@ -1,15 +0,0 @@
-import numpy as np
-import tensorflow as tf
-
-
-
-seed=None
-
-print(np.random.seed(seed))
-# 
-
-tf.set_random_seed(seed)
-generate = tf.random_uniform(())
-with tf.Session() as sess:
-  print(generate.eval())
-  # 0.96046877