Commit 0d5c21b8 authored by Rudolf Chrispens's avatar Rudolf Chrispens
Browse files

reworked a lot to get started with new model

parent 7b828692

caption-lib/.vscode/settings.json

+2 −1
Original line number Diff line number Diff line 
{

    "python.pythonPath": "/usr/local/opt/python/bin/python3.6",

    "python.linting.pylintEnabled": true,

    "python.linting.pylintEnabled": false,

    "python.linting.flake8Enabled": true,

    "python.linting.enabled": true,

    "python.linting.pylintArgs": [
@@ -16,5 +16,6 @@ 
        "**/*.pyc": true,

        "cnn/":true,

        "rnn/":true,

        "**/__pycache__/":true,

    }

}
 
 No newline at end of file

caption-lib/lstm/Models/__init__.py

0 → 100644
+5 −0
Original line number Diff line number Diff line 
from .coco_model import coco_model



__all__ = [

    'coco_model'

]
 
 No newline at end of file

caption-lib/lstm/Models/coco_model.py

+1 −1
Original line number Diff line number Diff line
@@ -14,7 +14,7 @@ from __future__ import division 


import tensorflow as tf



class CaptionGenerator(object):

class coco_model(object):

    def __init__(self, word_to_idx, dim_feature=[196, 512], dim_embed=512, dim_hidden=1024, n_time_step=16,

                  prev2out=True, ctx2out=True, alpha_c=0.0, selector=True, dropout=True):

        """

caption-lib/lstm/Readers/__init__.py

+3 −6
Original line number Diff line number Diff line 
# reader init

# from .basic_text_reader import basic_text_reader

# from .basic_text_reader import get_words_as_int

# from .basic_text_reader import get_integers_as_words

# from .basic_masa_reader import basic_masa_reader

from .helper import get_input_data

from .helper import get_vocabulary

from .helper import get_sequences

from .helper import check_folders

from .basic_masa_reader import basic_masa_reader

from .coco_reader import coco_reader



__all__ = [

    'get_input_data',

    'get_vocabulary',

    'get_sequences',

    'check_folders',

    'basic_masa_reader'

    'basic_masa_reader',

    'coco_reader'

]

caption-lib/lstm/Readers/coco_reader.py

+1 −15
Original line number Diff line number Diff line
@@ -6,30 +6,18 @@ import tensorflow as tf 
from lstm.Readers import helper

import pickle



"""To run this code, you'll need to first download and extract the text dataset

    from here: http://www.fit.vutbr.cz/~imikolov/rnnlm/simple-examples.tgz. Change the

    data_path variable below to your local exraction path"""



# data_path = "C:\\Users\Andy\Documents\simple-examples\data"



# parser = argparse.ArgumentParser()

# parser.add_argument('run_opt', type=int, default=1, help='An integer: 1 to train, 2 to test')

# parser.add_argument('--data_path', type=str, default=data_path, help='The full path of the training data')

# args = parser.parse_args()



"""

with open('interface_train_30pics_per_category.picle', 'rb') as handle:

    data = picle.load(handle)

"""



class basic_masa_reader:

class coco_reader:

    def read_input(self, filename: str):

        with tf.gfile.GFile(helper.inputPath + filename, "r") as f:

            if(config.reader.verbose is True):

                print("")

            return f.read().replace("\n", "<eos>").split()





    def create_vocabulary(self, filename: str):

        data = self.read_input(filename + config.reader.input_data_type)
@@ -41,12 +29,10 @@ class basic_masa_reader: 


        return word_to_id





    def file_to_word_ids(self, filename: str, word_to_id):

        data = self.read_input(filename + config.reader.input_data_type)

        return [word_to_id[word] for word in data if word in word_to_id]





    def load_data(self):

        # build the complete vocabulary, then convert text data to list of integers

        word_to_id = self.create_vocabulary(config.path.input_train)