# to pass in all the keyword arguments coming
# from `ColorizedInputDescriber`:
##### YOUR CODE HERE
# Return a `ColorizedEncoderDecoder` that uses
# your encoder and decoder:
##### YOUR CODE HERE
# That's it! Since these modifications are pretty intricate, you might want to use [a toy dataset](colors_overview.ipynb#Toy-problems-for-development-work) to debug it:
# In[ ]:
toy_color_seqs, toy_word_seqs, toy_vocab = create_example_dataset(
group_size=50, vec_dim=2)
# In[ ]:
toy_color_seqs_train, toy_color_seqs_test, toy_word_seqs_train, toy_word_seqs_test = train_test_split(
toy_color_seqs, toy_word_seqs)
# In[ ]:
toy_mod = ColorizedInputDescriber(toy_vocab,
embed_dim=10,
hidden_dim=10,
max_iter=100,
batch_size=128)
# In[ ]:
def dataset():
color_seqs, word_seqs, vocab = create_example_dataset(group_size=50,
vec_dim=2)
return color_seqs, word_seqs, vocab
def color_describer_dataset():
color_seqs, word_seqs, vocab = torch_color_describer.create_example_dataset(
group_size=50, vec_dim=2)
return color_seqs, word_seqs, vocab
from colors import ColorsCorpusReader
import os
import pandas as pd
from sklearn.model_selection import train_test_split
import torch
from torch_color_describer import (ContextualColorDescriber,
create_example_dataset)
import utils
from utils import START_SYMBOL, END_SYMBOL, UNK_SYMBOL
tiny_contexts, tiny_words, tiny_vocab = create_example_dataset(group_size=3,
vec_dim=2)
toy_mod = ContextualColorDescriber(
tiny_vocab,
embedding=None, # Option to supply a pretrained matrix as an `np.array`.
embed_dim=10,
hidden_dim=20,
max_iter=100,
eta=0.01,
optimizer=torch.optim.Adam,
batch_size=128,
l2_strength=0.0,
warm_start=False,
device=None)
_ = toy_mod.fit(tiny_contexts, tiny_words)
metric = toy_mod.listener_accuracy(tiny_contexts, tiny_words)
print("listener_accuracy:", metric)
