Feed a Tensor of SparseTensors to estimators - tensorflow

Question

To get started with TF, I wanted to learn a predictor of match outcomes for a game. There are three features: the 5 heros on team 0, the 5 heroes on team 1, and the map. The winner is the label, 0 or 1. I want to represent the teams and the maps as SparseTensors. Out of a possible 71 heroes, five will be selected. Likewise for maps, out of a possible 13, one will be selected.
import tensorflow as tf
import packunpack as source
import tempfile
from collections import namedtuple
GameRecord = namedtuple('GameRecord', 'team_0 team_1 game_map winner')
def parse(line):
parts = line.rstrip().split("\t")
return GameRecord(
game_map = parts[1],
team_0 = parts[2].split(","),
team_1 = parts[3].split(","),
winner = int(parts[4]))
def conjugate(record):
return GameRecord(
team_0 = record.team_1,
team_1 = record.team_0,
game_map = record.game_map,
winner = 0 if record.winner == 1 else 1)
def sparse_team(team):
indices = list(map(lambda x: [x], map(source.encode_hero, team)))
return tf.SparseTensor(indices=indices, values = [1] * len(indices), dense_shape=[len(source.heroes_array)])
def sparse_map(map_name):
return tf.SparseTensor(indices=[[source.encode_hero(map_name)]], values = [1], dense_shape=[len(source.maps_array)])
def make_input_fn(filename, shuffle = True, add_conjugate_games = True):
def _fn():
records = []
with open(filename, "r") as raw:
i = 0
for line in raw:
record = parse(line)
records.append(record)
if add_conjugate_games:
# since 0 and 1 are arbitrary team labels, learn and test the conjugate game whenever
# learning the original inference
records.append(conjugate(record))
print("Making team 0")
team_0s = tf.constant(list(map(lambda r: sparse_team(r.team_0), records)))
print("Making team 1")
team_1s = tf.constant(list(map(lambda r: sparse_team(r.team_1), records)))
print("making maps")
maps = tf.constant(list(map(lambda r: sparse_map(r.game_map), records)))
print("Making winners")
winners = tf.constant(list(map(lambda r: tf.constant([r.winner]), records)))
return {
"team_0": team_0s,
"team_1": team_1s,
"game_map": maps,
}, winners
#Please help me finish this function?
return _fn
team_0 = tf.feature_column.embedding_column(
tf.feature_column.categorical_column_with_vocabulary_list("team_0", source.heroes_array), len(source.heroes_array))
team_1 = tf.feature_column.embedding_column(
tf.feature_column.categorical_column_with_vocabulary_list("team_1", source.heroes_array), len(source.heroes_array))
game_map = tf.feature_column.embedding_column(
tf.feature_column.categorical_column_with_vocabulary_list("game_map", source.maps_array), len(source.maps_array))
model_dir = tempfile.mkdtemp()
m = tf.estimator.DNNClassifier(
model_dir=model_dir,
hidden_units = [1024, 512, 256],
feature_columns=[team_0, team_1, game_map])
def main():
m.train(input_fn=make_input_fn("tiny.txt"), steps = 100)
if __name__ == "__main__":
main()
This fails on team_0s = tf.constant(list(map(lambda r: sparse_team(r.team_0), records)))
It's very difficult to understand what tf wants me to return in my input_fn, because all of the examples I can find in the docs ultimately call out to a pandas or numpy helper function, and I'm not familiar with those frameworks. I thought that each dictionary value should be a Tensor containing all examples of a single feature. Each of my examples is a SparseTensor, and I want to simply embed them as their dense versions for the sake of the DNNClassifier.
I'm sure my mental model is horribly broken right now, and I appreciate any help setting it straight.
Error output:
python3 estimator.py
Making team 0
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 468, in make_tensor_proto
str_values = [compat.as_bytes(x) for x in proto_values]
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 468, in <listcomp>
str_values = [compat.as_bytes(x) for x in proto_values]
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/compat.py", line 65, in as_bytes
(bytes_or_text,))
TypeError: Expected binary or unicode string, got <tensorflow.python.framework.sparse_tensor.SparseTensor object at 0x7fe8
b4d7aef0>
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "estimator.py", line 79, in <module>
main()
File "estimator.py", line 76, in main
m.train(input_fn=make_input_fn("tiny.txt"), steps = 100)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 302, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 709, in _train_model
input_fn, model_fn_lib.ModeKeys.TRAIN)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 577, in _get_features_and_l
abels_from_input_fn
result = self._call_input_fn(input_fn, mode)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 663, in _call_input_fn
return input_fn(**kwargs)
File "estimator.py", line 44, in _fn
team_0s = tf.constant(list(map(lambda r: sparse_team(r.team_0), records)))
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py", line 208, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 472, in make_tensor_proto
"supported type." % (type(values), values))
TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [<tensorflow.python.framework.sparse_tenso
r.SparseTensor object at 0x7fe8b4d7aef0>, <tensorflow.python.framework.sparse_tensor.SparseTensor object at 0x7fe8b4d7af28
>, <tensorflow.python.framework.sparse_tensor.SparseTensor object at 0x7fe8b4d7af60>, <tensorflow.python.framework.sparse_
tensor.SparseTensor object at 0x7fe8b4d7aeb8> ... ]

Answer 1

Ultimately it wasn't necessary to convert my text representation into sparse vectors in my input_fn. Instead I had to tell the model to expect an input of an array of strings, which it understands how to convert into a "bag of words" or n-hot vector and how to embed as dense vectors.
import tensorflow as tf
import tempfile
import os
from collections import namedtuple
GameRecord = namedtuple('GameRecord', 'team_0 team_1 game_map winner')
def parse(line):
parts = line.rstrip().split("\t")
return GameRecord(
game_map = parts[1],
team_0 = parts[2].split(","),
team_1 = parts[3].split(","),
winner = int(parts[4]))
def conjugate(record):
return GameRecord(
team_0 = record.team_1,
team_1 = record.team_0,
game_map = record.game_map,
winner = 0 if record.winner == 1 else 1)
def make_input_fn(filename, batch_size=128, shuffle = True, add_conjugate_games = True, epochs=1):
def _fn():
records = []
with open(filename, "r") as raw:
i = 0
for line in raw:
record = parse(line)
records.append(record)
if add_conjugate_games:
records.append(conjugate(record))
team_0s = tf.constant(list(map(lambda r: r.team_0, records)))
team_1s = tf.constant(list(map(lambda r: r.team_1, records)))
maps = tf.constant(list(map(lambda r: r.game_map, records)))
winners = tf.constant(list(map(lambda r: [r.winner],
return {
"team_0": team_0s,
"team_1": team_1s,
"game_map": maps,
}, winners
return _fn
team_0 = tf.feature_column.embedding_column(
tf.feature_column.categorical_column_with_vocabulary_list("team_0", source.heroes_array), dimension=len(source.heroes_array))
team_1 = tf.feature_column.embedding_column(
tf.feature_column.categorical_column_with_vocabulary_list("team_1", source.heroes_array), dimension=len(source.heroes_array))
game_map = tf.feature_column.embedding_column(
tf.feature_column.categorical_column_with_vocabulary_list("game_map", source.maps_array), dimension=len(source.maps_array))
model_dir = "DNNClassifierModel_00"
os.mkdir(model_dir)
m = tf.estimator.DNNClassifier(
model_dir=model_dir,
hidden_units = [1024, 512, 256],
feature_columns=[team_0, team_1, game_map])
def main():
m.train(input_fn=make_input_fn("training.txt"))
results = m.evaluate(input_fn=make_input_fn("validation.txt"))
print("model directory = %s" % model_dir)
for key in sorted(results):
print("%s: %s" % (key, results[key]))
if __name__ == "__main__":
main()
Note that this code isn't perfect yet. I need to add in batching.