louislung

Factorised RankNet TensorFlow Implementation

For details please check this blog post

keywords: learning to rank | tensorflow | keras | custom training loop | ranknet | lambdaRank | recommendation

blepfo

TensorFlow Best Practices as of Q1 2018

By Adam Anderson

adam.b.anderson.96@gmail.com

Preface

This write-up assumes you have an general understanding of the TensorFlow programming model, but maybe you haven't kept up to date with the latest library features/standard practices.

higepon

import numpy as np
import tensorflow as tf
from tensorflow.python.layers import core as layers_core

hparams = tf.contrib.training.HParams(
    batch_size=3,
    encoder_length=4,
    decoder_length=5,
    num_units=6,
    src_vocab_size=7,

dolaameng

"""Script to illustrate usage of tf.estimator.Estimator in TF v1.3"""
import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data as mnist_data
from tensorflow.contrib import slim
from tensorflow.contrib.learn import ModeKeys
from tensorflow.contrib.learn import learn_runner


# Show debugging output

damienpontifex

import argparse
import psutil
import tensorflow as tf
from typing import Dict, Any, Callable, Tuple

## Data Input Function
def data_input_fn(data_param,
                  batch_size:int=None,
                  shuffle=False) -> Callable[[], Tuple]:
    """Return the input function to get the test data.

peterroelants

"""Script to illustrate usage of tf.estimator.Estimator in TF v1.3"""
import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data as mnist_data
from tensorflow.contrib import slim
from tensorflow.contrib.learn import ModeKeys
from tensorflow.contrib.learn import learn_runner


# Show debugging output

teamdandelion

7
2
1
0
4
1
4
9
5
9

benwu232

import tensorflow as tf

tf.GraphKeys.USEFUL = 'useful'

saver = tf.train.import_meta_graph("./model_ex1.meta")
sess = tf.Session()
saver.restore(sess, "./model_ex1")

var_list = tf.get_collection(tf.GraphKeys.USEFUL)
v1 = var_list[0]

floriandotpy

#!/usr/bin/python3

from cnn import cnn
import hyperopt


def objective(args):

    params = cnn.ExperimentParameters()

siemanko

"""Short and sweet LSTM implementation in Tensorflow.

Motivation:
When Tensorflow was released, adding RNNs was a bit of a hack - it required
building separate graphs for every number of timesteps and was a bit obscure
to use. Since then TF devs added things like `dynamic_rnn`, `scan` and `map_fn`.
Currently the APIs are decent, but all the tutorials that I am aware of are not
making the best use of the new APIs.

Advantages of this implementation: