fchollet

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data
In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/
- created cats/ and dogs/ subfolders inside train/ and validation/
- put the cat pictures index 0-999 in data/train/cats

rondy

FWIW: I (@rondy) am not the creator of the content shared here, which is an excerpt from Edmond Lau's book. I simply copied and pasted it from another location and saved it as a personal note, before it gained popularity on news.ycombinator.com. Unfortunately, I cannot recall the exact origin of the original source, nor was I able to find the author's name, so I am can't provide the appropriate credits.

---

Effective Engineer - Notes

• By Edmond Lau
• Highly Recommended 👍
• http://www.theeffectiveengineer.com/

What's an Effective Engineer?

shagunsodhani

Learning to Generate Reviews and Discovering Sentiment

Summary

The authors train a character-RNN (using mLSTM units) over Amazon Product Reviews (82 million reviews) and use the char-RNN as the feature extractor for sentiment analysis. These unsupervised features beat state of the art results for the dataset while are outperformed by supervised approaches on other datasets. Most important observation is that the authors find a single neuron (called as the sentiment neuron) which alone achieves a test accuracy of 92.3% thus giving the impression that the sentiment concept has been captured in that single neuron. Switching this neuron on (or off) during the generative process produces positive (or negative) reviews.

Notes

• The paper aims to evaluate if the low level features captured by char-RNN can support learning of high-level representations.

omoindrot

"""
Example TensorFlow script for finetuning a VGG model on your own data.
Uses tf.contrib.data module which is in release v1.2
Based on PyTorch example from Justin Johnson
(https://gist.github.com/jcjohnson/6e41e8512c17eae5da50aebef3378a4c)

Required packages: tensorflow (v1.2)
Download the weights trained on ImageNet for VGG:
```
wget http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz

ed-alertedh

import tensorflow as tf


def validate_dataset(filenames, reader_opts=None):
    """
    Attempt to iterate over every record in the supplied iterable of TFRecord filenames
    :param filenames: iterable of filenames to read
    :param reader_opts: (optional) tf.python_io.TFRecordOptions to use when constructing the record iterator
    """
    i = 0

lioutasb

import tensorflow as tf

def mrr_metric(labels, predictions, weights=None,
              metrics_collections=None,
              updates_collections=None,
              name=None):
    
    with tf.name_scope(name, 'mrr_metric', [predictions, labels, weights]) as scope:

    

peter0749

def att_loss(y_true, y_pred):
    def att_(x):
        a = tf.where(x>0, K.exp(x), K.zeros_like(x))
        return a / (K.sum(a, axis=-1, keepdims=True)+K.epsilon())
    y_true_a = att_(y_true)
    y_pred_a = att_(y_pred)
    loss = K.mean(K.binary_crossentropy(y_true_a, y_pred_a), axis=-1)
    return loss