deep learning Archives - Ilmu Pengetahuan & Teknologi

Gopher Language Model

DeepMind introduces a 280B parameter language model named Gopher. Investigates its effectiveness in reading comprehension & other complex tasks such as logical reasoning. Ethics & risks are also discussed.

Links:

Article: https://deepmind.com/blog/article/language-modelling-at-scale

Paper: “Scaling Language Models: Methods, Analysis & Insights from Training Gopher“

Introduction to Deep Learning (MIT 6.S191)

URL: http://introtodeeplearning.com/

Simple Image Classification with Keras

Keras logo

There are several kind of image classification:

Binary classification
Multiclass classification
Multi label classification

Image generation method for training

image.ImageGenerator.flow_from_directory()
image.ImageGenerator.flow()

Various models for training (built on model)

Xception
VGG16
VGG19
Resnet50
InceptionV3
InceptionResNetV2
MobileNet
DenseNet
NASNet
MobileNetV2

Keras built in models usually have pre-trained weight on Imagenet, which significantly speeds up training, but those weights are only available for some image sizes.

There are two techniques to feed image files for prediction in Keras:

keras.preprocessing.image.flow_from_directory()
keras.preprocessing.image.flow()

Simple Tutorials

Simple Binary Image Classifier with Keras with flow_from_directory()
Simple Binary Image Classifier with Keras with flow()
Simple Multiclass Image Classification with Keras and flow_from_directory()
Simple Multiclass Image Classification with Keras and flow()
Simple Multi Label Image Classification with Keras and flow()

Reference

How to Save a Keras Model to a JSON file

To save a keras model to a json file, simply use this code:

model_json = model.to_json()
with open(“model.json”, “w”) as json_file:
json_file.write(model_json)

where model is a keras model object.

Image Captioning Models and Fabrik

No	Name	URL	Framework	Note	Fabrik
1	NeuralTalk	https://github.com/karpathy/neuraltalk	Python + numpy	obsoleted by NeuralTalk2
2	NeuralTalk2	https://github.com/karpathy/neuraltalk2	Torch		Torch incompatible with Fabriq
3	Show and Tell	https://github.com/tensorflow/models/tree/master/research/im2txt	Tensorflow		Tensorflow parser Fabriq incompatible with Fabriq
4	Keras Image Caption	https://github.com/LemonATsu/Keras-Image-Caption	Keras	requires python 3.4+ fail with python 3.6
5	Image Captioning with Spatial Attention in Keras	https://github.com/amaiasalvador/imcap_keras	Keras		need MSCOCO
6	Neural Image Captioning	https://github.com/oarriaga/neural_image_captioning	Keras		TimeDistributed Layer incompatible with

I want to add an Image Captioning model to Fabrik. It seems pretty easy, all you have to do is find a JSON format of the model you want, and there you go! All done. But in reality, it wasn’t that easy.

First, I have to find an image captioning mode. My first choice landed to NeuralTalk since it’s pretty popular. After heading to the GitHub page, it seems like NeuralTalk is obsoleted by NeuralTalk2, so I take NeuralTalk2 After having a hard time trying to install it and trying to make the JSON file, I realized something. NeuralTalk2 use torch as its framework and Fabrik doesn’t support torch. Fabrik only supports Caffe, Keras, and Tensorflow. (I never made the JSON file by the way)

I have to try another model. I ended up trying Neural Image Captioning by oarriaga on github. Unlike NeuralTalk2, making the JSON file was pretty smooth.

So I try to find another model. Show and Tell looks good. It uses Tensorflow as its framework, but unfortunately Fabrik <><><>< so I have to find another model