asmith26

## classifier_from_little_data_script_3.py
'''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/

## classifier_from_little_data_script_2.py
'''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/

## model.to_yaml-error.log
$ python create_SDmodel_json_or_yaml.py
Using Theano backend.
/usr/local/lib/python2.7/dist-packages/yaml/representer.py:142: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.
  if data in [None, ()]:
Traceback (most recent call last):
  File "train.py", line 167, in <module>
    f.write( model.to_yaml() )
  File "/home/andyandy/git/keras/keras/engine/topology.py", line 2407, in to_yaml
    return yaml.dump(self._updated_config(), **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/yaml/__init__.py", line 202, in dump

## create_SDmodel_json_or_yaml.py
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np
np.random.seed(2 ** 10)

# Prevent reaching to maximum recursion depth in `theano.tensor.grad`
# import sys
# sys.setrecursionlimit(2 ** 20)

## model.json
{"loss": "categorical_crossentropy", "optimizer": {"nesterov": true, "lr": 0.10000000149011612, "name": "SGD", "momentum": 0.8999999761581421, "decay": 0.0}, "class_name": "Model", "loss_weights": null, "keras_version": "1.0.3", "config": {"layers": [{"class_name": "InputLayer", "config": {"batch_input_shape": [null, 3, 32, 32], "name": "input_1", "input_dtype": "float32"}, "inbound_nodes": [], "name": "input_1"}, {"class_name": "Convolution2D", "config": {"W_constraint": null, "b_constraint": null, "name": "convolution2d_1", "activity_regularizer": null, "trainable": true, "dim_ordering": "th", "nb_col": 3, "subsample": [1, 1], "init": "glorot_uniform", "bias": true, "nb_filter": 16, "border_mode": "same", "b_regularizer": null, "W_regularizer": {"l2": 9.999999747378752e-05, "name": "WeightRegularizer", "l1": 0.0}, "activation": "linear", "nb_row": 3}, "inbound_nodes": [[["input_1", 0, 0]]], "name": "convolution2d_1"}, {"class_name": "BatchNormalization", "config": {"name": "batchnormalization_1", "epsilon":
	'''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/
	$ python create_SDmodel_json_or_yaml.py
	Using Theano backend.
	/usr/local/lib/python2.7/dist-packages/yaml/representer.py:142: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.
	if data in [None, ()]:
	Traceback (most recent call last):
	File "train.py", line 167, in <module>
	f.write( model.to_yaml() )
	File "/home/andyandy/git/keras/keras/engine/topology.py", line 2407, in to_yaml
	return yaml.dump(self._updated_config(), **kwargs)
	File "/usr/local/lib/python2.7/dist-packages/yaml/__init__.py", line 202, in dump
	from __future__ import absolute_import
	from __future__ import division
	from __future__ import print_function

	import numpy as np
	np.random.seed(2 ** 10)

	# Prevent reaching to maximum recursion depth in `theano.tensor.grad`
	# import sys
	# sys.setrecursionlimit(2 ** 20)