This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
'''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/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
'''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/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
$ 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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{"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": |