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/ | |
- created cats/ and dogs/ subfolders inside train/ and validation/ | |
- put the cat pictures index 0-999 in data/train/cats |
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
import tensorflow as tf | |
import numpy as np | |
FC_SIZE = 1024 | |
DTYPE = tf.float32 | |
def _weight_variable(name, shape): | |
return tf.get_variable(name, shape, DTYPE, tf.truncated_normal_initializer(stddev=0.1)) |
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 scipy.io.wavfile import read, write | |
import io | |
## This may look a bit intricate/useless, considering the fact that scipy's read() and write() function already return a | |
## numpy ndarray, but the BytesIO "hack" may be useful in case you get the wav not through a file, but trough some websocket or | |
## HTTP Post request. This should obviously work with any other sound format, as long as you have the proper decoding function | |
with open("input_wav.wav", "rb") as wavfile: | |
input_wav = wavfile.read() |