f-rumblefish’s gists

f-rumblefish / multi-label-classification-in-keras.py

Created June 16, 2018 03:57

	from keras.models import Sequential
	from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D, Dense
	from keras.callbacks import EarlyStopping

	################################################################################
	# Build the model
	################################################################################
	model = Sequential()

	model.add(Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=input_shape_img))

f-rumblefish / meta_data.txt

Last active September 27, 2022 07:50

	file_name one_hot_encoding ordered_labels ordered_categories
	----------------------------------------------------------------------------------------------------
	0.png [0, 1, 1, 1, 0, 0, 1, 0, 0, 0] [6, 3, 2, 1] [Shirt, Dress, Pullover, Trouser]
	1.png [1, 0, 0, 0, 1, 1, 1, 0, 0, 0] [5, 4, 0, 6] [Sandal, Coat, T-shirt/top, Shirt]
	2.png [1, 1, 0, 1, 0, 0, 0, 0, 0, 0] [1, 3, 0, 3] [Trouser, Dress, T-shirt/top, Dress]
	3.png [0, 0, 0, 0, 0, 1, 1, 1, 0, 0] [5, 5, 7, 6] [Sandal, Sandal, Sneaker, Shirt]

f-rumblefish / Training_Epoch15.txt

Last active June 9, 2018 13:26

Trainging for Multi-Label Classification

	Train on 9000 samples, validate on 1000 samples
	Epoch 1/15
	9000/9000 [==============================] - 1865s 207ms/step - loss: 0.6278 - acc: 0.6629 - val_loss: 0.5947 - val_acc: 0.6845
	Epoch 2/15
	9000/9000 [==============================] - 1810s 201ms/step - loss: 0.5216 - acc: 0.7424 - val_loss: 0.4472 - val_acc: 0.7916
	Epoch 3/15
	9000/9000 [==============================] - 1789s 199ms/step - loss: 0.4024 - acc: 0.8191 - val_loss: 0.3396 - val_acc: 0.8529
	Epoch 4/15
	9000/9000 [==============================] - 1817s 202ms/step - loss: 0.3204 - acc: 0.8646 - val_loss: 0.3059 - val_acc: 0.8740
	Epoch 5/15

f-rumblefish / Performance under Different Algorithms

Created April 24, 2018 09:56

f-rumblefish / Multilayer Perceptron

Created April 24, 2018 09:06

	_________________________________________________________________
	Layer (type) Output Shape Param #
	=================================================================
	dense_1 (Dense) (None, 32) 16032
	_________________________________________________________________
	activation_1 (Activation) (None, 32) 0
	_________________________________________________________________
	dense_2 (Dense) (None, 32) 1056
	_________________________________________________________________
	activation_2 (Activation) (None, 32) 0

f-rumblefish / scikit-learn-classifier.py

Created April 24, 2018 08:48

	# import library from Scikit-Learn ---------------------------------------------
	from sklearn.metrics import accuracy_score
	from sklearn.metrics import confusion_matrix

	# algorithm 1 ------------------------------------------------------------------
	print(" Naive Bayes ... ")

	start = timeit.default_timer()
	from sklearn import naive_bayes
	classifier = naive_bayes.GaussianNB()

f-rumblefish / original_notes.txt

Created August 5, 2017 09:38

Original Data

60, 67, 63, 60, 65, 62, 60, 67, 63, 60, 65, 62, 60, 67, 63, 60, 65, 62, 60, 67, ...

f-rumblefish / train_data.txt

Created August 5, 2017 09:32

Training Data

f-rumblefish / Keras_sample.py

Last active August 4, 2017 09:56

Recurrent Neural Network (LSTM) in Keras

	# Import library in Keras 1.2.0
	from keras.layers.recurrent import SimpleRNN, GRU, LSTM
	from keras.models import Sequential
	from keras.layers import Dense, Activation
	from keras.callbacks import EarlyStopping
	from keras.utils.visualize_util import plot

	# Define parameters
	HIDDEN_SIZE = 128
	BATCH_SIZE = 10

f-rumblefish / hello_simple_player.py

Last active January 7, 2023 01:50

Using pygame to play notes

	# import library ---------------------------------------------------------------
	import pygame.midi
	import time

	# define all the constant values -----------------------------------------------
	device = 0 # device number in win10 laptop
	instrument = 9 # http://www.ccarh.org/courses/253/handout/gminstruments/
	note_Do = 48 # http://www.electronics.dit.ie/staff/tscarff/Music_technology/midi/midi_note_numbers_for_octaves.htm
	note_Re = 50
	note_Me = 52