Skip to content
Snippets Groups Projects
Commit bb86864d authored by Timothé Boulet's avatar Timothé Boulet :alien:
Browse files

bugfix

parent b943fe14
No related branches found
No related tags found
No related merge requests found
Show whitespace changes
Inline Side-by-side
Showing
with 2 additions and 2 deletions
buildEmotionModel.ipynb
+ 2
− 2
View file @ bb86864d
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
#@title Imports #@title Imports
#%load_ext autoreload #Need to uncomment for import sometime, dont understand #%load_ext autoreload #Need to uncomment for import sometime, dont understand
#Tensorflow : #Tensorflow :
import tensorflow as tf import tensorflow as tf
from tensorflow import keras from tensorflow import keras
from tensorflow.keras import datasets, layers, models, losses from tensorflow.keras import datasets, layers, models, losses
import tensorflow_datasets as tfds import tensorflow_datasets as tfds
#from google.colab import files #from google.colab import files
#Others : #Others :
from matplotlib import image from matplotlib import image
import os import os
import numpy as np import numpy as np
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import matplotlib import matplotlib
import random as rd import random as rd
import cv2 import cv2
import csv import csv
#Data loaders : #Data loaders :
from loadFer2013DS import * from loadFer2013DS import *
from loadRavdessDS import * from loadRavdessDS import *
from loadExpWDS import * from loadExpWDS import *
from loadAffwildDS import * from loadAffwildDS import *
#Others #Others
from utils import * from utils import *
from config import * from config import *
``` ```
%% Output %% Output
INFO:tensorflow:Enabling eager execution INFO:tensorflow:Enabling eager execution
INFO:tensorflow:Enabling v2 tensorshape INFO:tensorflow:Enabling v2 tensorshape
INFO:tensorflow:Enabling resource variables INFO:tensorflow:Enabling resource variables
INFO:tensorflow:Enabling tensor equality INFO:tensorflow:Enabling tensor equality
INFO:tensorflow:Enabling control flow v2 INFO:tensorflow:Enabling control flow v2
WARNING:tensorflow:SavedModel saved prior to TF 2.5 detected when loading Keras model. Please ensure that you are saving the model with model.save() or tf.keras.models.save_model(), *NOT* tf.saved_model.save(). To confirm, there should be a file named "keras_metadata.pb" in the SavedModel directory. WARNING:tensorflow:SavedModel saved prior to TF 2.5 detected when loading Keras model. Please ensure that you are saving the model with model.save() or tf.keras.models.save_model(), *NOT* tf.saved_model.save(). To confirm, there should be a file named "keras_metadata.pb" in the SavedModel directory.
Model used: firstModel Model used: firstModel
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
#Chargement des données #Chargement des données
print("Array loading...") print("Array loading...")
Xf = np.load("data/array/Xf") Xf = np.load("data/array/Xf")
Xe = np.load("data/array/Xe") Xe = np.load("data/array/Xe")
Xa = np.load("data/array/Xa") Xa = np.load("data/array/Xa")
Xr = np.load("data/array/Xr") Xr = np.load("data/array/Xr")
Yf = np.load("data/array/Yf") Yf = np.load("data/array/Yf")
Ye = np.load("data/array/Ye") Ye = np.load("data/array/Ye")
Ya = np.load("data/array/Ya") Ya = np.load("data/array/Ya")
Yr = np.load("data/array/Yr") Yr = np.load("data/array/Yr")
print("Concatenation...") print("Concatenation...")
X = np.concatenate([Xf, Xa, Xe, Xr]) X = np.concatenate([Xf, Xa, Xe, Xr])
Y = np.concatenate([Yf, Ya, Ye, Yr]) Y = np.concatenate([Yf, Ya, Ye, Yr])
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
#Enregistre X et Y directement, à faire si assez de ram #Enregistre X et Y directement, à faire si assez de ram
np.save("data/array/X", X) np.save("data/array/X", X)
np.save("data/array/Y", Y) np.save("data/array/Y", Y)
def loadData(): def loadData():
return np.load("data/array/X"), np.load("data/array/Y") return np.load("data/array/X"), np.load("data/array/Y")
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
#@title Visualisation de chaque dataset #@title Visualisation de chaque dataset
for X, Y, name in zip([Xf, Xr, Xe, Xa], [Yf, Yr, Ye, Ya], ["fer2013", "ravdess", "expW", "affwild"]): for X, Y, name in zip([Xf, Xr, Xe, Xa], [Yf, Yr, Ye, Ya], ["fer2013", "ravdess", "expW", "affwild"]):
N=5 N=5
M=5 M=5
print("Dataset:", name) print("Dataset:", name)
print("Images:", X.shape, "La bels:", Y.shape) print("Images:", X.shape, "La bels:", Y.shape)
plt.figure() plt.figure()
for i in range(N*M): for i in range(N*M):
if X.shape[0] == 0: continue if X.shape[0] == 0: continue
k = rd.randrange(X.shape[0]) k = rd.randrange(X.shape[0])
plt.subplot(N, M, i+1) plt.subplot(N, M, i+1)
plt.xticks([]) plt.xticks([])
plt.yticks([]) plt.yticks([])
plt.grid(False) plt.grid(False)
afficher(X[k]) afficher(X[k])
plt.title(emotions[int(Y[k])]) plt.title(emotions[int(Y[k])])
plt.show() plt.show()
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
#Visualisation du dataset global #Visualisation du dataset global
print("X_train:", X_train.shape) print("X_train:", X_train.shape)
print("Y_train:", Y_train.shape) print("Y_train:", Y_train.shape)
print("\nX_test:", X_test.shape) print("\nX_test:", X_test.shape)
print("Y_test:", Y_test.shape) print("Y_test:", Y_test.shape)
N=5 N=5
M=5 M=5
plt.figure() plt.figure()
for i in range(N*M): for i in range(N*M):
k = rd.randrange(X_train.shape[0]) k = rd.randrange(X_train.shape[0])
plt.subplot(N, M, i+1) plt.subplot(N, M, i+1)
plt.xticks([]) plt.xticks([])
plt.yticks([]) plt.yticks([])
plt.grid(False) plt.grid(False)
afficher(X_train[k]) afficher(X_train[k])
plt.title(emotions[int(Y_train[k])]) plt.title(emotions[int(Y_train[k])])
plt.show() plt.show()
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
#@title Hyperparamètres #@title Hyperparamètres
epochs = 2 epochs = 2
batch_size = 128 batch_size = 128
validation_size = 0.1 validation_size = 0.1
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
#Labels catégoriques #Labels catégoriques
Ycat = keras.utils.to_categorical(Y) Ycat = keras.utils.to_categorical(Y)
print("X", X_train.shape) print("X", X.shape)
print("Y", Y_train_cat.shape) print("Y", Ycat.shape)
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
#MODELE #MODELE
class MyModel(keras.Sequential): class MyModel(keras.Sequential):
def __init__(self, input_shape): def __init__(self, input_shape):
super(MyModel, self).__init__() super(MyModel, self).__init__()
#Pre processing #Pre processing
self.add(keras.layers.experimental.preprocessing.RandomContrast(factor=(0.5,0.5))) self.add(keras.layers.experimental.preprocessing.RandomContrast(factor=(0.5,0.5)))
self.add(keras.layers.experimental.preprocessing.RandomFlip(mode="horizontal")) self.add(keras.layers.experimental.preprocessing.RandomFlip(mode="horizontal"))
#48*48 *1 #48*48 *1
self.add(keras.layers.Conv2D(32, kernel_size = (3, 3), activation = 'relu', input_shape = input_shape)) self.add(keras.layers.Conv2D(32, kernel_size = (3, 3), activation = 'relu', input_shape = input_shape))
self.add(keras.layers.MaxPooling2D(pool_size = 2)) self.add(keras.layers.MaxPooling2D(pool_size = 2))
self.add(keras.layers.BatchNormalization()) self.add(keras.layers.BatchNormalization())
#23*23 *32 #23*23 *32
self.add(keras.layers.Conv2D(64, kernel_size = (3, 3), activation = 'relu')) self.add(keras.layers.Conv2D(64, kernel_size = (3, 3), activation = 'relu'))
self.add(keras.layers.MaxPooling2D(pool_size = 2)) self.add(keras.layers.MaxPooling2D(pool_size = 2))
self.add(keras.layers.BatchNormalization()) self.add(keras.layers.BatchNormalization())
#10*10 *64 #10*10 *64
self.add(keras.layers.Conv2D(128, kernel_size = (3, 3), activation = 'relu')) self.add(keras.layers.Conv2D(128, kernel_size = (3, 3), activation = 'relu'))
self.add(keras.layers.MaxPooling2D(pool_size = 2)) self.add(keras.layers.MaxPooling2D(pool_size = 2))
self.add(keras.layers.BatchNormalization()) self.add(keras.layers.BatchNormalization())
#4*4 *128 #4*4 *128
self.add(keras.layers.Conv2D(256, kernel_size = (3, 3), activation = 'relu')) self.add(keras.layers.Conv2D(256, kernel_size = (3, 3), activation = 'relu'))
self.add(keras.layers.MaxPooling2D(pool_size = 2)) self.add(keras.layers.MaxPooling2D(pool_size = 2))
self.add(keras.layers.BatchNormalization()) self.add(keras.layers.BatchNormalization())
#1*1 *256 #1*1 *256
self.add(keras.layers.Flatten()) self.add(keras.layers.Flatten())
self.add(keras.layers.Dense(128, activation = 'relu')) self.add(keras.layers.Dense(128, activation = 'relu'))
self.add(keras.layers.Dropout(0.2)) self.add(keras.layers.Dropout(0.2))
self.add(keras.layers.Dense(64, activation = 'relu')) self.add(keras.layers.Dense(64, activation = 'relu'))
self.add(keras.layers.Dropout(0.2)) self.add(keras.layers.Dropout(0.2))
#self.add(keras.layers.BatchNormalization()) #self.add(keras.layers.BatchNormalization())
self.add(keras.layers.Dense(7, activation = 'softmax')) self.add(keras.layers.Dense(7, activation = 'softmax'))
#7 #7
def predir(self, monImage): def predir(self, monImage):
return self.predict(np.array([monImage]))[0,:] return self.predict(np.array([monImage]))[0,:]
def compile_o(self): def compile_o(self):
self.compile(optimizer = 'adam', loss=losses.categorical_crossentropy, metrics = ['accuracy']) self.compile(optimizer = 'adam', loss=losses.categorical_crossentropy, metrics = ['accuracy'])
myModel = MyModel(input_shape) myModel = MyModel(input_shape)
myModel.compile_o() myModel.compile_o()
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
theImage = X_train[0] theImage = X_train[0]
afficher(theImage) afficher(theImage)
print(predir(myModel, theImage)) print(predir(myModel, theImage))
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
history = myModel.fit(X, Y, epochs=5, validation_rate=0.05) history = myModel.fit(X, Y, epochs=5, validation_rate=0.05)
#Affichage de l'historique de l'apprentissage #Affichage de l'historique de l'apprentissage
plt.plot(history.history['accuracy'], label='accuracy') plt.plot(history.history['accuracy'], label='accuracy')
plt.plot(history.history['val_accuracy'], label='val_accuracy') plt.plot(history.history['val_accuracy'], label='val_accuracy')
plt.legend() plt.legend()
plt.ylim([min(history.history['val_accuracy']+history.history['accuracy']), 1]) plt.ylim([min(history.history['val_accuracy']+history.history['accuracy']), 1])
plt.show() plt.show()
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
myModel.save('exp904') myModel.save('exp904')
``` ```
%% Cell type:code id: tags: %% Cell type:code id: tags:
``` ```
``` ```
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment