Per qualche motivo quando utilizzo un ImageDataGenerator con keras si blocca quando avvio il fit. Ottengo il seguente risultato. Si blocca proprio sulla linea Epoch 1/5
Le telecamere si bloccano durante l'uso di ImageDataGenerator
Using Theano backend.
Using gpu device 0: GeForce GTX TITAN (CNMeM is disabled, cuDNN not available)
Loading Data
Compiling Model
Fitting Data
Epoch 1/5
Essa mostra che uno dei miei core CPU è in esecuzione al 100% quindi qualcosa sta accadendo sulla CPU pari anche se va usando il mio GPU per adattarsi ai dati. Il codice qui sotto funziona se commento il fit_generator e utilizzo la funzione di adattamento.
import os
os.environ["THEANO_FLAGS"] = "mode=FAST_RUN,device=gpu,floatX=float32"
import minst_loader
import matplotlib.pyplot as plt
import numpy as np
from scipy.misc import imrotate
import random
from keras.datasets import cifar10
np.set_printoptions(suppress = True)
print('Loading Data')
x_train, y_train = (minst_loader.load_images('/home/chase/Desktop/MINST/train-images.idx3-ubyte'), \
minst_loader.load_labels('/home/chase/Desktop/MINST/train-labels.idx1-ubyte'))
x_test, y_test = (minst_loader.load_images('/home/chase/Desktop/MINST/t10k-images.idx3-ubyte'), \
minst_loader.load_labels('/home/chase/Desktop/MINST/t10k-labels.idx1-ubyte'))
for i in range(len(y_train)):
v = np.zeros(10)
v[y_train[i]] = 1
y_train[i] = v
# for j in range(8):
# x = imrotate(x_train[i], random.random() * 20)
# x_train.append(x)
# y_train.append(y_train[i])
for i in range(len(y_test)):
v = np.zeros(10)
v[y_test[i]] = 1
y_test[i] = v
x_train = np.array(x_train)
y_train = np.array(y_train)
x_test = np.array(x_test)
y_test = np.array(y_test)
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Flatten
from keras.layers.noise import GaussianNoise
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import SGD
from keras.callbacks import ProgbarLogger, Callback
datagen = ImageDataGenerator(rotation_range = 20, dim_ordering = 'tf')
model = Sequential()
model.add(Flatten(input_shape = (28, 28)))
model.add(Dense(200, activation = 'tanh'))
model.add(Dropout(0.5))
model.add(Dense(20, activation = 'tanh'))
model.add(Dense(10, activation = 'softmax'))
print('Compiling Model')
sgd = SGD(lr = 0.01, decay = 0.1, momentum = 0.9, nesterov = True)
model.compile(loss = 'categorical_crossentropy', optimizer = sgd)
print('Fitting Data')
#model.fit(x_train, y_train, batch_size = 128, nb_epoch = 400, validation_data = (x_test, y_test))
model.fit_generator(datagen.flow(x_train, y_train), samples_per_epoch = len(x_train), nb_epoch = 5)
def max_index(lst):
mi = 0
for i in range(1, len(lst)):
mi = i if lst[i] > lst[mi] else mi
return mi
result = model.predict(x_test)
correct = 0
for y, yt in zip(result, y_test):
correct += max_index(y) == max_index(yt)
print(correct/len(y_test))
qui è anche il mio MInst caricatore se qualcuno vuole provare a farlo funzionare ...
import struct
import numpy as np
import matplotlib.pyplot as plt
def load_images(images_file):
data = None
with open(images_file, 'rb') as f:
data = f.read()
mn, n, h, w = struct.unpack('>4I', data[0:16])
assert(mn == 2051)
data = data[16:]
images = []
for i in range(n):
img = np.array([float(b) for b in data[w * h * i:w * h * (i + 1)]])
img /= 255.0
img = np.reshape(img, (w, h))
images.append(img)
return images
def load_labels(labels_file):
data = None
with open(labels_file, 'rb') as f:
data = f.read()
mn, n = struct.unpack('>2I', data[0:8])
assert(mn == 2049)
return [int(b) for b in data[8:]]
Sei sicuro la vostra configurazione è impostato per utilizzare la GPU? Cosa ottieni se provi a utilizzare lo script "Test di Theano con GPU" in http://deeplearning.net/software/theano/tutorial/using_gpu.html? – ginge