Make examples agnostic to image_dim_ordering
This commit is contained in:
parent
f05cd95fad
commit
cc92025fdc
@ -43,7 +43,7 @@ Y_test = np_utils.to_categorical(y_test, nb_classes)
|
||||
model = Sequential()
|
||||
|
||||
model.add(Convolution2D(32, 3, 3, border_mode='same',
|
||||
input_shape=(img_channels, img_rows, img_cols)))
|
||||
input_shape=X_train.shape[1:]))
|
||||
model.add(Activation('relu'))
|
||||
model.add(Convolution2D(32, 3, 3))
|
||||
model.add(Activation('relu'))
|
||||
|
@ -61,6 +61,7 @@ OUTPUT_DIR = "image_ocr"
|
||||
|
||||
np.random.seed(55)
|
||||
|
||||
|
||||
# this creates larger "blotches" of noise which look
|
||||
# more realistic than just adding gaussian noise
|
||||
# assumes greyscale with pixels ranging from 0 to 1
|
||||
@ -73,6 +74,7 @@ def speckle(img):
|
||||
img_speck[img_speck <= 0] = 0
|
||||
return img_speck
|
||||
|
||||
|
||||
# paints the string in a random location the bounding box
|
||||
# also uses a random font, a slight random rotation,
|
||||
# and a random amount of speckle noise
|
||||
@ -114,6 +116,7 @@ def paint_text(text, w, h):
|
||||
|
||||
return a
|
||||
|
||||
|
||||
def shuffle_mats_or_lists(matrix_list, stop_ind=None):
|
||||
ret = []
|
||||
assert all([len(i) == len(matrix_list[0]) for i in matrix_list])
|
||||
@ -131,9 +134,11 @@ def shuffle_mats_or_lists(matrix_list, stop_ind=None):
|
||||
elif isinstance(mat, list):
|
||||
ret.append([mat[i] for i in a])
|
||||
else:
|
||||
raise TypeError('shuffle_mats_or_lists only supports numpy.array and list objects')
|
||||
raise TypeError('shuffle_mats_or_lists only supports '
|
||||
'numpy.array and list objects')
|
||||
return ret
|
||||
|
||||
|
||||
def text_to_labels(text, num_classes):
|
||||
ret = []
|
||||
for char in text:
|
||||
@ -143,6 +148,7 @@ def text_to_labels(text, num_classes):
|
||||
ret.append(26)
|
||||
return ret
|
||||
|
||||
|
||||
# only a-z and space..probably not to difficult
|
||||
# to expand to uppercase and symbols
|
||||
|
||||
@ -150,14 +156,15 @@ def is_valid_str(in_str):
|
||||
search = re.compile(r'[^a-z\ ]').search
|
||||
return not bool(search(in_str))
|
||||
|
||||
|
||||
# Uses generator functions to supply train/test with
|
||||
# data. Image renderings are text are created on the fly
|
||||
# each time with random perturbations
|
||||
|
||||
class TextImageGenerator(keras.callbacks.Callback):
|
||||
|
||||
def __init__(self, monogram_file, bigram_file, minibatch_size, img_w,
|
||||
img_h, downsample_width, val_split,
|
||||
def __init__(self, monogram_file, bigram_file, minibatch_size,
|
||||
img_w, img_h, downsample_width, val_split,
|
||||
absolute_max_string_len=16):
|
||||
|
||||
self.minibatch_size = minibatch_size
|
||||
@ -221,7 +228,10 @@ class TextImageGenerator(keras.callbacks.Callback):
|
||||
# each time an image is requested from train/val/test, a new random
|
||||
# painting of the text is performed
|
||||
def get_batch(self, index, size, train):
|
||||
X_data = np.ones([size, 1, self.img_h, self.img_w])
|
||||
if K.image_dim_ordering() == 'th':
|
||||
X_data = np.ones([size, 1, self.img_h, self.img_w])
|
||||
else:
|
||||
X_data = np.ones([size, self.img_h, self.img_w, 1])
|
||||
labels = np.ones([size, self.absolute_max_string_len])
|
||||
input_length = np.zeros([size, 1])
|
||||
label_length = np.zeros([size, 1])
|
||||
@ -231,13 +241,19 @@ class TextImageGenerator(keras.callbacks.Callback):
|
||||
# Mix in some blank inputs. This seems to be important for
|
||||
# achieving translational invariance
|
||||
if train and i > size - 4:
|
||||
X_data[i, 0, :, :] = paint_text('', self.img_w, self.img_h)
|
||||
if K.image_dim_ordering() == 'th':
|
||||
X_data[i, 0, :, :] = paint_text('', self.img_w, self.img_h)
|
||||
else:
|
||||
X_data[i, :, :, 0] = paint_text('', self.img_w, self.img_h)
|
||||
labels[i, 0] = self.blank_label
|
||||
input_length[i] = self.downsample_width
|
||||
label_length[i] = 1
|
||||
source_str.append('')
|
||||
else:
|
||||
X_data[i, 0, :, :] = paint_text(self.X_text[index + i], self.img_w, self.img_h)
|
||||
if K.image_dim_ordering() == 'th':
|
||||
X_data[i, 0, :, :] = paint_text(self.X_text[index + i], self.img_w, self.img_h)
|
||||
else:
|
||||
X_data[i, :, :, 0] = paint_text(self.X_text[index + i], self.img_w, self.img_h)
|
||||
labels[i, :] = self.Y_data[index + i]
|
||||
input_length[i] = self.downsample_width
|
||||
label_length[i] = self.Y_len[index + i]
|
||||
@ -285,6 +301,7 @@ class TextImageGenerator(keras.callbacks.Callback):
|
||||
if epoch == 30:
|
||||
self.build_word_list(64000, 12, 0.5)
|
||||
|
||||
|
||||
# the actual loss calc occurs here despite it not being
|
||||
# an internal Keras loss function
|
||||
|
||||
@ -295,6 +312,7 @@ def ctc_lambda_func(args):
|
||||
y_pred = y_pred[:, 2:, :]
|
||||
return K.ctc_batch_cost(labels, y_pred, input_length, label_length)
|
||||
|
||||
|
||||
# For a real OCR application, this should be beam search with a dictionary
|
||||
# and language model. For this example, best path is sufficient.
|
||||
|
||||
@ -314,9 +332,10 @@ def decode_batch(test_func, word_batch):
|
||||
ret.append(outstr)
|
||||
return ret
|
||||
|
||||
|
||||
class VizCallback(keras.callbacks.Callback):
|
||||
|
||||
def __init__(self, test_func, text_img_gen, num_display_words = 6):
|
||||
def __init__(self, test_func, text_img_gen, num_display_words=6):
|
||||
self.test_func = test_func
|
||||
self.output_dir = os.path.join(
|
||||
OUTPUT_DIR, datetime.datetime.now().strftime('%A, %d. %B %Y %I.%M%p'))
|
||||
@ -350,7 +369,11 @@ class VizCallback(keras.callbacks.Callback):
|
||||
|
||||
for i in range(self.num_display_words):
|
||||
pylab.subplot(self.num_display_words, 1, i + 1)
|
||||
pylab.imshow(word_batch['the_input'][i, 0, :, :], cmap='Greys_r')
|
||||
if K.image_dim_ordering() == 'th':
|
||||
the_input = word_batch['the_input'][i, 0, :, :]
|
||||
else:
|
||||
the_input = word_batch['the_input'][i, :, :, 0]
|
||||
pylab.imshow(the_input, cmap='Greys_r')
|
||||
pylab.xlabel('Truth = \'%s\' Decoded = \'%s\'' % (word_batch['source_str'][i], res[i]))
|
||||
fig = pylab.gcf()
|
||||
fig.set_size_inches(10, 12)
|
||||
@ -375,6 +398,11 @@ time_dense_size = 32
|
||||
rnn_size = 512
|
||||
time_steps = img_w / (pool_size_1 * pool_size_2)
|
||||
|
||||
if K.image_dim_ordering() == 'th':
|
||||
input_shape = (1, img_h, img_w)
|
||||
else:
|
||||
input_shape = (img_h, img_w, 1)
|
||||
|
||||
fdir = os.path.dirname(get_file('wordlists.tgz',
|
||||
origin='http://www.isosemi.com/datasets/wordlists.tgz', untar=True))
|
||||
|
||||
@ -387,7 +415,7 @@ img_gen = TextImageGenerator(monogram_file=os.path.join(fdir, 'wordlist_mono_cle
|
||||
val_split=words_per_epoch - val_words)
|
||||
|
||||
act = 'relu'
|
||||
input_data = Input(name='the_input', shape=(1, img_h, img_w), dtype='float32')
|
||||
input_data = Input(name='the_input', shape=input_shape, dtype='float32')
|
||||
inner = Convolution2D(conv_num_filters, filter_size, filter_size, border_mode='same',
|
||||
activation=act, name='conv1')(input_data)
|
||||
inner = MaxPooling2D(pool_size=(pool_size_1, pool_size_1), name='max1')(inner)
|
||||
|
@ -1,290 +0,0 @@
|
||||
'''This script demonstrates how to build the Inception v3 architecture
|
||||
using the Keras functional API.
|
||||
We are not actually training it here, for lack of appropriate data.
|
||||
|
||||
For more information about this architecture, see:
|
||||
|
||||
"Rethinking the Inception Architecture for Computer Vision"
|
||||
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna
|
||||
http://arxiv.org/abs/1512.00567
|
||||
'''
|
||||
from keras.layers import Convolution2D, MaxPooling2D, AveragePooling2D
|
||||
from keras.layers import BatchNormalization, Flatten, Dense, Dropout
|
||||
from keras.layers import Input, merge
|
||||
from keras.models import Model
|
||||
from keras import regularizers
|
||||
|
||||
|
||||
# global constants
|
||||
NB_CLASS = 1000 # number of classes
|
||||
DIM_ORDERING = 'th' # 'th' (channels, width, height) or 'tf' (width, height, channels)
|
||||
WEIGHT_DECAY = 0. # L2 regularization factor
|
||||
USE_BN = False # whether to use batch normalization
|
||||
|
||||
|
||||
def conv2D_bn(x, nb_filter, nb_row, nb_col,
|
||||
border_mode='same', subsample=(1, 1),
|
||||
activation='relu', batch_norm=USE_BN,
|
||||
weight_decay=WEIGHT_DECAY, dim_ordering=DIM_ORDERING):
|
||||
'''Utility function to apply to a tensor a module conv + BN
|
||||
with optional weight decay (L2 weight regularization).
|
||||
'''
|
||||
if weight_decay:
|
||||
W_regularizer = regularizers.l2(weight_decay)
|
||||
b_regularizer = regularizers.l2(weight_decay)
|
||||
else:
|
||||
W_regularizer = None
|
||||
b_regularizer = None
|
||||
x = Convolution2D(nb_filter, nb_row, nb_col,
|
||||
subsample=subsample,
|
||||
activation=activation,
|
||||
border_mode=border_mode,
|
||||
W_regularizer=W_regularizer,
|
||||
b_regularizer=b_regularizer,
|
||||
dim_ordering=dim_ordering)(x)
|
||||
if batch_norm:
|
||||
x = BatchNormalization()(x)
|
||||
return x
|
||||
|
||||
# Define image input layer
|
||||
|
||||
if DIM_ORDERING == 'th':
|
||||
img_input = Input(shape=(3, 299, 299))
|
||||
CONCAT_AXIS = 1
|
||||
elif DIM_ORDERING == 'tf':
|
||||
img_input = Input(shape=(299, 299, 3))
|
||||
CONCAT_AXIS = 3
|
||||
else:
|
||||
raise Exception('Invalid dim ordering: ' + str(DIM_ORDERING))
|
||||
|
||||
# Entry module
|
||||
|
||||
x = conv2D_bn(img_input, 32, 3, 3, subsample=(2, 2), border_mode='valid')
|
||||
x = conv2D_bn(x, 32, 3, 3, border_mode='valid')
|
||||
x = conv2D_bn(x, 64, 3, 3)
|
||||
x = MaxPooling2D((3, 3), strides=(2, 2), dim_ordering=DIM_ORDERING)(x)
|
||||
|
||||
x = conv2D_bn(x, 80, 1, 1, border_mode='valid')
|
||||
x = conv2D_bn(x, 192, 3, 3, border_mode='valid')
|
||||
x = MaxPooling2D((3, 3), strides=(2, 2), dim_ordering=DIM_ORDERING)(x)
|
||||
|
||||
# mixed: 35 x 35 x 256
|
||||
|
||||
branch1x1 = conv2D_bn(x, 64, 1, 1)
|
||||
|
||||
branch5x5 = conv2D_bn(x, 48, 1, 1)
|
||||
branch5x5 = conv2D_bn(branch5x5, 64, 5, 5)
|
||||
|
||||
branch3x3dbl = conv2D_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 32, 1, 1)
|
||||
x = merge([branch1x1, branch5x5, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed_1: 35 x 35 x 288
|
||||
|
||||
branch1x1 = conv2D_bn(x, 64, 1, 1)
|
||||
|
||||
branch5x5 = conv2D_bn(x, 48, 1, 1)
|
||||
branch5x5 = conv2D_bn(branch5x5, 64, 5, 5)
|
||||
|
||||
branch3x3dbl = conv2D_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 64, 1, 1)
|
||||
x = merge([branch1x1, branch5x5, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed2: 35 x 35 x 288
|
||||
|
||||
branch1x1 = conv2D_bn(x, 64, 1, 1)
|
||||
|
||||
branch5x5 = conv2D_bn(x, 48, 1, 1)
|
||||
branch5x5 = conv2D_bn(branch5x5, 64, 5, 5)
|
||||
|
||||
branch3x3dbl = conv2D_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 64, 1, 1)
|
||||
x = merge([branch1x1, branch5x5, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed3: 17 x 17 x 768
|
||||
|
||||
branch3x3 = conv2D_bn(x, 384, 3, 3, subsample=(2, 2), border_mode='valid')
|
||||
|
||||
branch3x3dbl = conv2D_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 96, 3, 3, subsample=(2, 2), border_mode='valid')
|
||||
|
||||
branch_pool = MaxPooling2D((3, 3), strides=(2, 2), dim_ordering=DIM_ORDERING)(x)
|
||||
x = merge([branch3x3, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed4: 17 x 17 x 768
|
||||
|
||||
branch1x1 = conv2D_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2D_bn(x, 128, 1, 1)
|
||||
branch7x7 = conv2D_bn(branch7x7, 128, 1, 7)
|
||||
branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2D_bn(x, 128, 1, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 128, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 128, 1, 7)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 128, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed5: 17 x 17 x 768
|
||||
|
||||
branch1x1 = conv2D_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2D_bn(x, 160, 1, 1)
|
||||
branch7x7 = conv2D_bn(branch7x7, 160, 1, 7)
|
||||
branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2D_bn(x, 160, 1, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 1, 7)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed5: 17 x 17 x 768
|
||||
|
||||
branch1x1 = conv2D_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2D_bn(x, 160, 1, 1)
|
||||
branch7x7 = conv2D_bn(branch7x7, 160, 1, 7)
|
||||
branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2D_bn(x, 160, 1, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 1, 7)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed6: 17 x 17 x 768
|
||||
|
||||
branch1x1 = conv2D_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2D_bn(x, 160, 1, 1)
|
||||
branch7x7 = conv2D_bn(branch7x7, 160, 1, 7)
|
||||
branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2D_bn(x, 160, 1, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed7: 17 x 17 x 768
|
||||
|
||||
branch1x1 = conv2D_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2D_bn(x, 192, 1, 1)
|
||||
branch7x7 = conv2D_bn(branch7x7, 192, 1, 7)
|
||||
branch7x7 = conv2D_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2D_bn(x, 160, 1, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 7, 1)
|
||||
branch7x7dbl = conv2D_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# Auxiliary head
|
||||
|
||||
aux_logits = AveragePooling2D((5, 5), strides=(3, 3), dim_ordering=DIM_ORDERING)(x)
|
||||
aux_logits = conv2D_bn(aux_logits, 128, 1, 1)
|
||||
aux_logits = conv2D_bn(aux_logits, 728, 5, 5, border_mode='valid')
|
||||
aux_logits = Flatten()(aux_logits)
|
||||
aux_preds = Dense(NB_CLASS, activation='softmax')(aux_logits)
|
||||
|
||||
# mixed8: 8 x 8 x 1280
|
||||
|
||||
branch3x3 = conv2D_bn(x, 192, 1, 1)
|
||||
branch3x3 = conv2D_bn(branch3x3, 320, 3, 3, subsample=(2, 2), border_mode='valid')
|
||||
|
||||
branch7x7x3 = conv2D_bn(x, 192, 1, 1)
|
||||
branch7x7x3 = conv2D_bn(branch7x7x3, 192, 1, 7)
|
||||
branch7x7x3 = conv2D_bn(branch7x7x3, 192, 7, 1)
|
||||
branch7x7x3 = conv2D_bn(branch7x7x3, 192, 3, 3, subsample=(2, 2), border_mode='valid')
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(2, 2), dim_ordering=DIM_ORDERING)(x)
|
||||
x = merge([branch3x3, branch7x7x3, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed9: 8 x 8 x 2048
|
||||
|
||||
branch1x1 = conv2D_bn(x, 320, 1, 1)
|
||||
|
||||
branch3x3 = conv2D_bn(x, 384, 1, 1)
|
||||
branch3x3_1 = conv2D_bn(branch3x3, 384, 1, 3)
|
||||
branch3x3_2 = conv2D_bn(branch3x3, 384, 3, 1)
|
||||
branch3x3 = merge([branch3x3_1, branch3x3_2], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
branch3x3dbl = conv2D_bn(x, 448, 1, 1)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 384, 3, 3)
|
||||
branch3x3dbl_1 = conv2D_bn(branch3x3dbl, 384, 1, 3)
|
||||
branch3x3dbl_2 = conv2D_bn(branch3x3dbl, 384, 3, 1)
|
||||
branch3x3dbl = merge([branch3x3dbl_1, branch3x3dbl_2], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch3x3, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# mixed10: 8 x 8 x 2048
|
||||
|
||||
branch1x1 = conv2D_bn(x, 320, 1, 1)
|
||||
|
||||
branch3x3 = conv2D_bn(x, 384, 1, 1)
|
||||
branch3x3_1 = conv2D_bn(branch3x3, 384, 1, 3)
|
||||
branch3x3_2 = conv2D_bn(branch3x3, 384, 3, 1)
|
||||
branch3x3 = merge([branch3x3_1, branch3x3_2], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
branch3x3dbl = conv2D_bn(x, 448, 1, 1)
|
||||
branch3x3dbl = conv2D_bn(branch3x3dbl, 384, 3, 3)
|
||||
branch3x3dbl_1 = conv2D_bn(branch3x3dbl, 384, 1, 3)
|
||||
branch3x3dbl_2 = conv2D_bn(branch3x3dbl, 384, 3, 1)
|
||||
branch3x3dbl = merge([branch3x3dbl_1, branch3x3dbl_2], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same', dim_ordering=DIM_ORDERING)(x)
|
||||
branch_pool = conv2D_bn(branch_pool, 192, 1, 1)
|
||||
x = merge([branch1x1, branch3x3, branch3x3dbl, branch_pool], mode='concat', concat_axis=CONCAT_AXIS)
|
||||
|
||||
# Final pooling and prediction
|
||||
|
||||
x = AveragePooling2D((8, 8), strides=(1, 1), dim_ordering=DIM_ORDERING)(x)
|
||||
x = Dropout(0.5)(x)
|
||||
x = Flatten()(x)
|
||||
preds = Dense(NB_CLASS, activation='softmax')(x)
|
||||
|
||||
# Define model
|
||||
|
||||
model = Model(input=img_input, output=[preds, aux_preds])
|
||||
model.compile('rmsprop', 'categorical_crossentropy')
|
||||
|
||||
# train via e.g. `model.fit(x_train, [y_train] * 2, batch_size=32, nb_epoch=100)`
|
||||
# Note that for a large dataset it would be preferable
|
||||
# to train using `fit_generator` (see Keras docs).
|
@ -14,6 +14,7 @@ from keras.models import Sequential
|
||||
from keras.layers import Dense, Dropout, Activation, Flatten
|
||||
from keras.layers import Convolution2D, MaxPooling2D
|
||||
from keras.utils import np_utils
|
||||
from keras import backend as K
|
||||
|
||||
batch_size = 128
|
||||
nb_classes = 10
|
||||
@ -24,15 +25,22 @@ img_rows, img_cols = 28, 28
|
||||
# number of convolutional filters to use
|
||||
nb_filters = 32
|
||||
# size of pooling area for max pooling
|
||||
nb_pool = 2
|
||||
pool_size = (2, 2)
|
||||
# convolution kernel size
|
||||
kernel_size = (3, 3)
|
||||
|
||||
# the data, shuffled and split between train and test sets
|
||||
(X_train, y_train), (X_test, y_test) = mnist.load_data()
|
||||
|
||||
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
|
||||
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
|
||||
if K.image_dim_ordering() == 'th':
|
||||
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
|
||||
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
|
||||
input_shape = (1, img_rows, img_cols)
|
||||
else:
|
||||
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
|
||||
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
|
||||
input_shape = (img_rows, img_cols, 1)
|
||||
|
||||
X_train = X_train.astype('float32')
|
||||
X_test = X_test.astype('float32')
|
||||
X_train /= 255
|
||||
@ -49,11 +57,11 @@ model = Sequential()
|
||||
|
||||
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
|
||||
border_mode='valid',
|
||||
input_shape=(1, img_rows, img_cols)))
|
||||
input_shape=input_shape))
|
||||
model.add(Activation('relu'))
|
||||
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
|
||||
model.add(Activation('relu'))
|
||||
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
|
||||
model.add(MaxPooling2D(pool_size=pool_size))
|
||||
model.add(Dropout(0.25))
|
||||
|
||||
model.add(Flatten())
|
||||
|
@ -22,7 +22,7 @@ from keras.models import Sequential
|
||||
from keras.layers import Dense, Dropout, Activation, Flatten
|
||||
from keras.layers import Convolution2D, MaxPooling2D
|
||||
from keras.utils import np_utils
|
||||
|
||||
from keras import backend as K
|
||||
|
||||
now = datetime.datetime.now
|
||||
|
||||
@ -35,14 +35,19 @@ img_rows, img_cols = 28, 28
|
||||
# number of convolutional filters to use
|
||||
nb_filters = 32
|
||||
# size of pooling area for max pooling
|
||||
nb_pool = 2
|
||||
pool_size = 2
|
||||
# convolution kernel size
|
||||
nb_conv = 3
|
||||
kernel_size = 3
|
||||
|
||||
if K.image_dim_ordering() == 'th':
|
||||
input_shape = (1, img_rows, img_cols)
|
||||
else:
|
||||
input_shape = (img_rows, img_cols, 1)
|
||||
|
||||
|
||||
def train_model(model, train, test, nb_classes):
|
||||
X_train = train[0].reshape(train[0].shape[0], 1, img_rows, img_cols)
|
||||
X_test = test[0].reshape(test[0].shape[0], 1, img_rows, img_cols)
|
||||
X_train = train[0].reshape((train[0].shape[0],) + input_shape)
|
||||
X_test = test[0].reshape((test[0].shape[0],) + input_shape)
|
||||
X_train = X_train.astype('float32')
|
||||
X_test = X_test.astype('float32')
|
||||
X_train /= 255
|
||||
@ -86,13 +91,13 @@ y_test_gte5 = y_test[y_test >= 5] - 5
|
||||
|
||||
# define two groups of layers: feature (convolutions) and classification (dense)
|
||||
feature_layers = [
|
||||
Convolution2D(nb_filters, nb_conv, nb_conv,
|
||||
Convolution2D(nb_filters, kernel_size, kernel_size,
|
||||
border_mode='valid',
|
||||
input_shape=(1, img_rows, img_cols)),
|
||||
input_shape=input_shape),
|
||||
Activation('relu'),
|
||||
Convolution2D(nb_filters, nb_conv, nb_conv),
|
||||
Convolution2D(nb_filters, kernel_size, kernel_size),
|
||||
Activation('relu'),
|
||||
MaxPooling2D(pool_size=(nb_pool, nb_pool)),
|
||||
MaxPooling2D(pool_size=(pool_size, pool_size)),
|
||||
Dropout(0.25),
|
||||
Flatten(),
|
||||
]
|
||||
@ -105,9 +110,7 @@ classification_layers = [
|
||||
]
|
||||
|
||||
# create complete model
|
||||
model = Sequential()
|
||||
for l in feature_layers + classification_layers:
|
||||
model.add(l)
|
||||
model = Sequential(feature_layers + classification_layers)
|
||||
|
||||
# train model for 5-digit classification [0..4]
|
||||
train_model(model,
|
||||
|
@ -1,6 +1,7 @@
|
||||
from __future__ import absolute_import
|
||||
from .cifar import load_batch
|
||||
from ..utils.data_utils import get_file
|
||||
from .. import backend as K
|
||||
import numpy as np
|
||||
import os
|
||||
|
||||
@ -18,8 +19,8 @@ def load_data():
|
||||
for i in range(1, 6):
|
||||
fpath = os.path.join(path, 'data_batch_' + str(i))
|
||||
data, labels = load_batch(fpath)
|
||||
X_train[(i-1)*10000:i*10000, :, :, :] = data
|
||||
y_train[(i-1)*10000:i*10000] = labels
|
||||
X_train[(i - 1) * 10000: i * 10000, :, :, :] = data
|
||||
y_train[(i - 1) * 10000: i * 10000] = labels
|
||||
|
||||
fpath = os.path.join(path, 'test_batch')
|
||||
X_test, y_test = load_batch(fpath)
|
||||
@ -27,4 +28,8 @@ def load_data():
|
||||
y_train = np.reshape(y_train, (len(y_train), 1))
|
||||
y_test = np.reshape(y_test, (len(y_test), 1))
|
||||
|
||||
if K.image_dim_ordering() == 'tf':
|
||||
X_train = X_train.transpose(0, 2, 3, 1)
|
||||
X_test = X_test.transpose(0, 2, 3, 1)
|
||||
|
||||
return (X_train, y_train), (X_test, y_test)
|
||||
|
@ -1,6 +1,7 @@
|
||||
from __future__ import absolute_import
|
||||
from .cifar import load_batch
|
||||
from ..utils.data_utils import get_file
|
||||
from .. import backend as K
|
||||
import numpy as np
|
||||
import os
|
||||
|
||||
@ -13,9 +14,6 @@ def load_data(label_mode='fine'):
|
||||
origin = "http://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz"
|
||||
path = get_file(dirname, origin=origin, untar=True)
|
||||
|
||||
nb_test_samples = 10000
|
||||
nb_train_samples = 50000
|
||||
|
||||
fpath = os.path.join(path, 'train')
|
||||
X_train, y_train = load_batch(fpath, label_key=label_mode+'_labels')
|
||||
|
||||
@ -25,4 +23,8 @@ def load_data(label_mode='fine'):
|
||||
y_train = np.reshape(y_train, (len(y_train), 1))
|
||||
y_test = np.reshape(y_test, (len(y_test), 1))
|
||||
|
||||
if K.image_dim_ordering() == 'tf':
|
||||
X_train = X_train.transpose(0, 2, 3, 1)
|
||||
X_test = X_test.transpose(0, 2, 3, 1)
|
||||
|
||||
return (X_train, y_train), (X_test, y_test)
|
||||
|
@ -162,7 +162,7 @@ def img_to_array(img, dim_ordering='default'):
|
||||
|
||||
def load_img(path, grayscale=False, target_size=None):
|
||||
'''Load an image into PIL format.
|
||||
|
||||
|
||||
# Arguments
|
||||
path: path to image file
|
||||
grayscale: boolean
|
||||
|
Loading…
Reference in New Issue
Block a user