До сих пор я экспериментировал с Tensorflow и Keras. Я взял код из image_ocr.py, который позволял меня тренировать распознавание печатного текста. Я хочу видеть ход обучения по мере его продвижения и успешно визуализировать точность и потери модели обучения. Однако из того, что я слышал, OCR RNN не принимает точность в качестве проверки, а вместо этого использует среднее расстояние редактирования для проверки точности слов. В этом случае я пытался получить переменную с именем mean_ed и mean_norm_ed для визуализации в Tensorboard из класса VizCallback. Я попробовал метод из этой ссылки, но он все еще не работает. Может ли кто-нибудь помочь мне с визуализацией переменных среднего расстояния редактирования? Вот фрагменты кода из моего кода:
class VizCallback(keras.callbacks.Callback):
def __init__(self, run_name, test_func, text_img_gen, num_display_words=6):
self.test_func = test_func
self.output_dir = os.path.join(
OUTPUT_DIR, run_name)
self.text_img_gen = text_img_gen
self.num_display_words = num_display_words
if not os.path.exists(self.output_dir):
os.makedirs(self.output_dir)
def on_train_begin(self, logs={}):
self.med = []
self.nmed = []
def show_edit_distance(self, num, logs={}):
num_left = num
mean_norm_ed = 0.0
mean_ed = 0.0
while num_left > 0:
word_batch = next(self.text_img_gen)[0]
num_proc = min(word_batch['the_input'].shape[0], num_left)
decoded_res = decode_batch(self.test_func, word_batch['the_input'][0:num_proc])
for j in range(num_proc):
edit_dist = editdistance.eval(decoded_res[j], word_batch['source_str'][j])
mean_ed += float(edit_dist)
mean_norm_ed += float(edit_dist) / len(word_batch['source_str'][j])
num_left -= num_proc
mean_norm_ed = mean_norm_ed / num
mean_ed = mean_ed / num
#Create scalar summaries for both mean edit distance and normalized mean edit distance
tf_med_ph = tf.placeholder(tf.float32,shape=None,name='med_summary')
tf_nmed_ph = tf.placeholder(tf.float32,shape=None,name='nmed_summary')
tf_med = tf.summary.scalar('med', tf_med_ph)
tf_nmed = tf.summary.scalar('nmed', tf_nmed_ph)
performance_summaries = tf.summary.merge([tf_med,tf_nmed])
#Create a session for displaying the summary
config = tf.ConfigProto(allow_soft_placement=True)
session = tf.InteractiveSession(config=config)
summ_writer = tf.summary.FileWriter(os.path.join('summaries','first'), session.graph)
# Execute the summaries defined above
summ = session.run(performance_summaries, feed_dict={tf_med_ph:mean_ed, tf_nmed_ph:mean_norm_ed})
# Write the obtained summaries to the file, so it can be displayed in the TensorBoard
summ_writer.add_summary(summ, epoch)
session.close()
print('\nOut of %d samples: Mean edit distance: %.3f Mean normalized edit distance: %0.3f'
% (num, mean_ed, mean_norm_ed))
def on_epoch_end(self, epoch, logs={}):
self.model.save_weights(os.path.join(self.output_dir, 'weights%02d.h5' % (epoch)))
self.show_edit_distance(256)
word_batch = next(self.text_img_gen)[0]
res = decode_batch(self.test_func, word_batch['the_input'][0:self.num_display_words])
if word_batch['the_input'][0].shape[0] < 256:
cols = 2
else:
cols = 1
for i in range(self.num_display_words):
plt.subplot(self.num_display_words // cols, cols, i + 1)
if K.image_data_format() == 'channels_first':
the_input = word_batch['the_input'][i, 0, :, :]
else:
the_input = word_batch['the_input'][i, :, :, 0]
plt.imshow(the_input.T, cmap='Greys_r')
plt.xlabel('Truth = \'%s\'\nDecoded = \'%s\'' % (word_batch['source_str'][i], res[i]))
fig = plt.gcf()
fig.set_size_inches(10, 13)
plt.savefig(os.path.join(self.output_dir, 'e%02d.png' % (epoch)))
plt.close()
def train(run_name, start_epoch, stop_epoch, img_w):
# Input Parameters
img_h = 64
words_per_epoch = 16000
val_split = 0.2
val_words = int(words_per_epoch * (val_split))
# Network parameters
conv_filters = 16
kernel_size = (3, 3)
pool_size = 2
time_dense_size = 32
rnn_size = 512
minibatch_size = 32
if K.image_data_format() == 'channels_first':
input_shape = (1, img_w, img_h)
else:
input_shape = (img_w, img_h, 1)
fdir = os.path.dirname(get_file('wordlists.tgz',
origin='http://test.com/wordlist.tgz', untar=True))
img_gen = TextImageGenerator(monogram_file=os.path.join(fdir, 'wordlist_mono_clean.txt'),
bigram_file=os.path.join(fdir, 'wordlist_bi_clean.txt'),
minibatch_size=minibatch_size,
img_w=img_w,
img_h=img_h,
downsample_factor=(pool_size ** 2),
val_split=words_per_epoch - val_words
)
act = 'relu'
input_data = Input(name='the_input', shape=input_shape, dtype='float32')
inner = Conv2D(conv_filters, kernel_size, padding='same',
activation=act, kernel_initializer='he_normal',
name='conv1')(input_data)
inner = MaxPooling2D(pool_size=(pool_size, pool_size), name='max1')(inner)
inner = Conv2D(conv_filters, kernel_size, padding='same',
activation=act, kernel_initializer='he_normal',
name='conv2')(inner)
inner = MaxPooling2D(pool_size=(pool_size, pool_size), name='max2')(inner)
conv_to_rnn_dims = (img_w // (pool_size ** 2), (img_h // (pool_size ** 2)) * conv_filters)
inner = Reshape(target_shape=conv_to_rnn_dims, name='reshape')(inner)
# cuts down input size going into RNN:
inner = Dense(time_dense_size, activation=act, name='dense1')(inner)
# Two layers of bidirectional GRUs
# GRU seems to work as well, if not better than LSTM:
gru_1 = GRU(rnn_size, return_sequences=True, kernel_initializer='he_normal', name='gru1')(inner)
gru_1b = GRU(rnn_size, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='gru1_b')(inner)
gru1_merged = add([gru_1, gru_1b])
gru_2 = GRU(rnn_size, return_sequences=True, kernel_initializer='he_normal', name='gru2')(gru1_merged)
gru_2b = GRU(rnn_size, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='gru2_b')(gru1_merged)
# transforms RNN output to character activations:
inner = Dense(img_gen.get_output_size(), kernel_initializer='he_normal',
name='dense2')(concatenate([gru_2, gru_2b]))
y_pred = Activation('softmax', name='softmax')(inner)
Model(inputs=input_data, outputs=y_pred).summary()
labels = Input(name='the_labels', shape=[img_gen.absolute_max_string_len], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
# Keras doesn't currently support loss funcs with extra parameters
# so CTC loss is implemented in a lambda layer
loss_out = Lambda(ctc_lambda_func, output_shape=(1,), name='ctc')([y_pred, labels, input_length, label_length])
# clipnorm seems to speeds up convergence
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True, clipnorm=5)
model = Model(inputs=[input_data, labels, input_length, label_length], outputs=loss_out)
#Make tensorboard instance
init_op = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init_op)
tbname="tensorboard-of-{}".format(int(time.time()))
tensorboard = keras.callbacks.TensorBoard(
log_dir="logs/{}".format(tbname),
histogram_freq=0,
write_images=True)
# the loss calc occurs elsewhere, so use a dummy lambda func for the loss
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd,
metrics=['accuracy'])
if start_epoch > 0:
weight_file = os.path.join(OUTPUT_DIR, os.path.join(run_name, 'weights%02d.h5' % (start_epoch - 1)))
model.load_weights(weight_file)
# captures output of softmax so we can decode the output during visualization
test_func = K.function([input_data], [y_pred])
viz_cb = VizCallback(run_name, test_func, img_gen.next_val())
model.fit_generator(generator=img_gen.next_train(),
steps_per_epoch=(words_per_epoch - val_words) // minibatch_size,
epochs=stop_epoch,
validation_data=img_gen.next_val(),
validation_steps=val_words // minibatch_size,
callbacks=[tensorboard,viz_cb, img_gen],
initial_epoch=start_epoch)
Любая помощь будет очень признательна. Благодарю вас!
P.S. Я использую Tensorflow 1.9.0 и Python 3.6.8.
ОБНОВЛЕНИЕ теперь это просто вопрос передачи переменной performance_summaries из класса VizCallbak в метрики в функции обучения. Любая помощь здесь?
