def inference(x,sequence_len,training,full_sequence_len,configure, apply_ratio = False):
"""Infer a logits of the input signal batch.
Args:
x: Tensor of shape [batch_size, max_time,channel], a batch of the input signal with a maximum length `max_time`.
sequence_len: Tensor of shape [batch_size], given the real lenghs of the segments.
training: Placeholder of Boolean, Ture if the inference is during training.
full_sequence_len: Scalar float, the maximum length of the sample in the batch.
configure:Model configuration.
apply_ratio: If apply the ration to the sequence_len or not.
Returns:
logits: Tensor of shape [batch_size, max_time, class_num]
ratio: Scalar float, the scale factor between the output logits and the input maximum length.
"""
cnn_feature = getcnnfeature(x,training = training,cnn_config = configure['cnn']['model'])
feashape = cnn_feature.get_shape().as_list()
ratio = full_sequence_len/feashape[1]
if apply_ratio:
sequence_len = tf.cast(tf.ceil(tf.cast(sequence_len,tf.float32)/ratio),tf.int32)
if configure['rnn']['layer_num'] == 0:
logits = getcnnlogit(cnn_feature)
else:
logits = rnn_layers(cnn_feature,
sequence_len,
training,
layer_num = 3,
hidden_num = 100,
cell="SRU")
#logits = cudnn_rnn(cnn_feature,rnn_layer_num)
return logits,ratio
def inference(x,seq_length,training):
cnn_feature = getcnnfeature(x,training = training)
feashape = cnn_feature.get_shape().as_list()
ratio = FLAGS.segment_len/feashape[1]
# logits = rnn_layers(cnn_feature,seq_length/ratio,training,class_n = 5 )
logits = rnn_layers_one_direction(cnn_feature,seq_length/ratio,training,class_n = len(FLAGS.alphabet)+1)
# logits = getcnnlogit(cnn_feature)
return logits,ratio
def inference(x,seq_length,training):
cnn_feature = getcnnfeature(x,training = training)
feashape = cnn_feature.get_shape().as_list()
ratio = FLAGS.sequence_len/feashape[1]
# logits = rnn_layers(cnn_feature,seq_length/ratio,training,class_n = 4**FLAGS.k_mer+1 )
# logits = rnn_layers_one_direction(cnn_feature,seq_length/ratio,training,class_n = 4**FLAGS.k_mer+1 )
logits = getcnnlogit(cnn_feature)
return logits,ratio
def inference(x,seq_length,training):
cnn_feature = getcnnfeature(x,training = training)
feashape = cnn_feature.get_shape().as_list()
ratio = FLAGS.segment_len/feashape[1]
logits = rnn_layers(cnn_feature, tf.cast(tf.truediv(tf.cast(seq_length, tf.float32),ratio), tf.int32),training,class_n = 5 )
# logits = rnn_layers_one_direction(cnn_feature,seq_length/ratio,training,class_n = 4**FLAGS.k_mer+1 )
# logits = getcnnlogit(cnn_feature)
return logits,ratio
def inference(im):
ab_size = 3851
#bs = 1
#imsize = [32,1024,3]
#im = tf.placeholder(tf.float32,shape=[bs,]+imsize)
#targetIxs = tf.placeholder(tf.int64)
#targetVals = tf.placeholder(tf.int32)
#targetShape = [bs,20]#tf.placeholder(tf.int64)
#gt_label = tf.SparseTensor(targetIxs, targetVals, targetShape)
fea = getcnnfeature(im)
shape = tf.shape(fea)
n = 1 #shape[0]
h = 2 #shape[1]
w = 1024 / 16
#w = shape[2]
c = 512 #shape[3]
fea = tf.transpose(fea, [2, 0, 1, 3])
fea = tf.reshape(fea, [w, n, h * c])
print(w)
feas = [tf.squeeze(t, [0]) for t in tf.split(fea, w)]
print(len(feas))
feass = []
for i in range(len(feas) - 1):
tt = tf.concat([feas[i], feas[i + 1]], axis=1)
feass.append(tt)
W = tf.get_variable("logit_weights",
shape=[h * h * c, ab_size],
initializer=tf.contrib.layers.xavier_initializer())
B = tf.get_variable("logit_bias",
shape=[ab_size],
initializer=tf.contrib.layers.xavier_initializer())
logits = [tf.matmul(t, W) + B for t in feass]
#print len(logits)
logits3d = tf.stack(logits)
print(logits3d.get_shape().as_list())
#logits3d = tf.transpose(logits3d,[1,0,2])
#logits3d = tf.multiply(fea,W) + B
seqLengths = [w - 1] #tf.placeholder(tf.int32)
predictions = tf.to_int32(
tf.nn.ctc_beam_search_decoder(logits3d,
seqLengths,
merge_repeated=False)[0][0])
return predictions.values
def inference(x, seq_len, training):
"""Infer a logits of the input signal batch.
Args:
x: Tensor of shape [batch_size, max_time], a batch of the input signal with a maximum length `max_time`.
seq_len: Scalar float, the maximum length of the sample in the batch.
training: Placeholder of Boolean, Ture if the inference is during training.
Returns:
logits: Tensor of shape [batch_size, max_time, class_num]
ratio: Scalar float, the scale factor between the output logits and the input maximum length.
"""
cnn_feature = getcnnfeature(x, training=training)
feashape = cnn_feature.get_shape().as_list()
ratio = seq_len / feashape[1]
logits = getcnnlogit(cnn_feature)
return logits, ratio
def inference(x,sequence_len,training):
cnn_feature = getcnnfeature(x,training = training)
feashape = cnn_feature.get_shape().as_list()
ratio = sequence_len/feashape[1]
logits = getcnnlogit(cnn_feature)
return logits,ratio
def inference(x, seq_length, training):
cnn_feature = getcnnfeature(x, training=training)
feashape = cnn_feature.get_shape().as_list()
ratio = FLAGS.sequence_len/feashape[1]
logits = rnn_layers(cnn_feature, seq_length, training)
return logits, ratio
for w in open("all_class_random.txt"):
word_dict.append(w.strip().decode('utf-8'))
if __name__ == '__main__':
ab_size = 3817
bs = 1
imsize = [32, 1024, 3]
im = tf.placeholder(tf.float32, shape=[
bs,
] + imsize)
targetIxs = tf.placeholder(tf.int64)
targetVals = tf.placeholder(tf.int32)
targetShape = [bs, 20] #tf.placeholder(tf.int64)
gt_label = tf.SparseTensor(targetIxs, targetVals, targetShape)
fea = getcnnfeature(im)
n, h, w, c = fea.get_shape().as_list()
fea = tf.transpose(fea, [2, 0, 1, 3])
fea = tf.reshape(fea, [w, n, h * c])
feas = [tf.squeeze(t, [0]) for t in tf.split(fea, [
1,
] * w)]
#feass = []
#for i in range(len(feas)-1):
# tt = tf.concat([feas[i],feas[i+1]],axis=1)
# feass.append(tt)
W = tf.get_variable("logits_weights",
shape=[h * c, ab_size],
initializer=tf.contrib.layers.xavier_initializer())
def inference(x, seq_length, training):
cnn_feature = getcnnfeature(x, training=training)
logits = rnn_layers(cnn_feature, seq_length, training)
return logits
