def create_embedding_visual_batch(logdir, batch_size=256):
streams = data_provider.get_streams(1, FLAGS.dataSet,
'clustering', crop_size=FLAGS.default_image_size)
stream_train, stream_train_eval, stream_test = streams
len = 0
for batch in tqdm(copy.copy(stream_train_eval.get_epoch_iterator())):
# get images and labels from batch
x_batch_data, c_batch_data = batch
# change images to [B,S,S,C]
x_batch_data = np.transpose(x_batch_data[:,[2,1,0],:,:],(0,2,3,1))
# Reduce mean
x_batch_data = x_batch_data-image_mean
Label_raw = np.reshape(c_batch_data,[1])
if Label_raw<256:
print(Label_raw)
if len == 0:
images = x_batch_data
labels = Label_raw
else:
images = np.concatenate([images, x_batch_data], axis=0)
labels = np.concatenate([labels, Label_raw], axis=0)
len +=1
if len >= batch_size:
print(labels)
with open(logdir+'metadata.tsv','w') as f:
for i in range(batch_size):
c = labels[i]
f.write('{}\n'.format(c))
return images, labels
import tensorflow as tf
import os
import time
import numpy as np
import keras.backend as K
from tqdm import tqdm
from parameters import *
# A Session object encapsulates the environment in which Operation objects are executed, and Tensor objects are evaluated.
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.compat.v1.Session(config=config)
sess.as_default()
# Creating Streams from the dataset
streams = data_provider.get_streams(BATCH_SIZE, DATASET, crop_size=IMAGE_SIZE)
stream_train, stream_train_eval, stream_test = streams
LEN_TRAIN = stream_train.data_stream.dataset.num_examples
MAX_ITER = int(LEN_TRAIN / BATCH_SIZE)
# check system time
_time = time.strftime('%m-%d-%H-%M', time.localtime(time.time()))
LOGDIR = './tensorboard_log/' + DATASET + '/' + _time + '/'
nn_Ops.create_path(_time)
# tfd = tfp.distributions
# prior = tfd.Independent(tfd.Normal(loc=tf.zeros(EMBEDDING_SIZE), scale=1),reinterpreted_batch_ndims=1)
def samplingGaussian(z_mean, z_log_var):
from datasets import data_provider
from lib import GoogleNet_Model, Loss_ops, nn_Ops, Embedding_Visualization, HDML, evaluation
import copy
from tqdm import tqdm
from tensorflow.contrib import layers
from FLAGS import *
print("applyHDML:{}".format(FLAGS.Apply_HDML))
FLAGS.Apply_HDML = False
if FLAGS.Apply_HDML:
print("HDML is true")
else:
print("HDML is false")
# Create the stream of datas from dataset
streams = data_provider.get_streams(FLAGS.batch_size,
FLAGS.dataSet,
method,
crop_size=FLAGS.default_image_size)
stream_train, stream_train_eval, stream_test = streams
streams2 = data_provider.get_streams(FLAGS.batch_size,
'iconTest',
method,
crop_size=FLAGS.default_image_size)
stream_train2, stream_train_eval2, stream_test2 = streams2
print("print train batch")
for batch in copy.copy(stream_train.get_epoch_iterator()):
x_batch_data, c_batch_data = batch
print(x_batch_data.shape)
print(x_batch_data[0])
print(c_batch_data[0], c_batch_data[-1])