When runing the following code I get this error "InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[1,65536] labels_size=[65536,1]" in cross_entropy_with_logits.
I can work around this by doing
And then when training the loss only increases continuously. I have changed the learning rate couple of times to no avail. I'm using images with 2 classes (Background and Ground Truth)
import numpy as np
import tensorflow as tf
import skimage.io as io
#import tensorflow.contrib.slim.nets
from matplotlib import pyplot as plt
from nets import vgg
from preprocessing import vgg_preprocessing
# Load the mean pixel values and the function
# that performs the subtraction from each pixel
from preprocessing.vgg_preprocessing import (_mean_image_subtraction,
_R_MEAN, _G_MEAN, _B_MEAN)
from tf_image_segmentation.utils.tf_records import read_tfrecord_and_decode_into_image_annotation_pair_tensors
from tf_image_segmentation.models.fcn_32s import FCN_32s, extract_vgg_16_mapping_without_fc8
from tf_image_segmentation.utils.pascal_voc import pascal_segmentation_lut
from tf_image_segmentation.utils.training import get_valid_logits_and_labels
from tf_image_segmentation.utils.augmentation import (distort_randomly_image_color,
flip_randomly_left_right_image_with_annotation,
scale_randomly_image_with_annotation_with_fixed_size_output)
#os.environ["CUDA_VISIBLE_DEVICES"] = '0'
def my_detection_lut():
"""Return look-up table with number and correspondng class names
for PASCAL VOC segmentation dataset. Two special classes are: 0 -
background and 255 - ambigious region. All others are numerated from
1 to 20.
Returns
-------
classes_lut : dict
look-up table with number and correspondng class names
"""
class_names = ['background', 'GT', 'ambigious']
enumerated_array = enumerate(class_names[:-1])
classes_lut = list(enumerated_array)
# Add a special class representing ambigious regions
# which has index 255.
classes_lut.append((255, class_names[-1]))
classes_lut = dict(classes_lut)
return classes_lut
root_folder = os.getcwd()
img_folder = os.path.join(root_folder, 'data\\images')
checkpoints_dir = os.path.join(root_folder, 'data')
vgg_checkpoint_path = os.path.join(checkpoints_dir, 'vgg_16.ckpt')
log_folder = os.path.join(root_folder, 'logs')
model_ckpt_path = os.path.join(root_folder, 'model_fcn32.ckpt')
slim = tf.contrib.slim
dataset_len = len([name for name in os.listdir(os.path.join(img_folder,'processed\\frames'))])
print(dataset_len)
trainset_len = int(dataset_len * 0.25)
testset_len = dataset_len - trainset_len
image_train_size = [256,256]
number_of_classes = 2
tfrecord_filename = 'polyp_test_pairs.tfrecords'
tfrecord_filename = os.path.join(img_folder, 'polyp_test_pairs.tfrecords')
print(tfrecord_filename)
my_detection = my_detection_lut()
class_labels = list(my_detection.keys())
tf.reset_default_graph()
filename_queue = tf.train.string_input_producer([tfrecord_filename], num_epochs=10)
image, annotation = read_tfrecord_and_decode_into_image_annotation_pair_tensors(filename_queue)
resized_image = tf.image.resize_images(images=image,
size=image_train_size)
resized_annotation = tf.image.resize_images(images=annotation,
size=image_train_size)
image_batch, annotation_batch = tf.train.shuffle_batch([resized_image, resized_annotation],
batch_size=1, capacity=20, num_threads=1,
min_after_dequeue=10)
upsampled_logits_batch, vgg_16_variables_mapping = FCN_32s(image_batch_tensor=image_batch,
number_of_classes=number_of_classes,
is_training=True)
valid_labels_batch_tensor, valid_logits_batch_tensor = get_valid_logits_and_labels(annotation_batch_tensor=annotation_batch,
logits_batch_tensor=upsampled_logits_batch,
class_labels=class_labels)
cross_entropies = tf.nn.softmax_cross_entropy_with_logits(logits=valid_logits_batch_tensor,
labels=valid_labels_batch_tensor)
# Normalize the cross entropy -- the number of elements
# is different during each step due to mask out regions
cross_entropy_sum = tf.reduce_mean(cross_entropies)
pred = tf.argmax(upsampled_logits_batch, dimension=3)
probabilities = tf.nn.softmax(upsampled_logits_batch)
with tf.variable_scope("adam_vars"):
train_step = tf.train.AdamOptimizer(learning_rate=0.000001).minimize(cross_entropy_sum)
# Variable's initialization functions
vgg_16_without_fc8_variables_mapping = extract_vgg_16_mapping_without_fc8(vgg_16_variables_mapping)
init_fn = slim.assign_from_checkpoint_fn(model_path=vgg_checkpoint_path,
var_list=vgg_16_without_fc8_variables_mapping)
global_vars_init_op = tf.global_variables_initializer()
tf.summary.scalar('cross_entropy_loss', cross_entropy_sum)
merged_summary_op = tf.summary.merge_all()
summary_string_writer = tf.summary.FileWriter(log_folder)
# Create the log folder if doesn't exist yet
if not os.path.exists(log_folder):
os.makedirs(log_folder)
#The op for initializing the variables.
local_vars_init_op = tf.local_variables_initializer()
combined_op = tf.group(local_vars_init_op, global_vars_init_op)
# We need this to save only model variables and omit optimization-related and other variables.
model_variables = slim.get_model_variables()
saver = tf.train.Saver(model_variables)
with tf.Session() as sess:
sess.run(combined_op)
init_fn(sess)
summary_string_writer.add_graph(sess.graph)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
for i in range(testset_len*10):
cross_entropy, summary_string, _ = sess.run([ cross_entropy_sum,
merged_summary_op,
train_step ])
print(i,") Current loss: " + str(cross_entropy))
summary_string_writer.add_summary(summary_string, i)
if i % trainset_len == 0:
save_path = saver.save(sess, model_ckpt_path)
print("Model saved in file: %s" % save_path)
coord.request_stop()
coord.join(threads)
save_path = saver.save(sess, model_ckpt_path)
print("Model saved in file: %s" % save_path)
summary_string_writer.close()
When runing the following code I get this error "InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[1,65536] labels_size=[65536,1]" in cross_entropy_with_logits. I can work around this by doing
but not
And then when training the loss only increases continuously. I have changed the learning rate couple of times to no avail. I'm using images with 2 classes (Background and Ground Truth)