def load_batch(dataset,
batch_size=28,
height=224,
width=224,
is_training=False):
"""Loads a single batch of data.
Args:
dataset: The dataset to load.
batch_size: The number of images in the batch.
height: The size of each image after preprocessing.
width: The size of each image after preprocessing.
is_training: Whether or not we're currently training or evaluating.
Returns:
images: A Tensor of size [batch_size, height, width, 3], image samples that have been preprocessed.
images_raw: A Tensor of size [batch_size, height, width, 3], image samples that can be used for visualization.
labels: A Tensor of size [batch_size], whose values range between 0 and dataset.num_classes.
"""
data_provider = slim.dataset_data_provider.DatasetDataProvider(
dataset, common_queue_capacity=32, common_queue_min=8)
image_raw, label = data_provider.get(['image', 'label'])
# Preprocess the image for display purposes.
image_raw_disp = tf.expand_dims(image_raw, 0)
image_raw_disp = tf.image.resize_images(image_raw_disp, [height, width])
image_raw_disp = tf.squeeze(image_raw_disp)
# Batch it up.
if is_training:
image = my_resnet_preprocessing.preprocess_image(
image_raw, height, width, is_training=is_training)
# To Use bot: flipped and non-flipped image, use:
#image = tf.stack([image, image_flipped], 0)
#label = tf.stack([label, label], 0)
images, images_raw, labels = tf.train.batch(
[image, image_raw_disp, label],
batch_size=batch_size,
num_threads=1,
capacity=5000)
return images, image_raw_disp, labels
else:
image = my_resnet_preprocessing.preprocess_image(
image_raw, height, width, is_training=is_training)
images, labels = tf.train.batch([image, label],
batch_size=batch_size,
num_threads=1,
capacity=2 * batch_size)
return images, image_raw_disp, labels
def show_examples(number=4):
with tf.Graph().as_default():
dataset = get_split('train_set3', data_dir)
data_provider = slim.dataset_data_provider.DatasetDataProvider(
dataset, common_queue_capacity=32, common_queue_min=8)
image_raw, label = data_provider.get(['image', 'label'])
image = my_resnet_preprocessing.preprocess_image(image_raw,
224,
224,
is_training=True)
with tf.Session() as sess:
with slim.queues.QueueRunners(sess):
for i in range(number):
np_image, np_label = sess.run([image, label])
height, width, _ = np_image.shape
class_name = name = dataset.labels_to_names[np_label]
plt.figure()
plt.imshow(np_image)
plt.title('%s, %d x %d' % (name, height, width))
plt.axis('off')
plt.show()
#show_examples(10)
def show_examples(number_images=4,
split_name='train_set3',
data_dir="mydata/PlantClefTraining2015"):
"""Shows a number of examples of the unprocessed flowerdataset
Args:
number_images: The number of images to show
split_name: A train/validation split name.
dataset_dir: The base directory of the dataset sources.
Returns:
Visualisation of images
"""
with tf.Graph().as_default():
dataset = get_split('train_set3', data_dir)
data_provider = slim.dataset_data_provider.DatasetDataProvider(
dataset, common_queue_capacity=32, common_queue_min=8)
image_raw, label = data_provider.get(['image', 'label'])
image = my_resnet_preprocessing.preprocess_image(image_raw,
224,
224,
is_training=True)
with tf.Session() as sess:
with slim.queues.QueueRunners(sess):
for i in range(number):
np_image, np_label = sess.run([image, label])
height, width, _ = np_image.shape
class_name = name = dataset.labels_to_names[np_label]
plt.figure()
plt.imshow(np_image)
plt.title('%s, %d x %d' % (name, height, width))
plt.axis('off')
plt.show()
def find_most_accurate(
label_directory="mydata/PlantClefTraining2015",
dataset_dir="mydata/train/",
model_directory="mydata/resnet_finetuned_plantclef2015_2/model.ckpt-150000",
dict_directory="mydata/labels",
dict_name="most_accurate_images.txt"):
"""
Finds the images in Filepath, that have the highest output probability, while beeing true.
Args:
label_directory: Where to find the dictionary mapping from class_id to one-hot-labels
dataset_dir: where to find the images
model_directory: where to find your models checkpoints
dict_directory: where to save the images with the highest activation
dict_name: name of the txt-file of the dictionary containing images with the highest activation
Returns:
best_act: dictionary containing images with the highest activation
"""
best_act = {}
label_dict = dataset_utils.read_label_file(label_directory)
label_dict = dict([int(v), k] for k, v in label_dict.items())
with tf.Graph().as_default():
X = tf.placeholder(tf.float32)
image_pre = my_resnet_preprocessing.preprocess_image(
X, 224, 224, False)
image_pre = tf.reshape(image_pre, shape=[-1, 224, 224, 3])
image_pre = tf.to_float(image_pre)
logits = resNetClassifier.my_cnn(image_pre,
is_training=False,
dropout_rate=1.0,
layer=None)
with tf.Session() as sess:
coord = tf.train.Coordinator()
saver = tf.train.Saver()
saver.restore(sess, model_directory)
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
dataset_dir = "optimal_stimuli"
for filename in os.listdir(dataset_dir):
if filename.endswith(".jpg"):
filepath = ("%s/%s" % (dataset_dir, filename))
im = my_functions.get_img(filepath, ).astype(np.float32)
layer_act = sess.run([logits], feed_dict={X: im})
layer_act = my_functions.numpy_softmax(layer_act)
label, _, _, _, _, _ = plantclef_download_and_convert_data.get_class_name_from_xml(
"%s.xml" % (str.split(filepath, ".jpg")[0]))
label = label_dict[label]
if np.argmax(layer_act) == label:
best_act.setdefault(label, [-1, "test.jpg"])
if best_act[label][0] < np.amax(layer_act):
best_act[label] = [np.amax(layer_act), filename]
dataset_utils.write_label_file(best_act,
dict_directory,
filename=dict_name)
return best_act