Python tensorflow.less_equal() Examples
The following are 30
code examples of tensorflow.less_equal().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
tensorflow
, or try the search function
.
Example #1
Source File: layers.py From PADME with MIT License | 6 votes |
def radial_cutoff(self, R, rc): """Calculates radial cutoff matrix. B = batch_size, N = max_num_atoms, M = max_num_neighbors Parameters ---------- R [B, N, M]: tf.Tensor Distance matrix. rc: tf.Variable Interaction cutoff [Angstrom]. Returns ------- FC [B, N, M]: tf.Tensor Radial cutoff matrix. """ T = 0.5 * (tf.cos(np.pi * R / (rc)) + 1) E = tf.zeros_like(T) cond = tf.less_equal(R, rc) FC = tf.where(cond, T, E) return FC
Example #2
Source File: preprocessor_test.py From yolo_v2 with Apache License 2.0 | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #3
Source File: preprocessor_test.py From vehicle_counting_tensorflow with MIT License | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #4
Source File: boxes_utils.py From R2CNN_Faster-RCNN_Tensorflow with MIT License | 6 votes |
def filter_outside_boxes(boxes, img_h, img_w): ''' :param anchors:boxes with format [xmin, ymin, xmax, ymax] :param img_h: height of image :param img_w: width of image :return: indices of anchors that inside the image boundary ''' with tf.name_scope('filter_outside_boxes'): xmin, ymin, xmax, ymax = tf.unstack(boxes, axis=1) xmin_index = tf.greater_equal(xmin, 0) ymin_index = tf.greater_equal(ymin, 0) xmax_index = tf.less_equal(xmax, tf.cast(img_w, tf.float32)) ymax_index = tf.less_equal(ymax, tf.cast(img_h, tf.float32)) indices = tf.transpose(tf.stack([xmin_index, ymin_index, xmax_index, ymax_index])) indices = tf.cast(indices, dtype=tf.int32) indices = tf.reduce_sum(indices, axis=1) indices = tf.where(tf.equal(indices, 4)) # indices = tf.equal(indices, 4) return tf.reshape(indices, [-1])
Example #5
Source File: shape_utils.py From vehicle_counting_tensorflow with MIT License | 6 votes |
def assert_box_normalized(boxes, maximum_normalized_coordinate=1.1): """Asserts the input box tensor is normalized. Args: boxes: a tensor of shape [N, 4] where N is the number of boxes. maximum_normalized_coordinate: Maximum coordinate value to be considered as normalized, default to 1.1. Returns: a tf.Assert op which fails when the input box tensor is not normalized. Raises: ValueError: When the input box tensor is not normalized. """ box_minimum = tf.reduce_min(boxes) box_maximum = tf.reduce_max(boxes) return tf.Assert( tf.logical_and( tf.less_equal(box_maximum, maximum_normalized_coordinate), tf.greater_equal(box_minimum, 0)), [boxes])
Example #6
Source File: preprocessor_test.py From object_detector_app with MIT License | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #7
Source File: preprocessor_test.py From Traffic-Rule-Violation-Detection-System with MIT License | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #8
Source File: dataloader.py From training_results_v0.5 with Apache License 2.0 | 6 votes |
def pad_to_fixed_size(data, pad_value, output_shape): """Pad data to a fixed length at the first dimension. Args: data: Tensor to be padded to output_shape. pad_value: A constant value assigned to the paddings. output_shape: The output shape of a 2D tensor. Returns: The Padded tensor with output_shape [max_num_instances, dimension]. """ max_num_instances = output_shape[0] dimension = output_shape[1] data = tf.reshape(data, [-1, dimension]) num_instances = tf.shape(data)[0] assert_length = tf.Assert( tf.less_equal(num_instances, max_num_instances), [num_instances]) with tf.control_dependencies([assert_length]): pad_length = max_num_instances - num_instances paddings = pad_value * tf.ones([pad_length, dimension]) padded_data = tf.concat([data, paddings], axis=0) padded_data = tf.reshape(padded_data, output_shape) return padded_data
Example #9
Source File: dataloader.py From training_results_v0.5 with Apache License 2.0 | 6 votes |
def pad_to_fixed_size(data, pad_value, output_shape): """Pad data to a fixed length at the first dimension. Args: data: Tensor to be padded to output_shape. pad_value: A constant value assigned to the paddings. output_shape: The output shape of a 2D tensor. Returns: The Padded tensor with output_shape [max_num_instances, dimension]. """ max_num_instances = output_shape[0] dimension = output_shape[1] data = tf.reshape(data, [-1, dimension]) num_instances = tf.shape(data)[0] assert_length = tf.Assert( tf.less_equal(num_instances, max_num_instances), [num_instances]) with tf.control_dependencies([assert_length]): pad_length = max_num_instances - num_instances paddings = pad_value * tf.ones([pad_length, dimension]) padded_data = tf.concat([data, paddings], axis=0) padded_data = tf.reshape(padded_data, output_shape) return padded_data
Example #10
Source File: preprocessor_test.py From DOTA_models with Apache License 2.0 | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #11
Source File: dataloader.py From training_results_v0.5 with Apache License 2.0 | 6 votes |
def pad_to_fixed_size(data, pad_value, output_shape): """Pad data to a fixed length at the first dimension. Args: data: Tensor to be padded to output_shape. pad_value: A constant value assigned to the paddings. output_shape: The output shape of a 2D tensor. Returns: The Padded tensor with output_shape [max_num_instances, dimension]. """ max_num_instances = output_shape[0] dimension = output_shape[1] data = tf.reshape(data, [-1, dimension]) num_instances = tf.shape(data)[0] assert_length = tf.Assert( tf.less_equal(num_instances, max_num_instances), [num_instances]) with tf.control_dependencies([assert_length]): pad_length = max_num_instances - num_instances paddings = pad_value * tf.ones([pad_length, dimension]) padded_data = tf.concat([data, paddings], axis=0) padded_data = tf.reshape(padded_data, output_shape) return padded_data
Example #12
Source File: model.py From attention-ocr with MIT License | 6 votes |
def _prepare_image(self, image): """Resize the image to a maximum height of `self.height` and maximum width of `self.width` while maintaining the aspect ratio. Pad the resized image to a fixed size of ``[self.height, self.width]``.""" img = tf.image.decode_png(image, channels=self.channels) dims = tf.shape(img) width = self.max_width max_width = tf.to_int32(tf.ceil(tf.truediv(dims[1], dims[0]) * self.height_float)) max_height = tf.to_int32(tf.ceil(tf.truediv(width, max_width) * self.height_float)) resized = tf.cond( tf.greater_equal(width, max_width), lambda: tf.cond( tf.less_equal(dims[0], self.height), lambda: tf.to_float(img), lambda: tf.image.resize_images(img, [self.height, max_width], method=tf.image.ResizeMethod.BICUBIC), ), lambda: tf.image.resize_images(img, [max_height, width], method=tf.image.ResizeMethod.BICUBIC) ) padded = tf.image.pad_to_bounding_box(resized, 0, 0, self.height, width) return padded
Example #13
Source File: preprocessor_test.py From HereIsWally with MIT License | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #14
Source File: preprocessor_test.py From garbage-object-detection-tensorflow with MIT License | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #15
Source File: inputter.py From OpenNMT-tf with MIT License | 6 votes |
def keep_for_training(self, features, maximum_length=None): """Returns ``True`` if this example should be kept for training. Args: features: A dictionary of ``tf.Tensor``. maximum_length: The maximum length used for training. Returns: A boolean. """ if isinstance(features, (list, tuple)): # Special case for unsupervised inputters that always return a tuple (features, labels). features = features[0] length = self.get_length(features) if length is None: return True is_valid = tf.greater(length, 0) if maximum_length is not None: is_valid = tf.logical_and(is_valid, tf.less_equal(length, maximum_length)) return is_valid
Example #16
Source File: ops.py From Tensorflow-Cookbook with MIT License | 6 votes |
def get_histogram(img, bin_size=0.2): hist_entries = [] img_r, img_g, img_b = tf.split(img, num_or_size_splits=3, axis=-1) for img_chan in [img_r, img_g, img_b]: for i in np.arange(-1, 1, bin_size): gt = tf.greater(img_chan, i) leq = tf.less_equal(img_chan, i + bin_size) condition = tf.cast(tf.logical_and(gt, leq), tf.float32) hist_entries.append(tf.reduce_sum(condition)) hist = normalization(hist_entries) return hist
Example #17
Source File: image_reader_cuda.py From Siamese-RPN-tensorflow with MIT License | 6 votes |
def read_from_disk(self,queue): index_t=queue[0]#tf.random_shuffle(self.input_list)[0] index_min=tf.reshape(tf.where(tf.less_equal(self.node,index_t)),[-1]) node_min=self.node[index_min[-1]] node_max=self.node[index_min[-1]+1] interval_list=list(range(30,100)) interval=tf.random_shuffle(interval_list)[0] index_d=[tf.cond(tf.greater(index_t-interval,node_min),lambda:index_t-interval,lambda:index_t+interval),tf.cond(tf.less(index_t+interval,node_max),lambda:index_t+interval,lambda:index_t-interval)] index_d=tf.random_shuffle(index_d) index_d=index_d[0] constant_t=tf.read_file(self.img_list[index_t]) template=tf.image.decode_jpeg(constant_t, channels=3) template=template[:,:,::-1] constant_d=tf.read_file(self.img_list[index_d]) detection=tf.image.decode_jpeg(constant_d, channels=3) detection=detection[:,:,::-1] template_label=self.label_list[index_t] detection_label=self.label_list[index_d] template_p,template_label_p,_,_=self.crop_resize(template,template_label,1) detection_p,detection_label_p,offset,ratio=self.crop_resize(detection,detection_label,2) return template_p,template_label_p,detection_p,detection_label_p,offset,ratio,detection,detection_label,index_t,index_d
Example #18
Source File: preprocessor_test.py From ros_people_object_detection_tensorflow with Apache License 2.0 | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #19
Source File: util.py From R-Net with MIT License | 6 votes |
def get_batch_dataset(record_file, parser, config): num_threads = tf.constant(config.num_threads, dtype=tf.int32) dataset = tf.data.TFRecordDataset(record_file).map( parser, num_parallel_calls=num_threads).shuffle(config.capacity).repeat() if config.is_bucket: buckets = [tf.constant(num) for num in range(*config.bucket_range)] def key_func(context_idxs, ques_idxs, context_char_idxs, ques_char_idxs, y1, y2, qa_id): c_len = tf.reduce_sum( tf.cast(tf.cast(context_idxs, tf.bool), tf.int32)) buckets_min = [np.iinfo(np.int32).min] + buckets buckets_max = buckets + [np.iinfo(np.int32).max] conditions_c = tf.logical_and( tf.less(buckets_min, c_len), tf.less_equal(c_len, buckets_max)) bucket_id = tf.reduce_min(tf.where(conditions_c)) return bucket_id def reduce_func(key, elements): return elements.batch(config.batch_size) dataset = dataset.apply(tf.contrib.data.group_by_window( key_func, reduce_func, window_size=5 * config.batch_size)).shuffle(len(buckets) * 25) else: dataset = dataset.batch(config.batch_size) return dataset
Example #20
Source File: sequence_at.py From onnx-tensorflow with Apache License 2.0 | 6 votes |
def chk_pos_in_bounds(cls, input_seq, pos): """ Check the position is in-bounds with respect to the sequence. Accepted range for 'position' is in [-n, n - 1], where n is the number of tensors in 'input_sequence'. :param input_seq: input sequence :param pos: position of the output tensor :return: True if position is in-bounds or input length is dynamic. """ seq_length = input_seq.shape[0] if seq_length is None: return True seq_length = tf.cast(seq_length, pos.dtype) cond1 = tf.greater_equal(pos, tf.negative(seq_length)) cond2 = tf.less_equal(pos, seq_length - 1) # pos >= -n and pos < n return tf.reduce_all(tf.logical_and(cond1, cond2))
Example #21
Source File: sequence_erase.py From onnx-tensorflow with Apache License 2.0 | 6 votes |
def chk_pos_in_bounds(cls, input_seq, pos): """ Check the position is in-bounds with respect to the sequence. Accepted range for 'position' is in [-n, n - 1], where n is the number of tensors in 'input_sequence'. :param input_seq: input sequence :param pos: position of the output tensor :return: True if position is in-bounds """ seq_length = tf.shape(input_seq.to_sparse(), out_type=pos.dtype)[0] cond1 = tf.greater_equal(pos, tf.negative(seq_length)) cond2 = tf.less_equal(pos, seq_length - 1) # pos >= -n and pos < n return tf.reduce_all(tf.logical_and(cond1, cond2))
Example #22
Source File: sequence_insert.py From onnx-tensorflow with Apache License 2.0 | 6 votes |
def chk_pos_in_bounds(cls, input_seq, pos): """ Check the position is in-bounds with respect to the sequence. Accepted range for 'position' is in [-n, n], where n is the number of tensors in 'input_sequence'. :param input_seq: input sequence :param pos: position to insert the tensor :return: True if position is in-bounds. """ seq_length = tf.shape(input_seq.to_sparse(), out_type=pos.dtype)[0] cond1 = tf.greater_equal(pos, tf.negative(seq_length)) cond2 = tf.less_equal(pos, seq_length) # pos >= -n and pos <= n return tf.reduce_all(tf.logical_and(cond1, cond2))
Example #23
Source File: util.py From Question_Answering_Models with MIT License | 6 votes |
def get_batch_dataset(record_file, parser, config): num_threads = tf.constant(config.num_threads, dtype=tf.int32) dataset = tf.data.TFRecordDataset(record_file).map( parser, num_parallel_calls=num_threads).shuffle(config.capacity).repeat() if config.is_bucket: buckets = [tf.constant(num) for num in range(*config.bucket_range)] def key_func(context_idxs, ques_idxs, context_char_idxs, ques_char_idxs, y1, y2, qa_id): c_len = tf.reduce_sum( tf.cast(tf.cast(context_idxs, tf.bool), tf.int32)) buckets_min = [np.iinfo(np.int32).min] + buckets buckets_max = buckets + [np.iinfo(np.int32).max] conditions_c = tf.logical_and( tf.less(buckets_min, c_len), tf.less_equal(c_len, buckets_max)) bucket_id = tf.reduce_min(tf.where(conditions_c)) return bucket_id def reduce_func(key, elements): return elements.batch(config.batch_size) dataset = dataset.apply(tf.contrib.data.group_by_window( key_func, reduce_func, window_size=5 * config.batch_size)).shuffle(len(buckets) * 25) else: dataset = dataset.batch(config.batch_size) return dataset
Example #24
Source File: util.py From Question_Answering_Models with MIT License | 6 votes |
def get_batch_dataset(record_file, parser, config): num_threads = tf.constant(config.num_threads, dtype=tf.int32) dataset = tf.data.TFRecordDataset(record_file).map( parser, num_parallel_calls=num_threads).shuffle(config.capacity).repeat() if config.is_bucket: buckets = [tf.constant(num) for num in range(*config.bucket_range)] def key_func(context_idxs, ques_idxs, context_char_idxs, ques_char_idxs, y1, y2, qa_id): c_len = tf.reduce_sum( tf.cast(tf.cast(context_idxs, tf.bool), tf.int32)) buckets_min = [np.iinfo(np.int32).min] + buckets buckets_max = buckets + [np.iinfo(np.int32).max] conditions_c = tf.logical_and( tf.less(buckets_min, c_len), tf.less_equal(c_len, buckets_max)) bucket_id = tf.reduce_min(tf.where(conditions_c)) return bucket_id def reduce_func(key, elements): return elements.batch(config.batch_size) dataset = dataset.apply(tf.contrib.data.group_by_window( key_func, reduce_func, window_size=5 * config.batch_size)).shuffle(len(buckets) * 25) else: dataset = dataset.batch(config.batch_size) return dataset
Example #25
Source File: util.py From Question_Answering_Models with MIT License | 6 votes |
def get_batch_dataset(record_file, parser, config): num_threads = tf.constant(config.num_threads, dtype=tf.int32) dataset = tf.data.TFRecordDataset(record_file).map( parser, num_parallel_calls=num_threads).shuffle(config.capacity).repeat() if config.is_bucket: buckets = [tf.constant(num) for num in range(*config.bucket_range)] def key_func(context_idxs, ques_idxs, context_char_idxs, ques_char_idxs, y1, y2, qa_id): c_len = tf.reduce_sum( tf.cast(tf.cast(context_idxs, tf.bool), tf.int32)) buckets_min = [np.iinfo(np.int32).min] + buckets buckets_max = buckets + [np.iinfo(np.int32).max] conditions_c = tf.logical_and( tf.less(buckets_min, c_len), tf.less_equal(c_len, buckets_max)) bucket_id = tf.reduce_min(tf.where(conditions_c)) return bucket_id def reduce_func(key, elements): return elements.batch(config.batch_size) dataset = dataset.apply(tf.contrib.data.group_by_window( key_func, reduce_func, window_size=5 * config.batch_size)).shuffle(len(buckets) * 25) else: dataset = dataset.batch(config.batch_size) return dataset
Example #26
Source File: preprocessor_test.py From cartoonify with MIT License | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #27
Source File: boxes_utils.py From R2CNN-Plus-Plus_Tensorflow with MIT License | 6 votes |
def filter_outside_boxes(boxes, img_h, img_w): ''' :param anchors:boxes with format [xmin, ymin, xmax, ymax] :param img_h: height of image :param img_w: width of image :return: indices of anchors that inside the image boundary ''' with tf.name_scope('filter_outside_boxes'): xmin, ymin, xmax, ymax = tf.unstack(boxes, axis=1) xmin_index = tf.greater_equal(xmin, 0) ymin_index = tf.greater_equal(ymin, 0) xmax_index = tf.less_equal(xmax, tf.cast(img_w, tf.float32)) ymax_index = tf.less_equal(ymax, tf.cast(img_h, tf.float32)) indices = tf.transpose(tf.stack([xmin_index, ymin_index, xmax_index, ymax_index])) indices = tf.cast(indices, dtype=tf.int32) indices = tf.reduce_sum(indices, axis=1) indices = tf.where(tf.equal(indices, 4)) # indices = tf.equal(indices, 4) return tf.reshape(indices, [-1])
Example #28
Source File: shape_utils.py From object_centric_VAD with MIT License | 6 votes |
def assert_box_normalized(boxes, maximum_normalized_coordinate=1.1): """Asserts the input box tensor is normalized. Args: boxes: a tensor of shape [N, 4] where N is the number of boxes. maximum_normalized_coordinate: Maximum coordinate value to be considered as normalized, default to 1.1. Returns: a tf.Assert op which fails when the input box tensor is not normalized. Raises: ValueError: When the input box tensor is not normalized. """ box_minimum = tf.reduce_min(boxes) box_maximum = tf.reduce_max(boxes) return tf.Assert( tf.logical_and( tf.less_equal(box_maximum, maximum_normalized_coordinate), tf.greater_equal(box_minimum, 0)), [boxes])
Example #29
Source File: preprocessor_test.py From Person-Detection-and-Tracking with MIT License | 6 votes |
def testRandomPixelValueScale(self): preprocessing_options = [] preprocessing_options.append((preprocessor.normalize_image, { 'original_minval': 0, 'original_maxval': 255, 'target_minval': 0, 'target_maxval': 1 })) preprocessing_options.append((preprocessor.random_pixel_value_scale, {})) images = self.createTestImages() tensor_dict = {fields.InputDataFields.image: images} tensor_dict = preprocessor.preprocess(tensor_dict, preprocessing_options) images_min = tf.to_float(images) * 0.9 / 255.0 images_max = tf.to_float(images) * 1.1 / 255.0 images = tensor_dict[fields.InputDataFields.image] values_greater = tf.greater_equal(images, images_min) values_less = tf.less_equal(images, images_max) values_true = tf.fill([1, 4, 4, 3], True) with self.test_session() as sess: (values_greater_, values_less_, values_true_) = sess.run( [values_greater, values_less, values_true]) self.assertAllClose(values_greater_, values_true_) self.assertAllClose(values_less_, values_true_)
Example #30
Source File: boxes_utils.py From R3Det_Tensorflow with MIT License | 6 votes |
def filter_outside_boxes(boxes, img_h, img_w): ''' :param anchors:boxes with format [xmin, ymin, xmax, ymax] :param img_h: height of image :param img_w: width of image :return: indices of anchors that inside the image boundary ''' with tf.name_scope('filter_outside_boxes'): xmin, ymin, xmax, ymax = tf.unstack(boxes, axis=1) xmin_index = tf.greater_equal(xmin, 0) ymin_index = tf.greater_equal(ymin, 0) xmax_index = tf.less_equal(xmax, tf.cast(img_w, tf.float32)) ymax_index = tf.less_equal(ymax, tf.cast(img_h, tf.float32)) indices = tf.transpose(tf.stack([xmin_index, ymin_index, xmax_index, ymax_index])) indices = tf.cast(indices, dtype=tf.int32) indices = tf.reduce_sum(indices, axis=1) indices = tf.where(tf.equal(indices, 4)) # indices = tf.equal(indices, 4) return tf.reshape(indices, [-1])