我们从Python开源项目中，提取了以下23个代码示例，用于说明如何使用utils.Dequantize()。
def get_frame_input_feature(input_file): features = [] record_iterator = tf.python_io.tf_record_iterator(path=input_file) for i, string_record in enumerate(record_iterator): example = tf.train.SequenceExample() example.ParseFromString(string_record) # traverse the Example format to get data video_id = example.context.feature['video_id'].bytes_list.value[0] label = example.context.feature['labels'].int64_list.value[:] rgbs = [] audios = [] rgb_feature = example.feature_lists.feature_list['rgb'].feature for i in range(len(rgb_feature)): rgb = np.fromstring(rgb_feature[i].bytes_list.value[0], dtype=np.uint8).astype(np.float32) rgb = utils.Dequantize(rgb, 2, -2) rgbs.append(rgb) audio_feature = example.feature_lists.feature_list['audio'].feature for i in range(len(audio_feature)): audio = np.fromstring(audio_feature[i].bytes_list.value[0], dtype=np.uint8).astype(np.float32) audio = utils.Dequantize(audio, 2, -2) audios.append(audio) rgbs = np.array(rgbs) audios = np.array(audios) features.append((video_id, label, rgbs, audios)) return features
def get_video_matrix(self, features, feature_size, max_frames, max_quantized_value, min_quantized_value): """Decodes features from an input string and quantizes it. Args: features: raw feature values feature_size: length of each frame feature vector max_frames: number of frames (rows) in the output feature_matrix max_quantized_value: the maximum of the quantized value. min_quantized_value: the minimum of the quantized value. Returns: feature_matrix: matrix of all frame-features num_frames: number of frames in the sequence """ decoded_features = tf.reshape( tf.cast(tf.decode_raw(features, tf.uint8), tf.float32), [-1, feature_size]) num_frames = tf.minimum(tf.shape(decoded_features)[0], max_frames) feature_matrix = utils.Dequantize(decoded_features, max_quantized_value, min_quantized_value) feature_matrix = resize_axis(feature_matrix, 0, max_frames) return feature_matrix, num_frames
def frame_example_2_np(seq_example_bytes, max_quantized_value=2, min_quantized_value=-2): feature_names=['rgb','audio'] feature_sizes = [1024, 128] with tf.Graph().as_default(): contexts, features = tf.parse_single_sequence_example( seq_example_bytes, context_features={"video_id": tf.FixedLenFeature( [], tf.string), "labels": tf.VarLenFeature(tf.int64)}, sequence_features={ feature_name : tf.FixedLenSequenceFeature([], dtype=tf.string) for feature_name in feature_names }) decoded_features = { name: tf.reshape( tf.cast(tf.decode_raw(features[name], tf.uint8), tf.float32), [-1, size]) for name, size in zip(feature_names, feature_sizes) } feature_matrices = { name: utils.Dequantize(decoded_features[name], max_quantized_value, min_quantized_value) for name in feature_names} with tf.Session() as sess: vid = sess.run(contexts['video_id']) labs = sess.run(contexts['labels'].values) rgb = sess.run(feature_matrices['rgb']) audio = sess.run(feature_matrices['audio']) return vid, labs, rgb, audio #%% Split frame level file into three video level files: all, 1st half, 2nd half.
def build_graph(): feature_names=['rgb','audio'] feature_sizes = [1024, 128] max_quantized_value=2 min_quantized_value=-2 seq_example_bytes = tf.placeholder(tf.string) contexts, features = tf.parse_single_sequence_example( seq_example_bytes, context_features={"video_id": tf.FixedLenFeature( [], tf.string), "labels": tf.VarLenFeature(tf.int64)}, sequence_features={ feature_name : tf.FixedLenSequenceFeature([], dtype=tf.string) for feature_name in feature_names }) decoded_features = { name: tf.reshape( tf.cast(tf.decode_raw(features[name], tf.uint8), tf.float32), [-1, size]) for name, size in zip(feature_names, feature_sizes) } feature_matrices = { name: utils.Dequantize(decoded_features[name], max_quantized_value, min_quantized_value) for name in feature_names} tf.add_to_collection("vid_tsr", contexts['video_id']) tf.add_to_collection("labs_tsr", contexts['labels'].values) tf.add_to_collection("rgb_tsr", feature_matrices['rgb']) tf.add_to_collection("audio_tsr", feature_matrices['audio']) tf.add_to_collection("seq_example_bytes", seq_example_bytes) # with tf.Session() as sess: # writer = tf.summary.FileWriter('./graphs', sess.graph)
def prepare_reader(self, filename_queue, max_quantized_value=2, min_quantized_value=-2): reader = tf.TFRecordReader() _, serialized_example = reader.read(filename_queue) context_features, sequence_features = {"video_id": tf.FixedLenFeature([], tf.string), "labels": tf.VarLenFeature(tf.int64)}, None if self.sequence_data: sequence_features = {self.feature_name[0]: tf.FixedLenSequenceFeature([], dtype=tf.string), self.feature_name[1]: tf.FixedLenSequenceFeature([], dtype=tf.string), } else: context_features[self.feature_name[0]] = tf.FixedLenFeature(self.feature_size[0], tf.float32) context_features[self.feature_name[1]] = tf.FixedLenFeature(self.feature_size[1], tf.float32) contexts, features = tf.parse_single_sequence_example(serialized_example, context_features=context_features, sequence_features=sequence_features) labels = (tf.cast(contexts["labels"].values, tf.int64)) if self.sequence_data: decoded_features = tf.reshape(tf.cast(tf.decode_raw(features[self.feature_name[0]], tf.uint8), tf.float32), [-1, self.feature_size[0]]) video_matrix = Dequantize(decoded_features, max_quantized_value, min_quantized_value) decoded_features = tf.reshape(tf.cast(tf.decode_raw(features[self.feature_name[1]], tf.uint8), tf.float32), [-1, self.feature_size[1]]) audio_matrix = Dequantize(decoded_features, max_quantized_value, min_quantized_value) num_frames = tf.minimum(tf.shape(decoded_features)[0], self.max_frames) else: video_matrix = contexts[self.feature_name[0]] audio_matrix = contexts[self.feature_name[1]] num_frames = tf.constant(-1) # Pad or truncate to 'max_frames' frames. # video_matrix = resize_axis(video_matrix, 0, self.max_frames) return contexts["video_id"], video_matrix, audio_matrix, labels, num_frames
