def input_fn(): with tf.name_scope('post_forward'): out_shape = [FLAGS.train_image_size] * 2 anchor_creator = anchor_manipulator.AnchorCreator( out_shape, layers_shapes=[(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)], anchor_scales=[(0.1, ), (0.2, ), (0.375, ), (0.55, ), (0.725, ), (0.9, )], extra_anchor_scales=[(0.1414, ), (0.2739, ), (0.4541, ), (0.6315, ), (0.8078, ), (0.9836, )], anchor_ratios=[(1., 2., .5), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., .5), (1., 2., .5)], layer_steps=[8, 16, 32, 64, 100, 300]) all_anchors, all_num_anchors_depth, all_num_anchors_spatial = anchor_creator.get_all_anchors( ) num_anchors_per_layer = [] for ind in range(len(all_anchors)): num_anchors_per_layer.append(all_num_anchors_depth[ind] * all_num_anchors_spatial[ind]) anchor_encoder_decoder = anchor_manipulator.AnchorEncoder( allowed_borders=[1.0] * 6, positive_threshold=FLAGS.match_threshold, ignore_threshold=FLAGS.neg_threshold, prior_scaling=[0.1, 0.1, 0.2, 0.2]) # global global_anchor_info # global_anchor_info = {'decode_fn': lambda pred : anchor_encoder_decoder.decode_all_anchors(pred, num_anchors_per_layer), # 'num_anchors_per_layer': num_anchors_per_layer, # 'all_num_anchors_depth': all_num_anchors_depth, # 'encode_fn': lambda glabels_, gbboxes_: anchor_encoder_decoder.encode_all_anchors(glabels_, gbboxes_, all_anchors, all_num_anchors_depth, all_num_anchors_spatial)} image_preprocessing_fn = lambda image_, labels_, bboxes_: ssd_preprocessing.preprocess_image( image_, labels_, bboxes_, out_shape, is_training=is_training, data_format=FLAGS.data_format, output_rgb=False) # anchor_encoder_fn = lambda glabels_, gbboxes_: anchor_encoder_decoder.encode_all_anchors(glabels_, gbboxes_, all_anchors, all_num_anchors_depth, all_num_anchors_spatial) filenames = tf.placeholder(tf.string, shape=[None]) arga = tf.constant(True) dataset = tf.data.TFRecordDataset(training_files) dataset = dataset.map(lambda x: data_mapping_fn( x, is_training, image_preprocessing_fn)) dataset = dataset.repeat() # repeat the input infinitely dataset = dataset.batch(batch_size) # set the batch size iterator = dataset.make_initializable_iterator() # return image, {'shape': shape, 'loc_targets': loc_targets, 'cls_targets': cls_targets, 'match_scores': match_scores} return dataset
def image_preprocessing_fn(image_, labels_, bboxes_): return ssd_preprocessing.preprocess_image(image_, labels_, bboxes_, out_shape, is_training=False, data_format=DATA_FORMAT, output_rgb=False)
def image_preprocessing_fn(image_, labels_, bboxes_): return ssd_preprocessing.preprocess_image( image_, labels_, bboxes_, out_shape, is_training=is_training, data_format=FLAGS.data_format, output_rgb=False)
def input_fn(dataset_pattern='val-*', batch_size=1, data_location=None): out_shape = [SSD_VGG16_IMAGE_SIZE] * 2 anchor_creator = anchor_manipulator.AnchorCreator( out_shape, layers_shapes=[(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)], anchor_scales=[(0.1, ), (0.2, ), (0.375, ), (0.55, ), (0.725, ), (0.9, )], extra_anchor_scales=[(0.1414, ), (0.2739, ), (0.4541, ), (0.6315, ), (0.8078, ), (0.9836, )], anchor_ratios=[(1., 2., .5), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., .5), (1., 2., .5)], layer_steps=[8, 16, 32, 64, 100, 300]) all_anchors, all_num_anchors_depth, all_num_anchors_spatial = anchor_creator.get_all_anchors( ) num_anchors_per_layer = [] for ind in range(len(all_anchors)): num_anchors_per_layer.append(all_num_anchors_depth[ind] * all_num_anchors_spatial[ind]) anchor_encoder_decoder = anchor_manipulator.AnchorEncoder( allowed_borders=[1.0] * 6, positive_threshold=MATCH_THRESHOLD, ignore_threshold=NEG_THRESHOLD, prior_scaling=[0.1, 0.1, 0.2, 0.2]) image_preprocessing_fn = lambda image_, labels_, bboxes_: ssd_preprocessing.preprocess_image( image_, labels_, bboxes_, out_shape, is_training=False, data_format=DATA_FORMAT, output_rgb=False) anchor_encoder_fn = lambda glabels_, gbboxes_: anchor_encoder_decoder.encode_all_anchors( glabels_, gbboxes_, all_anchors, all_num_anchors_depth, all_num_anchors_spatial) image, filename, shape, loc_targets, cls_targets, match_scores = \ dataset_common.slim_get_batch(NUM_CLASSES, batch_size, 'val', os.path.join( data_location, dataset_pattern), NUM_READERS, NUM_PREPROCESSING_THREADS, image_preprocessing_fn, anchor_encoder_fn, num_epochs=1, is_training=False) return image, filename, shape
def input_fn(): out_shape = [FLAGS.train_image_size] * 2 ssd300_anchor_params = {'layers_shapes': [(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)], 'anchor_scales': [(0.1,), (0.2,), (0.375,), (0.55,), (0.725,), (0.9,)], 'extra_anchor_scales': [(0.1414,), (0.2739,), (0.4541,), (0.6315,), (0.8078,), (0.9836,)], 'anchor_ratios': [(1., 2., .5), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., .5), (1., 2., .5)], 'layer_steps': [8, 16, 32, 64, 100, 300]} ssd512_anchor_params = {'layers_shapes': [(64, 64), (32, 32), (16, 16), (8, 8), (4, 4), (2, 2), (1, 1)], 'anchor_scales': [(0.07,), (0.15,), (0.3,), (0.45,), (0.6,), (0.75,), (0.9,)], 'extra_anchor_scales': [(0.1025,), (0.2121,), (0.3674,), (0.5196,), (0.6708,), (0.8216,), (0.9721,)], 'anchor_ratios': [(1., 2., .5), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., .5), (1., 2., .5)], 'layer_steps': [8, 16, 32, 64, 128, 256, 512]} if FLAGS.train_image_size == 512: net_params = ssd512_anchor_params print('using ssd512 model') else: net_params = ssd300_anchor_params print('using ssd300 model') anchor_creator = anchor_manipulator.AnchorCreator(out_shape, **net_params) all_anchors, all_num_anchors_depth, all_num_anchors_spatial = anchor_creator.get_all_anchors() num_anchors_per_layer = [] for ind in range(len(all_anchors)): num_anchors_per_layer.append(all_num_anchors_depth[ind] * all_num_anchors_spatial[ind]) anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(allowed_borders = [1.0] * len(net_params['layer_steps']), positive_threshold = FLAGS.match_threshold, ignore_threshold = FLAGS.neg_threshold, prior_scaling=[0.1, 0.1, 0.2, 0.2]) image_preprocessing_fn = lambda image_, labels_, bboxes_ : ssd_preprocessing.preprocess_image(image_, labels_, bboxes_, out_shape, is_training=is_training, data_format=FLAGS.data_format, output_rgb=False) anchor_encoder_fn = lambda glabels_, gbboxes_: anchor_encoder_decoder.encode_all_anchors(glabels_, gbboxes_, all_anchors, all_num_anchors_depth, all_num_anchors_spatial) image, filename, shape, loc_targets, cls_targets, match_scores = dataset_common.slim_get_batch(FLAGS.num_classes, batch_size, ('train' if is_training else 'val'), os.path.join(FLAGS.data_dir, dataset_pattern), FLAGS.num_readers, FLAGS.num_preprocessing_threads, image_preprocessing_fn, anchor_encoder_fn, num_epochs=FLAGS.train_epochs, is_training=is_training) global global_anchor_info global_anchor_info = {'decode_fn': lambda pred : anchor_encoder_decoder.decode_all_anchors(pred, num_anchors_per_layer), 'num_anchors_per_layer': num_anchors_per_layer, 'all_num_anchors_depth': all_num_anchors_depth } return {'image': image, 'filename': filename, 'shape': shape, 'loc_targets': loc_targets, 'cls_targets': cls_targets, 'match_scores': match_scores}, None
def input_fn(): assert batch_size==1, 'We only support single batch when evaluation.' target_shape = [FLAGS.train_image_size] * 2 image_preprocessing_fn = lambda image_, labels_, bboxes_ : ssd_preprocessing.preprocess_image(image_, labels_, bboxes_, target_shape, is_training=is_training, data_format=FLAGS.data_format, output_rgb=False) image, filename, shape, output_shape = dataset_common.slim_get_batch(FLAGS.num_classes, batch_size, ('train' if is_training else 'val'), os.path.join(FLAGS.data_dir, dataset_pattern), FLAGS.num_readers, FLAGS.num_preprocessing_threads, image_preprocessing_fn, None, num_epochs=1, is_training=is_training) return {'image': image, 'filename': filename, 'shape': shape, 'output_shape': output_shape}, None
def input_fn(): out_shape = [FLAGS.train_image_size] * 2 anchor_creator = anchor_manipulator.AnchorCreator(out_shape, layers_shapes = [(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)], anchor_scales = [(0.1,), (0.2,), (0.375,), (0.55,), (0.725,), (0.9,)], extra_anchor_scales = [(0.1414,), (0.2739,), (0.4541,), (0.6315,), (0.8078,), (0.9836,)], anchor_ratios = [(1., 2., .5), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., .5), (1., 2., .5)], layer_steps = [8, 16, 32, 64, 100, 300]) all_anchors, all_num_anchors_depth, all_num_anchors_spatial = anchor_creator.get_all_anchors() # all_anchors: [[(38x38x1),(38x38x1),(4x1),(4x1)],[(19x19x1),(19x19x1),(4x1),(4x1)]... ] -> recording all the anchors information num_anchors_per_layer = [] for ind in range(len(all_anchors)): num_anchors_per_layer.append(all_num_anchors_depth[ind] * all_num_anchors_spatial[ind]) anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(allowed_borders = [1.0] * 6, positive_threshold = FLAGS.match_threshold, ignore_threshold = FLAGS.neg_threshold, prior_scaling=[0.1, 0.1, 0.2, 0.2]) image_preprocessing_fn = lambda image_, labels_, bboxes_ : ssd_preprocessing.preprocess_image(image_, labels_, bboxes_, out_shape, is_training=is_training, data_format=FLAGS.data_format, output_rgb=False) anchor_encoder_fn = lambda glabels_, gbboxes_: anchor_encoder_decoder.encode_all_anchors(glabels_, gbboxes_, all_anchors, all_num_anchors_depth, all_num_anchors_spatial) anchor_decoder_fn = lambda pred : anchor_encoder_decoder.decode_all_anchors(pred, num_anchors_per_layer) image, _, shape, loc_targets, cls_targets, match_scores = dataset_common.slim_get_batch(FLAGS.num_classes, batch_size, ('train' if is_training else 'val'), os.path.join(FLAGS.data_dir, dataset_pattern), FLAGS.num_readers, FLAGS.num_preprocessing_threads, image_preprocessing_fn, anchor_encoder_fn, num_epochs=FLAGS.train_epochs, is_training=is_training) global global_anchor_info global_anchor_info = {'decode_fn': anchor_decoder_fn, 'num_anchors_per_layer': num_anchors_per_layer, 'all_num_anchors_depth': all_num_anchors_depth } return image, {'shape': shape, 'loc_targets': loc_targets, 'cls_targets': cls_targets, 'match_scores': match_scores}
def slim_get_split(file_pattern='{}_????'): # Features in Pascal VOC TFRecords. keys_to_features = { 'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''), 'image/format': tf.FixedLenFeature((), tf.string, default_value='jpeg'), 'image/height': tf.FixedLenFeature([1], tf.int64), 'image/width': tf.FixedLenFeature([1], tf.int64), 'image/channels': tf.FixedLenFeature([1], tf.int64), 'image/shape': tf.FixedLenFeature([3], tf.int64), 'image/object/bbox/xmin': tf.VarLenFeature(dtype=tf.float32), 'image/object/bbox/ymin': tf.VarLenFeature(dtype=tf.float32), 'image/object/bbox/xmax': tf.VarLenFeature(dtype=tf.float32), 'image/object/bbox/ymax': tf.VarLenFeature(dtype=tf.float32), 'image/object/bbox/label': tf.VarLenFeature(dtype=tf.int64), 'image/object/bbox/difficult': tf.VarLenFeature(dtype=tf.int64), 'image/object/bbox/truncated': tf.VarLenFeature(dtype=tf.int64), } items_to_handlers = { 'image': slim.tfexample_decoder.Image('image/encoded', 'image/format'), 'shape': slim.tfexample_decoder.Tensor('image/shape'), 'object/bbox': slim.tfexample_decoder.BoundingBox( ['ymin', 'xmin', 'ymax', 'xmax'], 'image/object/bbox/'), 'object/label': slim.tfexample_decoder.Tensor('image/object/bbox/label'), 'object/difficult': slim.tfexample_decoder.Tensor('image/object/bbox/difficult'), 'object/truncated': slim.tfexample_decoder.Tensor('image/object/bbox/truncated'), } decoder = slim.tfexample_decoder.TFExampleDecoder(keys_to_features, items_to_handlers) dataset = slim.dataset.Dataset( data_sources=file_pattern, reader=tf.TFRecordReader, decoder=decoder, num_samples=100, items_to_descriptions=None, num_classes=21, labels_to_names=None) with tf.name_scope('dataset_data_provider'): provider = slim.dataset_data_provider.DatasetDataProvider( dataset, num_readers=2, common_queue_capacity=32, common_queue_min=8, shuffle=True, num_epochs=1) [org_image, shape, glabels_raw, gbboxes_raw, isdifficult] = provider.get(['image', 'shape', 'object/label', 'object/bbox', 'object/difficult']) image, glabels, gbboxes = ssd_preprocessing.preprocess_image(org_image, glabels_raw, gbboxes_raw, [300, 300], is_training=True, data_format='channels_last', output_rgb=True) anchor_creator = anchor_manipulator.AnchorCreator([300] * 2, layers_shapes=[(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)], anchor_scales=[(0.1,), (0.2,), (0.375,), (0.55,), (0.725,), (0.9,)], extra_anchor_scales=[(0.1414,), (0.2739,), (0.4541,), (0.6315,), (0.8078,), (0.9836,)], anchor_ratios=[(2., .5), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., .5), (2., .5)], layer_steps=[8, 16, 32, 64, 100, 300]) all_anchors, all_num_anchors_depth, all_num_anchors_spatial = anchor_creator.get_all_anchors() num_anchors_per_layer = [] for ind in range(len(all_anchors)): num_anchors_per_layer.append(all_num_anchors_depth[ind] * all_num_anchors_spatial[ind]) anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(allowed_borders=[1.0] * 6, positive_threshold=0.5, ignore_threshold=0.5, prior_scaling=[0.1, 0.1, 0.2, 0.2]) gt_targets, gt_labels, gt_scores = anchor_encoder_decoder.encode_all_anchors(glabels, gbboxes, all_anchors, all_num_anchors_depth, all_num_anchors_spatial, True) anchors = anchor_encoder_decoder._all_anchors # split by layers gt_targets, gt_labels, gt_scores, anchors = tf.split(gt_targets, num_anchors_per_layer, axis=0), \ tf.split(gt_labels, num_anchors_per_layer, axis=0), \ tf.split(gt_scores, num_anchors_per_layer, axis=0), \ [tf.split(anchor, num_anchors_per_layer, axis=0) for anchor in anchors] save_image_op = tf.py_func(save_image_with_bbox, [ssd_preprocessing.unwhiten_image(image), tf.clip_by_value(tf.concat(gt_labels, axis=0), 0, tf.int64.max), tf.concat(gt_scores, axis=0), tf.concat(gt_targets, axis=0)], tf.int64, stateful=True) return save_image_op
def slim_get_split(file_pattern='{}_????'): # Features in Pascal VOC TFRecords. keys_to_features = { 'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''), 'image/format': tf.FixedLenFeature((), tf.string, default_value='jpeg'), 'image/height': tf.FixedLenFeature([1], tf.int64), 'image/width': tf.FixedLenFeature([1], tf.int64), 'image/channels': tf.FixedLenFeature([1], tf.int64), 'image/shape': tf.FixedLenFeature([3], tf.int64), 'image/object/bbox/xmin': tf.VarLenFeature(dtype=tf.float32), 'image/object/bbox/ymin': tf.VarLenFeature(dtype=tf.float32), 'image/object/bbox/xmax': tf.VarLenFeature(dtype=tf.float32), 'image/object/bbox/ymax': tf.VarLenFeature(dtype=tf.float32), 'image/object/bbox/label': tf.VarLenFeature(dtype=tf.int64), 'image/object/bbox/difficult': tf.VarLenFeature(dtype=tf.int64), 'image/object/bbox/truncated': tf.VarLenFeature(dtype=tf.int64), } items_to_handlers = { 'image': slim.tfexample_decoder.Image('image/encoded', 'image/format'), 'shape': slim.tfexample_decoder.Tensor('image/shape'), 'object/bbox': slim.tfexample_decoder.BoundingBox(['ymin', 'xmin', 'ymax', 'xmax'], 'image/object/bbox/'), 'object/label': slim.tfexample_decoder.Tensor('image/object/bbox/label'), 'object/difficult': slim.tfexample_decoder.Tensor('image/object/bbox/difficult'), 'object/truncated': slim.tfexample_decoder.Tensor('image/object/bbox/truncated'), } decoder = slim.tfexample_decoder.TFExampleDecoder(keys_to_features, items_to_handlers) dataset = slim.dataset.Dataset(data_sources=file_pattern, reader=tf.TFRecordReader, decoder=decoder, num_samples=100, items_to_descriptions=None, num_classes=21, labels_to_names=None) with tf.name_scope('dataset_data_provider'): provider = slim.dataset_data_provider.DatasetDataProvider( dataset, num_readers=2, common_queue_capacity=32, common_queue_min=8, shuffle=True, num_epochs=1) [org_image, shape, glabels_raw, gbboxes_raw, isdifficult] = provider.get( ['image', 'shape', 'object/label', 'object/bbox', 'object/difficult']) image, glabels, gbboxes = ssd_preprocessing.preprocess_image( org_image, glabels_raw, gbboxes_raw, [300, 300], is_training=True, data_format='channels_last', output_rgb=True) anchor_encoder_decoder = anchor_manipulator.AnchorEncoder( positive_threshold=0.5, ignore_threshold=0.5, prior_scaling=[0.1, 0.1, 0.2, 0.2]) all_anchor_scales = [(30., ), (60., ), (112.5, ), (165., ), (217.5, ), (270., )] all_extra_scales = [(42.43, ), (82.17, ), (136.23, ), (189.45, ), (242.34, ), (295.08, )] all_anchor_ratios = [(2., .5), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., 3., .5, 0.3333), (2., .5), (2., .5)] all_layer_shapes = [(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)] all_layer_strides = [8, 16, 32, 64, 100, 300] total_layers = len(all_layer_shapes) anchors_height = list() anchors_width = list() anchors_depth = list() for ind in range(total_layers): _anchors_height, _anchors_width, _anchor_depth = anchor_encoder_decoder.get_anchors_width_height( all_anchor_scales[ind], all_extra_scales[ind], all_anchor_ratios[ind]) anchors_height.append(_anchors_height) anchors_width.append(_anchors_width) anchors_depth.append(_anchor_depth) anchors_ymin, anchors_xmin, anchors_ymax, anchors_xmax, inside_mask = anchor_encoder_decoder.get_all_anchors( [300] * 2, anchors_height, anchors_width, anchors_depth, [0.5] * total_layers, all_layer_shapes, all_layer_strides, [300.] * total_layers, [False] * total_layers) gt_targets, gt_labels, gt_scores = anchor_encoder_decoder.encode_anchors( glabels, gbboxes, anchors_ymin, anchors_xmin, anchors_ymax, anchors_xmax, inside_mask, True) num_anchors_per_layer = list() for ind, layer_shape in enumerate(all_layer_shapes): _, _num_anchors_per_layer = anchor_encoder_decoder.get_anchors_count( anchors_depth[ind], layer_shape) num_anchors_per_layer.append(_num_anchors_per_layer) # split by layers all_anchors = tf.stack( [anchors_ymin, anchors_xmin, anchors_ymax, anchors_xmax], axis=-1) gt_targets, gt_labels, gt_scores, anchors = tf.split(gt_targets, num_anchors_per_layer, axis=0),\ tf.split(gt_labels, num_anchors_per_layer, axis=0),\ tf.split(gt_scores, num_anchors_per_layer, axis=0),\ tf.split(all_anchors, num_anchors_per_layer, axis=0) save_image_op = tf.py_func(save_image_with_bbox, [ ssd_preprocessing.unwhiten_image(image), tf.clip_by_value(tf.concat(gt_labels, axis=0), 0, tf.int64.max), tf.concat(gt_scores, axis=0), tf.concat(gt_targets, axis=0) ], tf.int64, stateful=True) return save_image_op
def input_fn(): #train_imgage_size = 300 [300, 300] target_shape = [FLAGS.train_image_size] * 2 #match_threshold:0.5 #neg_threshold:0.5 anchor_encoder_decoder = anchor_manipulator.AnchorEncoder( positive_threshold=FLAGS.match_threshold, ignore_threshold=FLAGS.neg_threshold, prior_scaling=[0.1, 0.1, 0.2, 0.2]) all_anchor_scales = [(30., ), (60., ), (112.5, ), (165., ), (217.5, ), (270., )] all_extra_scales = [(42.43, ), (82.17, ), (136.23, ), (189.45, ), (242.34, ), (295.08, )] all_anchor_ratios = [(1., 2., .5), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., 3., .5, 0.3333), (1., 2., .5), (1., 2., .5)] all_layer_shapes = [(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)] all_layer_strides = [8, 16, 32, 64, 100, 300] total_layers = len(all_layer_shapes) anchors_height = list() anchors_width = list() anchors_depth = list() for ind in range(total_layers): #若该层有n个default_prior_box则anchors_height是这些box的h,_anchor_depth是n _anchors_height, _anchors_width, _anchor_depth = anchor_encoder_decoder.get_anchors_width_height( all_anchor_scales[ind], all_extra_scales[ind], all_anchor_ratios[ind], name='get_anchors_width_height{}'.format(ind)) anchors_height.append(_anchors_height) anchors_width.append(_anchors_width) anchors_depth.append(_anchor_depth) #anchors_ymin: [38*38*4 + 19*19*6 + 10*10*6 + 5*5*6 + 3*3*4 + 1*!*4] anchors_ymin, anchors_xmin, anchors_ymax, anchors_xmax, inside_mask = anchor_encoder_decoder.get_all_anchors( target_shape, anchors_height, anchors_width, anchors_depth, [0.5] * total_layers, all_layer_shapes, all_layer_strides, [FLAGS.train_image_size * 1.] * total_layers, [False] * total_layers) num_anchors_per_layer = list() #all_layer_shapes [(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)] for ind, layer_shape in enumerate(all_layer_shapes): #num_anchors_per_layer:layer_shape[0]*layer_layer[1]*anchors_depth _, _num_anchors_per_layer = anchor_encoder_decoder.get_anchors_count( anchors_depth[ind], layer_shape, name='get_anchor_count{}'.format(ind)) num_anchors_per_layer.append(_num_anchors_per_layer) #num_anchors_per_layer:[38*38*4, 19*19*6, 10*10*6, 5*5*6, 3*3*4, 1*!*4] image_preprocessing_fn = lambda image_, labels_, bboxes_: ssd_preprocessing.preprocess_image( image_, labels_, bboxes_, target_shape, is_training=is_training, data_format=FLAGS.data_format, output_rgb=False) anchor_encoder_fn = lambda glabels_, gbboxes_: anchor_encoder_decoder.encode_anchors( glabels_, gbboxes_, anchors_ymin, anchors_xmin, anchors_ymax, anchors_xmax, inside_mask) image, _, shape, loc_targets, cls_targets, match_scores = dataset_common.slim_get_batch( FLAGS.num_classes, batch_size, ('train' if is_training else 'val'), os.path.join(FLAGS.data_dir, dataset_pattern), FLAGS.num_readers, FLAGS.num_preprocessing_threads, image_preprocessing_fn, anchor_encoder_fn, num_epochs=FLAGS.train_epochs, is_training=is_training) global global_anchor_info global_anchor_info = { 'decode_fn': lambda pred: anchor_encoder_decoder.batch_decode_anchors( pred, anchors_ymin, anchors_xmin, anchors_ymax, anchors_xmax), 'num_anchors_per_layer': num_anchors_per_layer, 'all_num_anchors_depth': anchors_depth } return image, { 'shape': shape, 'loc_targets': loc_targets, 'cls_targets': cls_targets, 'match_scores': match_scores }