| model { | |
| ssd { | |
| num_classes: 2 | |
| box_coder { | |
| keypoint_box_coder { | |
| num_keypoints: 23 | |
| y_scale: 10.0 | |
| x_scale: 10.0 | |
| height_scale: 5.0 | |
| width_scale: 5.0 | |
| } | |
| } | |
| matcher { | |
| argmax_matcher { | |
| matched_threshold: 0.5 | |
| unmatched_threshold: 0.5 | |
| ignore_thresholds: false | |
| negatives_lower_than_unmatched: true | |
| force_match_for_each_row: true | |
| } | |
| } | |
| similarity_calculator { | |
| iou_similarity { | |
| } | |
| } | |
| anchor_generator { | |
| ssd_anchor_generator { | |
| num_layers: 6 | |
| min_scale: 0.2 | |
| max_scale: 0.95 | |
| aspect_ratios: 1.0 | |
| aspect_ratios: 2.0 | |
| aspect_ratios: 0.5 | |
| aspect_ratios: 3.0 | |
| aspect_ratios: 0.3333 | |
| height_stride: 16 | |
| height_stride: 32 | |
| height_stride: 64 | |
| height_stride: 128 | |
| height_stride: 256 | |
| height_stride: 512 | |
| width_stride: 16 | |
| width_stride: 32 | |
| width_stride: 64 | |
| width_stride: 128 | |
| width_stride: 256 | |
| width_stride: 512 | |
| height_offset: 0 | |
| height_offset: 0 | |
| height_offset: 0 | |
| height_offset: 0 | |
| height_offset: 0 | |
| height_offset: 0 | |
| width_offset: 0 | |
| width_offset: 0 | |
| width_offset: 0 | |
| width_offset: 0 | |
| width_offset: 0 | |
| width_offset: 0 | |
| } | |
| } | |
| image_resizer { | |
| keep_aspect_ratio_resizer { | |
| min_dimension: 320 | |
| max_dimension: 640 | |
| convert_to_grayscale: true | |
| } | |
| } | |
| box_predictor { | |
| convolutional_box_predictor { | |
| min_depth: 0 | |
| max_depth: 0 | |
| num_layers_before_predictor: 0 | |
| use_dropout: false | |
| kernel_size: 3 | |
| box_code_size: 50 | |
| apply_sigmoid_to_scores: false | |
| conv_hyperparams { | |
| activation: RELU_6 | |
| regularizer { | |
| l2_regularizer { | |
| weight: 0.00004 | |
| } | |
| } | |
| initializer { | |
| truncated_normal_initializer { | |
| stddev: 0.03 | |
| mean: 0.0 | |
| } | |
| } | |
| batch_norm { | |
| train: true | |
| scale: true | |
| center: true | |
| decay: 0.9997 | |
| epsilon: 0.001 | |
| } | |
| } | |
| } | |
| } | |
| feature_extractor { | |
| type: "ssd_mobilenet_v1" | |
| min_depth: 16 | |
| depth_multiplier: 0.25 | |
| use_explicit_padding: true | |
| conv_hyperparams { | |
| activation: RELU_6 | |
| regularizer { | |
| l2_regularizer { | |
| weight: 0.00004 | |
| } | |
| } | |
| initializer { | |
| truncated_normal_initializer { | |
| stddev: 0.03 | |
| mean: 0.0 | |
| } | |
| } | |
| batch_norm { | |
| train: true | |
| scale: true | |
| center: true | |
| decay: 0.9997 | |
| epsilon: 0.001 | |
| } | |
| } | |
| } | |
| loss { | |
| classification_loss { | |
| weighted_sigmoid { | |
| } | |
| } | |
| localization_loss { | |
| weighted_smooth_l1 { | |
| } | |
| } | |
| hard_example_miner { | |
| num_hard_examples: 3000 | |
| iou_threshold: 0.99 | |
| loss_type: CLASSIFICATION | |
| max_negatives_per_positive: 3 | |
| min_negatives_per_image: 10 | |
| } | |
| classification_weight: 1.0 | |
| localization_weight: 1.0 | |
| } | |
| normalize_loss_by_num_matches: true | |
| post_processing { | |
| batch_non_max_suppression { | |
| score_threshold: 1e-8 | |
| iou_threshold: 0.5 | |
| max_detections_per_class: 100 | |
| max_total_detections: 100 | |
| } | |
| score_converter: SIGMOID | |
| } | |
| } | |
| } | |
| train_config: { | |
| fine_tune_checkpoint: "" | |
| num_steps: 10000000 | |
| batch_size: 32 | |
| data_augmentation_options { | |
| random_horizontal_flip { | |
| keypoint_flip_permutation: 1 | |
| keypoint_flip_permutation: 0 | |
| keypoint_flip_permutation: 2 | |
| keypoint_flip_permutation: 3 | |
| keypoint_flip_permutation: 5 | |
| keypoint_flip_permutation: 4 | |
| keypoint_flip_permutation: 6 | |
| keypoint_flip_permutation: 8 | |
| keypoint_flip_permutation: 7 | |
| keypoint_flip_permutation: 10 | |
| keypoint_flip_permutation: 9 | |
| keypoint_flip_permutation: 12 | |
| keypoint_flip_permutation: 11 | |
| keypoint_flip_permutation: 14 | |
| keypoint_flip_permutation: 13 | |
| keypoint_flip_permutation: 16 | |
| keypoint_flip_permutation: 15 | |
| keypoint_flip_permutation: 18 | |
| keypoint_flip_permutation: 17 | |
| keypoint_flip_permutation: 20 | |
| keypoint_flip_permutation: 19 | |
| keypoint_flip_permutation: 22 | |
| keypoint_flip_permutation: 21 | |
| } | |
| } | |
| data_augmentation_options { | |
| ssd_random_crop_fixed_aspect_ratio { | |
| } | |
| } | |
| optimizer { | |
| rms_prop_optimizer { | |
| learning_rate { | |
| exponential_decay_learning_rate { | |
| initial_learning_rate: 0.0004 | |
| decay_steps: 800720 | |
| decay_factor: 0.95 | |
| } | |
| } | |
| momentum_optimizer_value: 0.9 | |
| decay: 0.9 | |
| epsilon: 1.0 | |
| } | |
| } | |
| } | |
| train_input_reader { | |
| label_map_path: "PATH_TO_BE_CONFIGURED/face_person_with_keypoints_label_map.pbtxt" | |
| tf_record_input_reader { | |
| input_path: "PATH_TO_BE_CONFIGURED/faces_train.record-?????-of-00010" | |
| } | |
| num_keypoints: 23 | |
| } | |
| eval_config { | |
| num_visualizations: 10 | |
| metrics_set: "coco_detection_metrics" | |
| use_moving_averages: true | |
| parameterized_metric { | |
| coco_keypoint_metrics { | |
| class_label: "face" | |
| } | |
| } | |
| parameterized_metric { | |
| coco_keypoint_metrics { | |
| class_label: "PERSON" | |
| } | |
| } | |
| } | |
| eval_input_reader { | |
| label_map_path: "PATH_TO_BE_CONFIGURED/face_person_with_keypoints_label_map.pbtxt" | |
| shuffle: true | |
| num_epochs: 1 | |
| tf_record_input_reader { | |
| input_path: "PATH_TO_BE_CONFIGURED/faces_val.record-?????-of-00010" | |
| } | |
| num_keypoints: 23 | |
| } | |
| graph_rewriter { | |
| quantization { | |
| delay: 2000000 | |
| activation_bits: 8 | |
| weight_bits: 8 | |
| } | |
| } | |