File size: 3,995 Bytes
759e5fd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 |
# Context R-CNN unit test configuration using sequence example sample data with
# context_features created from the Snapshot Serengeti Dataset and stored in
# snapshot_serengeti_sequence_examples.record.
# This model uses attention into contextual features within the Faster R-CNN
# object detection framework to improve object detection performance.
# See https://arxiv.org/abs/1912.03538 for more information.
model {
faster_rcnn {
num_classes: 48
image_resizer {
fixed_shape_resizer {
height: 640
width: 640
}
}
feature_extractor {
type: "faster_rcnn_resnet101"
first_stage_features_stride: 16
batch_norm_trainable: true
}
first_stage_anchor_generator {
grid_anchor_generator {
height_stride: 16
width_stride: 16
scales: 0.25
scales: 0.5
scales: 1.0
scales: 2.0
aspect_ratios: 0.5
aspect_ratios: 1.0
aspect_ratios: 2.0
}
}
first_stage_box_predictor_conv_hyperparams {
op: CONV
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
truncated_normal_initializer {
stddev: 0.00999999977648
}
}
}
first_stage_nms_score_threshold: 0.0
first_stage_nms_iou_threshold: 0.699999988079
first_stage_max_proposals: 300
first_stage_localization_loss_weight: 2.0
first_stage_objectness_loss_weight: 1.0
initial_crop_size: 14
maxpool_kernel_size: 2
maxpool_stride: 2
second_stage_box_predictor {
mask_rcnn_box_predictor {
fc_hyperparams {
op: FC
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
use_dropout: false
dropout_keep_probability: 1.0
share_box_across_classes: true
}
}
second_stage_post_processing {
batch_non_max_suppression {
score_threshold: 0.0
iou_threshold: 0.600000023842
max_detections_per_class: 100
max_total_detections: 300
}
score_converter: SOFTMAX
}
second_stage_localization_loss_weight: 2.0
second_stage_classification_loss_weight: 1.0
use_matmul_crop_and_resize: true
clip_anchors_to_image: true
use_matmul_gather_in_matcher: true
use_static_balanced_label_sampler: true
use_static_shapes: true
context_config {
max_num_context_features: 2000
context_feature_length: 2057
}
}
}
train_config {
batch_size: 1
data_augmentation_options {
random_horizontal_flip {
}
}
sync_replicas: true
optimizer {
momentum_optimizer {
learning_rate {
manual_step_learning_rate {
initial_learning_rate: 0.0
schedule {
step: 2000
learning_rate: 0.00200000009499
}
schedule {
step: 200000
learning_rate: 0.000199999994948
}
schedule {
step: 300000
learning_rate: 1.99999994948e-05
}
warmup: true
}
}
momentum_optimizer_value: 0.899999976158
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
num_steps: 500000
replicas_to_aggregate: 8
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
}
train_input_reader {
label_map_path: ""
tf_record_input_reader {
input_path: ""
}
load_context_features: true
input_type: TF_SEQUENCE_EXAMPLE
}
eval_config {
max_evals: 50
metrics_set: "coco_detection_metrics"
use_moving_averages: false
batch_size: 1
}
eval_input_reader {
label_map_path: ""
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: ""
}
load_context_features: true
input_type: TF_SEQUENCE_EXAMPLE
}
|