You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
136 lines
3.5 KiB
136 lines
3.5 KiB
# R-FCN with Resnet-101 (v1), configured for Oxford-IIIT Pets Dataset.
|
|
# Users should configure the fine_tune_checkpoint field in the train config as
|
|
# well as the label_map_path and input_path fields in the train_input_reader and
|
|
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
|
|
# should be configured.
|
|
|
|
model {
|
|
faster_rcnn {
|
|
num_classes: 37
|
|
image_resizer {
|
|
keep_aspect_ratio_resizer {
|
|
min_dimension: 600
|
|
max_dimension: 1024
|
|
}
|
|
}
|
|
feature_extractor {
|
|
type: 'faster_rcnn_resnet101'
|
|
first_stage_features_stride: 16
|
|
}
|
|
first_stage_anchor_generator {
|
|
grid_anchor_generator {
|
|
scales: [0.25, 0.5, 1.0, 2.0]
|
|
aspect_ratios: [0.5, 1.0, 2.0]
|
|
height_stride: 16
|
|
width_stride: 16
|
|
}
|
|
}
|
|
first_stage_box_predictor_conv_hyperparams {
|
|
op: CONV
|
|
regularizer {
|
|
l2_regularizer {
|
|
weight: 0.0
|
|
}
|
|
}
|
|
initializer {
|
|
truncated_normal_initializer {
|
|
stddev: 0.01
|
|
}
|
|
}
|
|
}
|
|
first_stage_nms_score_threshold: 0.0
|
|
first_stage_nms_iou_threshold: 0.7
|
|
first_stage_max_proposals: 300
|
|
first_stage_localization_loss_weight: 2.0
|
|
first_stage_objectness_loss_weight: 1.0
|
|
second_stage_box_predictor {
|
|
rfcn_box_predictor {
|
|
conv_hyperparams {
|
|
op: CONV
|
|
regularizer {
|
|
l2_regularizer {
|
|
weight: 0.0
|
|
}
|
|
}
|
|
initializer {
|
|
truncated_normal_initializer {
|
|
stddev: 0.01
|
|
}
|
|
}
|
|
}
|
|
crop_height: 18
|
|
crop_width: 18
|
|
num_spatial_bins_height: 3
|
|
num_spatial_bins_width: 3
|
|
}
|
|
}
|
|
second_stage_post_processing {
|
|
batch_non_max_suppression {
|
|
score_threshold: 0.0
|
|
iou_threshold: 0.6
|
|
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
|
|
}
|
|
}
|
|
|
|
train_config: {
|
|
batch_size: 1
|
|
optimizer {
|
|
momentum_optimizer: {
|
|
learning_rate: {
|
|
manual_step_learning_rate {
|
|
initial_learning_rate: 0.0003
|
|
schedule {
|
|
step: 900000
|
|
learning_rate: .00003
|
|
}
|
|
schedule {
|
|
step: 1200000
|
|
learning_rate: .000003
|
|
}
|
|
}
|
|
}
|
|
momentum_optimizer_value: 0.9
|
|
}
|
|
use_moving_average: false
|
|
}
|
|
gradient_clipping_by_norm: 10.0
|
|
fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
|
|
from_detection_checkpoint: true
|
|
load_all_detection_checkpoint_vars: true
|
|
# Note: The below line limits the training process to 200K steps, which we
|
|
# empirically found to be sufficient enough to train the pets dataset. This
|
|
# effectively bypasses the learning rate schedule (the learning rate will
|
|
# never decay). Remove the below line to train indefinitely.
|
|
num_steps: 200000
|
|
data_augmentation_options {
|
|
random_horizontal_flip {
|
|
}
|
|
}
|
|
}
|
|
|
|
train_input_reader: {
|
|
tf_record_input_reader {
|
|
input_path: "PATH_TO_BE_CONFIGURED/pet_faces_train.record-?????-of-00010"
|
|
}
|
|
label_map_path: "PATH_TO_BE_CONFIGURED/pet_label_map.pbtxt"
|
|
}
|
|
|
|
eval_config: {
|
|
metrics_set: "coco_detection_metrics"
|
|
num_examples: 1101
|
|
}
|
|
|
|
eval_input_reader: {
|
|
tf_record_input_reader {
|
|
input_path: "PATH_TO_BE_CONFIGURED/pet_faces_val.record-?????-of-00010"
|
|
}
|
|
label_map_path: "PATH_TO_BE_CONFIGURED/pet_label_map.pbtxt"
|
|
shuffle: false
|
|
num_readers: 1
|
|
}
|