tensorflow目标检测：RFCN模块'；sMAP@0.5价格很低
我使用tensorflow对象检测api（）来训练rfcn模型，使用voc 2007+2012 trainval数据集，并在voc 2007测试中进行测试。这个MAP@0.5与caffe版本相比要低得多。caffe版本训练110000次迭代，tensorflow版本训练140000次迭代。预训练的resnet-v1-50模块，用于初始化主干功能提取器。配置文件如下所示：tensorflow目标检测：RFCN模块'；sMAP@0.5价格很低,tensorflow,object-detection-api,Tensorflow,Object Detection Api,我使用tensorflow对象检测api（）来训练rfcn模型，使用voc 2007+2012 trainval数据集，并在voc 2007测试中进行测试。这个MAP@0.5与caffe版本相比要低得多。caffe版本训练110000次迭代，tensorflow版本训练140000次迭代。预训练的resnet-v1-50模块，用于初始化主干功能提取器。配置文件如下所示： #pascal_voc_resnet50_rfcn.config: model { faster_rcnn { n
#pascal_voc_resnet50_rfcn.config:
model {
faster_rcnn {
num_classes: 20
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 600
max_dimension: 1024
}
}
feature_extractor {
type: 'faster_rcnn_resnet50'
first_stage_features_stride: 16
}
first_stage_anchor_generator {
grid_anchor_generator {
scales: [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: 0.0005
}
}
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: 1.0
first_stage_objectness_loss_weight: 1.0
second_stage_box_predictor {
rfcn_box_predictor {
conv_hyperparams {
op: CONV
regularizer {
l2_regularizer {
weight: 0.0005
}
}
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: 0.7
max_detections_per_class: 100
max_total_detections: 300
}
score_converter: SOFTMAX
}
second_stage_localization_loss_weight: 1.0
second_stage_classification_loss_weight: 1.0
}
}
train_config: {
batch_size: 1
optimizer {
momentum_optimizer: {
learning_rate: {
manual_step_learning_rate {
initial_learning_rate: 0.001
schedule {
step: 0
learning_rate: .001
}
schedule {
step: 900000
learning_rate: .0001
}
schedule {
step: 1200000
learning_rate: .00001
}
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "resnet_v1_50/resnet_v1_50.ckpt"
from_detection_checkpoint: false
# 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: 1500000
data_augmentation_options {
random_horizontal_flip {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "voc_dataset/trainval.tfrecords"
}
label_map_path: "object_detection/data/pascal_label_map.pbtxt"
}
eval_config: {
# num_examples: 8000
num_examples: 4952
num_visualizations: 4952
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 1
visualization_export_dir: 'outputs_eval_imgs'
metrics_set: 'pascal_voc_metrics'
}
eval_input_reader: {
tf_record_input_reader {
input_path: "voc_dataset/test.tfrecords"
}
label_map_path: "object_detection/data/pascal_label_map.pbtxt"
shuffle: false
num_readers: 1
num_epochs: 1
}