tensorflow中更快的rcnn配置文件
我正在使用tensorflow中的Google对自定义数据集进行训练和推断 我想调整配置文件的参数,以更好地适应我的样本(例如,区域提案的数量、ROI bbox的大小等)。 为此,我需要知道每个参数的作用。 遗憾的是,配置文件(找到的)没有注释或解释。 有些,如“num类”是不言自明的,但有些则很棘手 我发现有更多的评论,但无法将其“翻译”为我的格式 我想知道以下情况之一: 1.谷歌API配置文件的每个参数说明 或 2. '从官方更快的rcnn到谷歌API配置的翻译 或者至少 3.通过参数的技术细节对更快的rcnn进行全面审查(官方文章没有提供所有细节) 谢谢你的帮助 配置文件的示例:tensorflow中更快的rcnn配置文件,tensorflow,deep-learning,config,conv-neural-network,object-detection,Tensorflow,Deep Learning,Config,Conv Neural Network,Object Detection,我正在使用tensorflow中的Google对自定义数据集进行训练和推断 我想调整配置文件的参数,以更好地适应我的样本(例如,区域提案的数量、ROI bbox的大小等)。 为此,我需要知道每个参数的作用。 遗憾的是,配置文件(找到的)没有注释或解释。 有些,如“num类”是不言自明的,但有些则很棘手 我发现有更多的评论,但无法将其“翻译”为我的格式 我想知道以下情况之一: 1.谷歌API配置文件的每个参数说明 或 2. '从官方更快的rcnn到谷歌API配置的翻译 或者至少 3.通过参数的技术
# Faster R-CNN with Resnet-101 (v1) configuration for MSCOCO 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: 90
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
initial_crop_size: 14
maxpool_kernel_size: 2
maxpool_stride: 2
second_stage_box_predictor {
mask_rcnn_box_predictor {
use_dropout: false
dropout_keep_probability: 1.0
fc_hyperparams {
op: FC
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
}
}
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: 0
learning_rate: .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
# 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/mscoco_train.record"
}
label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
}
eval_config: {
num_examples: 8000
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 10
}
eval_input_reader: {
tf_record_input_reader {
input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"
}
label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
shuffle: false
num_readers: 1
num_epochs: 1
}
我发现了两个关于配置文件的来源: 1.tensorflow github中的文件夹涵盖了所有配置选项,并对每个选项进行了一些注释。对于最常见的问题,您应该更快地签出\u rcnn.proto、eval.proto和train.proto 2.Algorithmia的博客文章全面涵盖了在谷歌的开放图像数据集上下载、准备和训练更快的RCNN的所有步骤。通过2/3,对配置选项进行了一些讨论