[英]Configure Fast-Rcnn.config to use Adam optimizer and other parameters
I have following fast_rcnn_resnet101_coco.config ( here ). 我关注了fast_rcnn_resnet101_coco.config( 这里 )。 In this config file I have replaced momentum_optimizer with adam optimizer as follows:
在此配置文件中,我已使用adam优化器替换了momentum_optimizer,如下所示:
train_config: {
batch_size: 1
optimizer {
#momentum_optimizer: {
adam_optimizer: {
learning_rate: {
manual_step_learning_rate {
initial_learning_rate: 0.00001
schedule {
step: 4500
learning_rate: .00001
}
schedule {
step: 10000
learning_rate: .000001
}
}
}
#momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "faster_rcnn_resnet101_coco_2018_01_28/model.ckpt"
from_detection_checkpoint: true
data_augmentation_options {
random_horizontal_flip {
}
}
}
I have referred Tensorflow Object Detection: use Adam instead of RMSProp to do this change. 我已经提到了Tensorflow对象检测:使用Adam而不是RMSProp来进行此更改。 My aim is to configure my faster rcnnresnet101.config file ( attached here ) to match that of this file:
我的目标是配置我的更快的rcnnresnet101.config文件( 在此处附加 )以匹配此文件的文件:
My aim is that my .config file should have all the parameters mentioned in the .yaml file. 我的目标是我的.config文件应该包含.yaml文件中提到的所有参数。 So far I have succeed in doing this only for one parameter ("learning rate").
到目前为止,我已经成功地只为一个参数(“学习率”)这样做。 How can I integrate rpn_batch size, step size etc. parameters in my config file ?
如何在配置文件中集成rpn_batch大小,步长等参数?
The basic fact you need to understand is the following : 您需要了解的基本事实如下:
The config file is must match the message TrainEvalPipelineConfig . 配置文件必须与消息TrainEvalPipelineConfig匹配。 Now that message consists of multiple components.
现在该消息由多个组件组成。 So, if you want to modify something in a component, you should go to the proto file in which that component message is defined, see the possible parameters therein and then modify the configuration file according to that.
因此,如果要修改组件中的某些内容,则应该转到定义该组件消息的proto文件,查看其中的可能参数,然后根据该文件修改配置文件。 That is exactly what you ultimately did in order to change the optimizer.
这正是您最终为更改优化程序所做的工作。
To give you a hint, if you want to change the RPN batch size, you have to modify this parameter . 要给出提示,如果要更改RPN批处理大小,则必须修改此参数 。 So, look it up in the proto file and simply add it to your final configuration file.
因此,在proto文件中查找它,只需将其添加到最终配置文件中即可。
To give you an illustration, if I were to use the original configuration file with one minor change which is a RPN batch size of 128, my configuration file will appear as follows : 为了举例说明,如果我使用原始配置文件进行一次微小更改(RPN批量大小为128),我的配置文件将显示如下:
# 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
# below i modify the RPN batch size to 128
first_stage_minibatch_size: 128
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: 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
data_augmentation_options {
random_horizontal_flip {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record-?????-of-00100"
}
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-?????-of-00010"
}
label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
shuffle: false
num_readers: 1
}
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.