如何解决如何使用TF1在TensorFlow对象检测API中正确还原检查点?
我正在对COCO 2017数据集上的SSD-MobileNetV3 Large和SSD-MobileDet-CPU进行微调,但只有书籍类。我为此创建了一个新的数据集并检查了该数据集,它很好。我还根据自己的需要修改了配置文件。当我开始训练时,它只是忽略配置文件中提供的“ fine_tune_checkpoint”,并从头开始。但是,如果我执行相同的过程,但是在'model_dir'目录中使用了检查点,它将尝试还原它,但是由于我使用的类数不同,因此会出现错误。如何使培训过程正确还原检查点?我还尝试了所有90个类的普通COCO数据集,当我开始训练时,'fine_tune_checkpoint'被忽略,但是如果将检查点放在'model_dir'中,它将被正确还原。
我的配置文件如下。
# SSDLite with MobileDet-CPU feature extractor.
# Reference: Xiong & Liu et al.,https://arxiv.org/abs/2004.14525
# Trained on COCO,initialized from scratch.
#
# 0.45B MulAdds,4.21M Parameters. Latency is 113ms on Pixel 1 CPU.
# Achieves 24.0 mAP on COCO14 minival dataset.
# Achieves 23.5 mAP on COCO17 val dataset.
#
# This config is TPU compatible.
model {
ssd {
inplace_batchnorm_update: true
freeze_batchnorm: false
num_classes: 1
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}
}
matcher {
argmax_matcher {
matched_threshold: 0.5
unmatched_threshold: 0.5
ignore_thresholds: false
negatives_lower_than_unmatched: true
force_match_for_each_row: true
use_matmul_gather: true
}
}
similarity_calculator {
iou_similarity {
}
}
encode_background_as_zeros: true
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.2
max_scale: 0.95
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.3333
}
}
image_resizer {
fixed_shape_resizer {
height: 320
width: 320
}
}
box_predictor {
convolutional_box_predictor {
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.8
kernel_size: 3
use_depthwise: true
box_code_size: 4
apply_sigmoid_to_scores: false
class_prediction_bias_init: -4.6
conv_hyperparams {
activation: RELU_6,regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
random_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,scale: true,center: true,decay: 0.97,epsilon: 0.001,}
}
}
}
feature_extractor {
type: 'ssd_mobiledet_cpu'
min_depth: 16
depth_multiplier: 1.0
use_depthwise: true
conv_hyperparams {
activation: RELU_6,regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,}
}
override_base_feature_extractor_hyperparams: false
}
loss {
classification_loss {
weighted_sigmoid_focal {
alpha: 0.75,gamma: 2.0
}
}
localization_loss {
weighted_smooth_l1 {
delta: 1.0
}
}
classification_weight: 1.0
localization_weight: 1.0
}
normalize_loss_by_num_matches: true
normalize_loc_loss_by_codesize: true
post_processing {
batch_non_max_suppression {
score_threshold: 1e-8
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
use_static_shapes: true
}
score_converter: SIGMOID
}
}
}
train_config: {
batch_size: 64
sync_replicas: true
startup_delay_steps: 0
replicas_to_aggregate: 1
num_steps: 800000
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
optimizer {
momentum_optimizer: {
learning_rate: {
cosine_decay_learning_rate {
learning_rate_base: 0.8
total_steps: 800000
warmup_learning_rate: 0.13333
warmup_steps: 100
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
fine_tune_checkpoint: "./checkpoints/model.ckpt-400000"
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
fine_tune_checkpoint_type: "detection"
fine_tune_checkpoint_version: V1
load_all_detection_checkpoint_vars: true
}
train_input_reader: {
tf_record_input_reader {
input_path: "./tf_record_coco_books/coco_train.record"
}
label_map_path: "./tf_record_coco_books/label_map.pbtxt"
}
eval_config: {
metrics_set: "coco_detection_metrics"
use_moving_averages: false
}
eval_input_reader: {
tf_record_input_reader {
input_path: "./tf_record_coco_books/coco_val.record"
}
label_map_path: "./tf_record_coco_books/label_map.pbtxt"
shuffle: false
num_readers: 1
}
解决方法
您必须指定一个 model_dir ,该目录与要加载先前训练过的检查点的目录不同。
在培训的一开始,Tensorflow对象检测API培训脚本(当前的 model_main 或 legacy / train )将创建一个与之对应的新检查点。您的 model_dir 中的新配置,然后在此检查点进行训练。如果您的目录已经包含预先训练的检查点,则确实会引发与类数相对应的问题。
如果这不起作用,您还可以在配置文件中更改字段:
fine_tune_checkpoint_type = "detection"
至:
fine_tune_checkpoint_type = "fine_tune"
关于这是对象检测API上的当前问题:https://github.com/tensorflow/models/issues/8892#issuecomment-680207038
,问题出自model_lib.py中的第446行
load_pretrained = hparams.load_pretrained if hparams else False;
因为先前的提交之一将hparams更改为None,所以load_pretrained始终为False。将其设置为True,然后重新安装object_detection库即可解决此问题。
我在相关的github问题中提到了这一点: https://github.com/tensorflow/models/issues/9284
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。