1.搭建faster_rcnn_inception_resnet_v2_atrous_lowproposals_coco时遇到的问题
(1)没有同名配置文件问题
解决办法:
从models/research/object_detection/samples/config下复制faster_rcnn_inception_resnet_v2_atrous_coco.config,参考已下载的预训练权重中的pipeline.config,对配置文件进行参数修改。以下即为修改后的配置文件:
# Faster R-CNN with Inception Resnet v2, Atrous version;
# Configured 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: 1
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 600
max_dimension: 1024
}
}
feature_extractor {
type: 'faster_rcnn_inception_resnet_v2'
first_stage_features_stride: 8
}
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: 8
width_stride: 8
}
}
first_stage_atrous_rate: 2
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: 20
first_stage_localization_loss_weight: 2.0
first_stage_objectness_loss_weight: 1.0
initial_crop_size: 17
maxpool_kernel_size: 1
maxpool_stride: 1
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: 0.3
iou_threshold: 0.6
max_detections_per_class: 20
max_total_detections: 20
}
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: "pretrained/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: "train.record"
}
label_map_path: "label_map.pbtxt"
}
eval_config: {
num_examples: 180
# 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: "test.record"
}
label_map_path: "label_map.pbtxt"
shuffle: false
num_readers: 1
}
(2)值异常报错ValueError: second_stage_batch_size should be no greater than first_stage_max_proposals.
解决办法:(second_stage_batch_size默认大小64)
如下图所示,在(1)的配置文件“second_stage_classification_loss_weight:1.0”之后显式添加“second_stage_batch_size: x”,然后修改first_stage_max_proposals的值即可。(first_stage_max_proposals必须≥second_stage_batch_size)
2、搭建ssd_resnet_50_fpn_coco、ssd——mobilenet_v1_fpn时遇到的问题
(1)训练时报错ValueError: No variables to save
解决办法:
如下图所示,在相应配置文件fine_tune_checkpoint: "pretrained/model.ckpt"后边添加以下行(参考文件在object_detection/legency/tyrainer.py中,true为检测问题,flase为分类问题):
from_detection_checkpoint: true(或者fine_tune_checkpoint_type: "detection"都可以,性质一样)
(2)训练时训练若干步之后报错停止,提示内存错误
解决办法:
将配置文件中的batch_size调小