如何解决低训练和验证损失,但Mapillary数据集上Faster R-CNN的mAP也很低
我是深度学习的新手,我正在使用Tensorflow 2对象检测API来微调Mapillary数据集上的Faster R-CNN模型(在COCO 2017数据集上进行了预训练)以检测道路标志。该数据集包含训练集中的36589张图像(带有180287个边界框)和验证集中的5320张图像(带有26101个边界框)。
但是我正在经历一种怪异的行为:训练和验证损失似乎正在收敛(我也在尝试不同的学习率),但是mAP仍然为0。
通过使用以下配置:
# Faster R-CNN with resnet-50 (v1)
# Trained on COCO,initialized from Imagenet classification checkpoint
# This config is TPU compatible.
model {
faster_rcnn {
num_classes: 314
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 1024
max_dimension: 1024
pad_to_max_dimension: true
}
}
feature_extractor {
type: 'faster_rcnn_resnet101_keras'
batch_norm_trainable: false #fine-tuning: false | from-scratch: true
}
first_stage_anchor_generator {
grid_anchor_generator {
scales: [0.25,0.5,1.0,2.0]
aspect_ratios: [0.5,2.0]
height_stride: 16
width_stride: 16
}
}
first_stage_Box_predictor_conv_hyperparams {
op: CONV
regularizer {
l2_regularizer {
weight: 0.0 #no regularization?
}
}
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 #no regularization?
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
share_Box_across_classes: false #it should'nt be needed in this case since a Box has only one class
}
}
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 #applies softmax on input detection scores
}
second_stage_localization_loss_weight: 2.0
second_stage_classification_loss_weight: 1.0
use_static_shapes: true
use_matmul_crop_and_resize: true
clip_anchors_to_image: true
use_static_balanced_label_sampler: true
use_matmul_gather_in_matcher: true
}
}
train_config: {
batch_size: 1
sync_replicas: true
startup_delay_steps: 0
replicas_to_aggregate: 8
num_steps: 10000
optimizer {
momentum_optimizer: {
learning_rate: {
cosine_decay_learning_rate {
learning_rate_base: .0000004
total_steps: 10000
warmup_learning_rate: .000000133
warmup_steps: 2000
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
add_regularization_loss: true
fine_tune_checkpoint_version: V2
fine_tune_checkpoint: "pretrained-model/faster_rcnn_resnet101_v1_1024x1024_coco17_tpu-8/checkpoint/ckpt-0"
fine_tune_checkpoint_type: "detection"
# data_augmentation_options {
# random_horizontal_flip {
# }
# }
# data_augmentation_options {
# random_adjust_hue {
# }
# }
# data_augmentation_options {
# random_adjust_contrast {
# }
# }
# data_augmentation_options {
# random_adjust_saturation {
# }
# }
# data_augmentation_options {
# random_square_crop_by_scale {
# scale_min: 0.6
# scale_max: 1.3
# }
# }
#merge_multiple_label_Boxes: false
max_number_of_Boxes: 206388 #this is the total number considering the entire dataset
unpad_groundtruth_tensors: false
use_bfloat16: false # works only on TPUs
}
train_input_reader: {
label_map_path: "data/training/label_map.pbtxt"
tf_record_input_reader {
input_path: "data/training/train.tfrecord"
}
}
eval_config: {
min_score_threshold: 0.5
batch_size: 1
#num_examples: 100
num_visualizations: 10
metrics_set: "pascal_voc_detection_metrics"
use_moving_averages: false
eval_interval_secs: 30
#max_evals: 10
include_metrics_per_category: true
}
eval_input_reader: {
label_map_path: "data/validation/label_map.pbtxt"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "data/validation/train.tfrecord"
}
}
我得到以下结果:
但所有mAP均为0(总计和每个类别)。
通过将学习率基数更改为.00000004并将预热学习率更改为.0000000133,将batch_size更改为8并将num_steps更改为50000,我得到以下结果(仍在训练中):
按类别划分的性能全为0,但总体mAP似乎开始有所提高,但仍然很低:
我认为此行为可能是由某些错误的超参数引起的。我应该在配置文件中更改一些内容吗?您还认为两者之间最好的配置是什么?
注意:在使用整个数据集之前,我在非常小型数据集(具有较高的学习率)上训练了模型,并通过使用相同的数据集来评估模型,该模型表现良好(但可能太适合了)。打开整个数据集会导致这种奇怪的行为。
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。