我在以下教程的帮助下使用 Tensoflow 对象检测 API 创建树检测器：https ://www.youtube.com/watch?v=a1br6gW-8Ss
我的问题是模型过度拟合了训练集。我怎样才能避免它？我的训练集由 130 张图像组成，图像中平均标记了 4 棵树。共有7种。我使用的模型是：在 COCO 数据集上预训练的“Faster R-CNN ResNet50 V1 640x640”..（链接如下） https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/ tf2_detection_zoo.md 在教程中使用以下模型“EfficientDet D0 512x512”，但该模型也过拟合了我的数据集，所以我尝试使用“Faster R-CNN ResNet50 V1 640x640”。
我用来减少过拟合的技术是
- 辍学（率=0.675）
- 数据增强（random_crop）
- 低学习率（learning_rate_base: .008 , total_steps: 25000 .warmup_learning_rate: .0001）
- 原始图像尺寸为 860x860，我将它们调整为 tp 640x640 并在 xml 中更改了边界框坐标。
我应该在模型配置中添加或更改什么以避免过度拟合？
这是我的模型配置文件：
# Faster R-CNN with Resnet-50 (v1) with 640x640 input resolution
# Trained on COCO, initialized from Imagenet classification checkpoint
#
# Train on TPU-8
#
# Achieves 29.3 mAP on COCO17 Val
model {
faster_rcnn {
num_classes: 7
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 640
max_dimension: 640
pad_to_max_dimension: true
}
}
feature_extractor {
type: 'faster_rcnn_resnet50_keras'
batch_norm_trainable: true
}
first_stage_anchor_generator {
grid_anchor_generator {
scales: [0.25, 0.5, 1.0, 2.0]
aspect_ratios: [0.5, 1.0, 1.5, 2.0, 2.5, 3.0, 3.5]
height_stride: 8
width_stride: 8
}
}
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: true
dropout_keep_probability: 0.675
fc_hyperparams {
op: FC
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
share_box_across_classes: true
}
}
second_stage_post_processing {
batch_non_max_suppression {
score_threshold: 0.2
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
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: 4
sync_replicas: true
startup_delay_steps: 0
replicas_to_aggregate: 8
num_steps: 25000
optimizer {
momentum_optimizer: {
learning_rate: {
cosine_decay_learning_rate {
learning_rate_base: .008
total_steps: 25000
warmup_learning_rate: .0001
warmup_steps: 2000
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
fine_tune_checkpoint_version: V2
fine_tune_checkpoint: "faster_rcnn_resnet50_v1_640x640_coco17_tpu-8/checkpoint/ckpt-0"
fine_tune_checkpoint_type: "detection"
data_augmentation_options {
random_crop_image {
min_object_covered: 0.0
min_aspect_ratio: 0.75
max_aspect_ratio: 3.0
min_area: 0.75
max_area: 1.0
overlap_thresh: 0.0
}
}
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
use_bfloat16: true # works only on TPUs
}
train_input_reader: {
label_map_path: "images/labelmap.pbtxt"
tf_record_input_reader {
input_path: "train.record"
}
}
eval_config: {
metrics_set: "coco_detection_metrics"
use_moving_averages: false
batch_size: 1;
}
eval_input_reader: {
label_map_path: "images/labelmap.pbtxt"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "test.record"
}
}