我正在尝试使用 Tensorflow 2.0 对象检测来训练更快的 r-cnn 模型，但是我在 0.01 时得到了极低的 mAP。
我查看了 Tensorboard 中的训练图像，但训练图像看起来没有正确加载，或者我在配置文件中做错了什么。. 我正在学习使用 Hardhat 示例数据集的 RoboFlow 教程。这是我的 colab 笔记本（https://colab.research.google.com/drive/1cjHpLYq8NAEce36mJGGg0Lec31wSdtF9?usp=sharing）。
上图显示了已在 Tensorboard 中加载的训练数据集中使用的图像，下图是原始图像。
我对此完全陌生，我不确定我哪里出错了。下面是我正在使用的配置文件。
model {
faster_rcnn {
num_classes: 3
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 640
max_dimension: 640
pad_to_max_dimension: true
}
}
feature_extractor {
type: 'faster_rcnn_resnet101_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, 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
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
}
}
}
share_box_across_classes: true
}
}
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
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: 2000
optimizer {
momentum_optimizer: {
learning_rate: {
cosine_decay_learning_rate {
learning_rate_base: .04
total_steps: 25000
warmup_learning_rate: .013333
warmup_steps: 2000
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
fine_tune_checkpoint_version: V2
fine_tune_checkpoint: "/content/models/research/deploy/faster_rcnn_resnet101_v1_640x640_coco17_tpu-8/checkpoint/ckpt-0"
fine_tune_checkpoint_type: "detection"
data_augmentation_options {
random_horizontal_flip {
}
}
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
use_bfloat16: true # works only on TPUs
}
train_input_reader: {
label_map_path: "/content/train/Workers_label_map.pbtxt"
tf_record_input_reader {
input_path: "/content/train/Workers.tfrecord"
}
}
eval_config: {
metrics_set: "coco_detection_metrics"
use_moving_averages: false
batch_size: 1;
}
eval_input_reader: {
label_map_path: "/content/train/Workers_label_map.pbtxt"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "/content/valid/Workers.tfrecord"
}
}
先感谢您 ！