现在我正在训练ssd_mobilenet_v2 net从零开始检测汽车牌照。我的损失图在300κ步后看起来像对数轴视图中的巨大锯齿，最大值在5e+11。最低的最低值是130，然后我又得到了一个巨大的峰值，7e+11。还好吗，还是我遇到了一些问题，我的训练过程永远不会以良好的准确性结束？
https://ibb.co/wCwTwLp锯齿
这是管道。配置文件内容
model {
ssd {
num_classes: 1
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
feature_extractor {
type: "ssd_mobilenet_v2_keras"
depth_multiplier: 1.0
min_depth: 16
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 3.9999998989515007e-05
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.029999999329447746
}
}
activation: RELU_6
batch_norm {
decay: 0.9700000286102295
center: true
scale: true
epsilon: 0.0010000000474974513
train: true
}
}
override_base_feature_extractor_hyperparams: true
}
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 {
}
}
box_predictor {
convolutional_box_predictor {
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 3.9999998989515007e-05
}
}
initializer {
random_normal_initializer {
mean: 0.0
stddev: 0.009999999776482582
}
}
activation: RELU_6
batch_norm {
decay: 0.9700000286102295
center: true
scale: true
epsilon: 0.0010000000474974513
train: true
}
}
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.800000011920929
kernel_size: 1
box_code_size: 4
apply_sigmoid_to_scores: false
class_prediction_bias_init: -4.599999904632568
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.1000000298023224
max_scale: 0.549999988079071
aspect_ratios: 1.0
aspect_ratios: 1.0
aspect_ratios: 0.5
aspect_ratios: 1.0
aspect_ratios: 0.33329999446868896
}
}
post_processing {
batch_non_max_suppression {
score_threshold: 9.99999993922529e-09
iou_threshold: 0.6000000238418579
max_detections_per_class: 100
max_total_detections: 100
use_static_shapes: false
}
score_converter: SIGMOID
}
normalize_loss_by_num_matches: true
loss {
localization_loss {
weighted_smooth_l1 {
delta: 1.0
}
}
classification_loss {
weighted_sigmoid_focal {
gamma: 2.0
alpha: 0.75
}
}
classification_weight: 1.0
localization_weight: 1.0
}
encode_background_as_zeros: true
normalize_loc_loss_by_codesize: true
inplace_batchnorm_update: true
freeze_batchnorm: false
}
}
train_config {
batch_size: 24
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
sync_replicas: true
optimizer {
momentum_optimizer {
learning_rate {
cosine_decay_learning_rate {
learning_rate_base: 0.800000011920929
total_steps: 1000000
warmup_learning_rate: 0.13333000242710114
warmup_steps: 2000
}
}
momentum_optimizer_value: 0.8999999761581421
}
use_moving_average: false
}
#fine_tune_checkpoint: "modelsmy_ssd_mobilenet_V2_300ckpt-51"
num_steps: 1000000
startup_delay_steps: 0.0
replicas_to_aggregate: 8
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
fine_tune_checkpoint_type: "detection"
use_bfloat16: false
fine_tune_checkpoint_version: V2
}
train_input_reader {
label_map_path: "annotationslabelmap.pbtxt"
tf_record_input_reader {
input_path: "annotations/train.record"
}
}
eval_config {
metrics_set: "coco_detection_metrics"
use_moving_averages: false
}
eval_input_reader {
label_map_path: "annotationslabelmap.pbtxt"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "annotations/test.record"
}
}
将learning_rate_base参数更改为0.08，将warmup_learning_rate更改为.013。这些参数配置错误。这是TensorFlow(10509(的一个已知且最近解决的问题。