tensorflow - 使用 tensorflow 的 OD API 时评估结果低
问题描述
我正在尝试使用 tf1.4 OD API 创建用于检测车牌的检测模型。经过前几个评估检查点后,我开始认为我一定是做错了什么,因为结果都是否定的o_0
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = -1.000
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = -1.000
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = -1.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
现在我以前使用相同的管道进行过培训,但这是我第一次在单个课程上进行培训,也许我错过了一些重要的事情?这是管道:
model {
ssd {
num_classes: 1
image_resizer {
fixed_shape_resizer {
height: 320
width: 320
}
}
feature_extractor {
type: "ssd_mobiledet_edgetpu"
depth_multiplier: 1.0
min_depth: 16
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 4e-05
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.03
}
}
activation: RELU_6
batch_norm {
decay: 0.97
center: true
scale: true
epsilon: 0.001
train: true
}
}
use_depthwise: true
override_base_feature_extractor_hyperparams: false
}
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: 4e-05
}
}
initializer {
random_normal_initializer {
mean: 0.0
stddev: 0.03
}
}
activation: RELU_6
batch_norm {
decay: 0.97
center: true
scale: true
epsilon: 0.001
train: true
}
}
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.8
kernel_size: 3
box_code_size: 4
apply_sigmoid_to_scores: false
class_prediction_bias_init: -4.6
use_depthwise: true
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.2
max_scale: 0.95
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.3333
}
}
post_processing {
batch_non_max_suppression {
score_threshold: 1e-08
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
use_static_shapes: true
}
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: 32
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: 0.8
total_steps: 400000
warmup_learning_rate: 0.13333
warmup_steps: 2000
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
fine_tune_checkpoint: "/content/pretrained_model/ssdlite_mobiledet_edgetpu_320x320_coco_2020_05_19/ft32/model.ckpt"
num_steps: 5000
startup_delay_steps: 0.0
replicas_to_aggregate: 32
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
}
train_input_reader {
label_map_path: "/content/dataset/label_map.pbtxt"
tf_record_input_reader {
input_path: "/content/dataset/train.record"
}
}
eval_config {
num_examples: 51
metrics_set: "coco_detection_metrics"
use_moving_averages: false
}
eval_input_reader {
label_map_path: "/content/dataset/label_map.pbtxt"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "/content/dataset/test.record"
}
}
graph_rewriter {
quantization {
delay: 0
weight_bits: 8
activation_bits: 8
}
}
解决方案
我想从这个模型中检测到的类是车牌。我使用的数据集将对象标记为licence
. 这是我手动创建的 label_map.pbtxt....
%%file /content/dataset/label_map.pbtxt
item {
id: 1
name: 'license'
}
不同之处在于s
拼写c
错误的数据集中 - 应该是licence
,不是license
。
推荐阅读
- reactjs - 反应本机内存泄漏反应本机手势处理程序
- lua - 将“local i = 1”作为单行放入lua终端有什么用处?
- saas - SAAS 用户自定义域功能的正确结构
- excel - 突出显示值前后有空格的单元格
- c++ - 从 shared_ptr 获取原始指针以将其传递给需要原始的函数
- php - 如何将三个不同的 JSON 文件合并为一个 JSON?
- javascript - BrowserslistError:未知浏览器查询`heroku create $YOUR_APP_NAME --region eudefaults`
- xamarin - Xamarin Essentials 电子邮件附件
- node.js - 将反应表中不同行中的两个不同数值数据相乘
- web-crawler - 如何在 StormCrawler 中将 URL 作为文本文件播种?