我在mobilenet V2配置中使用tensorflow-object-detection默认参数来训练VOC0712数据集,测试VOC2007测试数据集,地图非常低只有65%,有什么建议可以提高地图值?
以下是同样的问题,但没有解决方案。 https://github.com/tensorflow/models/issues/1735,
我想感谢您提供有关改善地图的任何培训建议。
对不起,这是我的错。这是我使用tensorflow-Object-detection的ssd_litemobilenet_v2模型在VOC0712的trainval数据集上训练的损失和地图值,然后在VOC2007的测试数据集上进行测试。
效果不如论文中那么好。有没有更好的方法来改善地图?感谢。
# SSDLite with Mobilenet v2 configuration for MSCOCO Dataset.
model {
ssd {
num_classes: 20
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
}
}
similarity_calculator {
iou_similarity {
}
}
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
}
}
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
box_predictor {
convolutional_box_predictor {
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.8
kernel_size: 3
use_depthwise: true
box_code_size: 4
apply_sigmoid_to_scores: false
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
}
feature_extractor {
type: 'ssd_mobilenet_v2'
min_depth: 16
depth_multiplier: 1.0
use_depthwise: true
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
loss {
classification_loss {
weighted_sigmoid {
}
}
localization_loss {
weighted_smooth_l1 {
}
}
hard_example_miner {
num_hard_examples: 3000
iou_threshold: 0.99
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 3
}
classification_weight: 1.0
localization_weight: 1.0
}
normalize_loss_by_num_matches: true
post_processing {
batch_non_max_suppression {
score_threshold: 1e-8
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SIGMOID
}
}
}
train_config: {
batch_size: 24
optimizer {
rms_prop_optimizer: {
learning_rate: {
exponential_decay_learning_rate {
initial_learning_rate: 0.004
decay_steps: 800720
decay_factor: 0.95
}
}
momentum_optimizer_value: 0.9
decay: 0.9
epsilon: 1.0
}
}
fine_tune_checkpoint: "./object_detection/mine/ssdlite_mobilenet_v2/model.ckpt"
fine_tune_checkpoint_type: "detection"
num_steps: 300000
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "./object_detection/mine/pascal_voc0712_trainval.record"
}
label_map_path: "./object_detection/mine/pascal_label_map.pbtxt"
}
eval_config: {
num_examples: 4952
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 10
}
eval_input_reader:
{
tf_record_input_reader
{
input_path: "./object_detection/mine/pascal_voc2007_test.record"
}
label_map_path: "./object_detection/mine/pascal_label_map.pbtxt"
shuffle: false
num_readers: 1
}
[enter image description here][1]
[enter image description here][2]
[1]: https://i.stack.imgur.com/R8u6G.png
[2]: https://i.stack.imgur.com/AzrdU.png