在Google中,我试图使用Tensorflow Object和SSD_mobilenet_v1_pets.config来检测汽车,它用car检测humans,用N/A检测car。以下是size config和image dimensions:
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
}我有1160幅不同尺寸的图像(例如: 73 x 63,118 x 62,62 x 56,71 x 56,276 x 183,259 x 184,318 x 159,700 x 420,647 x 407,897 x 554)
我上面提到的产出:


请澄清,问题是汽车的错误检测是因为图像尺寸还是其他什么的?
这是我的配置文件
model {
ssd {
num_classes: 1
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: 1
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_v1'
min_depth: 16
depth_multiplier: 1.0
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 {
anchorwise_output: true
}
}
localization_loss {
weighted_smooth_l1 {
anchorwise_output: true
}
}
hard_example_miner {
num_hard_examples: 3000
iou_threshold: 0.99
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 0
}
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: 32
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: "ssd_mobilenet_v1_coco_11_06_2017/model.ckpt"
from_detection_checkpoint: true
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "object_detection/data/train.record"
}
label_map_path: "object_detection/data/object-detection.pbtxt"
}
eval_config: {
num_examples: 40
}
eval_input_reader: {
tf_record_input_reader {
input_path: "object_detection/data/test.record"
}
label_map_path: "training/object-detection.pbtxt"
shuffle: false
num_readers: 1
}这是我的pbtxt代码
item {
id: 1
name: 'car'
}我还有另一个疑问,请帮助我,我试着去发现没有戴头盔的人。我使用了上面提到的相同的模型。这是我的pbtxt文件
item {
id: 91
name: 'withouthelmet'
}我得到了这个输出

请帮帮我..。
发布于 2018-09-28 04:11:53
正如@Janikan所指出的,问题在于.pbtxt文件。由于您使用的是默认的ssd_mobilenet模型,所以它是在model上训练的,该数据集实际上有90个类,而car的ID为3。由于它在标签映射中找不到ID 3,输出显示为N/A。默认标签映射中的ID 1是person,这就是为什么它将"car“显示为所有人的分类。
如果你只想展示汽车。替换pbtxt文件并编辑visualisation_tools,只筛选所需的class_Id。
发布于 2018-09-27 13:18:31
请张贴您的标签-地图object-detection.pbtxt.
我猜在第一位置上只提到了那辆车!?
https://stackoverflow.com/questions/52401644
复制相似问题