Tensorflow GPU自定义对象检测不工作
我对使用tensorflow进行目标检测比较陌生,需要以下问题的指导 我正在构建一个自定义模型,使用tensorflow和Faster_Rcnn_inception_v2模型检测两个对象。为此,我使用了600个包含这两个对象的图像。这些图像分为75%的train和25%的test文件夹。 我能够在GPU(Linux)机器上使用该模型进行训练,并且只实现了0.05的损失 在生成冻结的_推断_graph.pb文件后,当我测试时,它甚至在10多幅图像中检测不到单个对象。 只有当我将min_score_thresh参数的值降低到0.4时,它才起作用 检测对象的置信度约为47% 然而,当我在不同的CPU(Windows)机器上训练相同的模型时,它工作得非常好,结果令人满意,置信度在80%以上 有人能解释一下这个问题吗?为什么在GPU上训练时模型不工作,而在CPU上训练时模型工作 注意:该问题仅发生在最近,2个月前,GPU模型针对不同的对象异常工作 如果需要,我可以共享config labelmap或任何其他文件的内容 训练指挥部:Tensorflow GPU自定义对象检测不工作,tensorflow,object-detection,custom-object,Tensorflow,Object Detection,Custom Object,我对使用tensorflow进行目标检测比较陌生,需要以下问题的指导 我正在构建一个自定义模型,使用tensorflow和Faster_Rcnn_inception_v2模型检测两个对象。为此,我使用了600个包含这两个对象的图像。这些图像分为75%的train和25%的test文件夹。 我能够在GPU(Linux)机器上使用该模型进行训练,并且只实现了0.05的损失 在生成冻结的_推断_graph.pb文件后,当我测试时,它甚至在10多幅图像中检测不到单个对象。 只有当我将min_score_
python train.py --logtostderr --train_dir="TrainingDp" --pipeline_config_path="TrainingDp/faster_rcnn.config"
代码:
配置文件的内容:
# Faster R-CNN with Inception v2, configured for Oxford-IIIT Pets Dataset.
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.
model {
faster_rcnn {
num_classes: 2
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 600
max_dimension: 1024
}
}
feature_extractor {
type: 'faster_rcnn_inception_v2'
first_stage_features_stride: 16
}
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
}
}
}
}
}
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
}
}
train_config: {
batch_size: 1
optimizer {
momentum_optimizer: {
learning_rate: {
manual_step_learning_rate {
initial_learning_rate: 0.0002
schedule {
step: 900000
learning_rate: .00002
}
schedule {
step: 1200000
learning_rate: .000002
}
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/faster_rcnn_inception_v2_coco_2018_01_28/model.ckpt"
from_detection_checkpoint: true
load_all_detection_checkpoint_vars: true
# Note: The below line limits the training process to 200K steps, which we
# empirically found to be sufficient enough to train the pets dataset. This
# effectively bypasses the learning rate schedule (the learning rate will
# never decay). Remove the below line to train indefinitely.
num_steps: 200000
data_augmentation_options {
random_horizontal_flip {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/Train.record"
}
label_map_path: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/TrainingDp2/labelmap.pbtxt"
}
eval_config: {
metrics_set: "coco_detection_metrics"
num_examples: 1101
}
eval_input_reader: {
tf_record_input_reader {
input_path: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/Test.record"
}
label_map_path: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/TrainingDp2/labelmap.pbtxt"
shuffle: false
num_readers: 1
}
谢谢。如果有人有同样的问题,
我通过更改配置文件中的batch_size=2来解决问题。如果有人有相同的问题,
我通过更改配置文件中的batch_size=2解决了此问题。请将您正在处理的代码添加到问题中Hi Aragon,我已经添加了代码。请将您正在处理的代码添加到问题中Hi Aragon,我已经添加了代码。
# Faster R-CNN with Inception v2, configured for Oxford-IIIT Pets Dataset.
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.
model {
faster_rcnn {
num_classes: 2
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 600
max_dimension: 1024
}
}
feature_extractor {
type: 'faster_rcnn_inception_v2'
first_stage_features_stride: 16
}
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
}
}
}
}
}
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
}
}
train_config: {
batch_size: 1
optimizer {
momentum_optimizer: {
learning_rate: {
manual_step_learning_rate {
initial_learning_rate: 0.0002
schedule {
step: 900000
learning_rate: .00002
}
schedule {
step: 1200000
learning_rate: .000002
}
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/faster_rcnn_inception_v2_coco_2018_01_28/model.ckpt"
from_detection_checkpoint: true
load_all_detection_checkpoint_vars: true
# Note: The below line limits the training process to 200K steps, which we
# empirically found to be sufficient enough to train the pets dataset. This
# effectively bypasses the learning rate schedule (the learning rate will
# never decay). Remove the below line to train indefinitely.
num_steps: 200000
data_augmentation_options {
random_horizontal_flip {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/Train.record"
}
label_map_path: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/TrainingDp2/labelmap.pbtxt"
}
eval_config: {
metrics_set: "coco_detection_metrics"
num_examples: 1101
}
eval_input_reader: {
tf_record_input_reader {
input_path: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/Test.record"
}
label_map_path: "C:/Users/xxxxxx/Desktop/models-master/models-master/research/object_detection/TrainingDp2/labelmap.pbtxt"
shuffle: false
num_readers: 1
}