如何解决TF OD 2 API的培训过早结束
这些天来，我一直在使用Tensorflow对象检测API 2（TF OD 2），我正在使用git head commit ce3b7227。我的目标是通过使用TensorFlow 2 Model Zoo中存在的现有DL体系结构，找到最适合我的自定义数据集的模型。我已经按照以下Roboflow教程生成了TF记录，并且已经在GPU模式下使用我的笔记本电脑和Google Colab对其进行了培训。
我发现了这一惊人的Roboflow's Colab Notebook，同时尝试通过 models / research / object_detection / model_main_tf2.py 来复制数据集的相同步骤，对我来说，训练脚本总是在开始迭代之前就结束了。它没有显示任何Python错误，还像往常一样显示了一些警告。完整的输出在我的Colab Notebook
中我正在使用以下命令对模型进行微调。
PIPELINE_CONFIG_PATH=models/ssd_resnet152_v1_fpn_640x640_coco17_tpu-8/pipeline.config; MODEL_DIR=training/; NUM_TRAIN_STEPS=10000; SAMPLE_1_OF_N_EVAL_EXAMPLES=1;
python models/research/object_detection/model_main_tf2.py --model_dir=$MODEL_DIR --num_train_steps=$NUM_TRAIN_STEPS --sample_1_of_n_eval_examples=$SAMPLE_1_OF_N_EVAL_EXAMPLES --pipeline_config_path=$PIPELINE_CONFIG_PATH --alsologtostderr
这是我的pipeline.config文件
model {
ssd {
num_classes: 90
image_resizer {
fixed_shape_resizer {
height: 640
width: 640
}
}
feature_extractor {
type: "ssd_resnet152_v1_fpn_keras"
depth_multiplier: 1.0
min_depth: 16
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 0.00039999998989515007
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.029999999329447746
}
}
activation: RELU_6
batch_norm {
decay: 0.996999979019165
scale: true
epsilon: 0.0010000000474974513
}
}
override_base_feature_extractor_hyperparams: true
fpn {
min_level: 3
max_level: 7
}
}
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 {
weight_shared_convolutional_box_predictor {
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 0.00039999998989515007
}
}
initializer {
random_normal_initializer {
mean: 0.0
stddev: 0.009999999776482582
}
}
activation: RELU_6
batch_norm {
decay: 0.996999979019165
scale: true
epsilon: 0.0010000000474974513
}
}
depth: 256
num_layers_before_predictor: 4
kernel_size: 3
class_prediction_bias_init: -4.599999904632568
}
}
anchor_generator {
multiscale_anchor_generator {
min_level: 3
max_level: 7
anchor_scale: 4.0
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
scales_per_octave: 2
}
}
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 {
}
}
classification_loss {
weighted_sigmoid_focal {
gamma: 2.0
alpha: 0.25
}
}
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: 8
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
random_crop_image {
min_object_covered: 0.0
min_aspect_ratio: 0.75
max_aspect_ratio: 3.0
min_area: 0.75
max_area: 1.0
overlap_thresh: 0.0
}
}
sync_replicas: true
optimizer {
momentum_optimizer {
learning_rate {
cosine_decay_learning_rate {
learning_rate_base: 0.03999999910593033
total_steps: 25000
warmup_learning_rate: 0.013333000242710114
warmup_steps: 2000
}
}
momentum_optimizer_value: 0.8999999761581421
}
use_moving_average: false
}
fine_tune_checkpoint_version: V2
fine_tune_checkpoint: "models/ssd_resnet152_v1_fpn_640x640_coco17_tpu-8/checkpoint/ckpt-0"
num_steps: 25000
startup_delay_steps: 0.0
replicas_to_aggregate: 8
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
fine_tune_checkpoint_type: "classification"
use_bfloat16: true
}
train_input_reader {
label_map_path: "datasets/UrbanTracker/urban_tracker_label_map.pbtxt"
tf_record_input_reader {
input_path: "datasets/UrbanTracker/urban_tracker_train.record"
}
}
eval_config {
metrics_set: "coco_detection_metrics"
use_moving_averages: false
}
eval_input_reader {
label_map_path: "datasets/UrbanTracker/urban_tracker_label_map.pbtxt"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "datasets/UrbanTracker/urban_tracker_test.record"
}
}
这是我的模型目录的样子。
.
├── datasets
│ ├── raccoon
│ │ ├── raccoon_label_map.pbtxt
│ │ ├── raccoon_test.record
│ │ └── raccoon_train.record
│ ├── readme.md
│ └── UrbanTracker
│ ├── labels_urbantracker.txt
│ ├── urban_tracker_label_map.pbtxt
│ ├── urban_tracker_test.record
│ └── urban_tracker_train.record
├── __main__.py
├── models
│ ├── AUTHORS
│ ├── efficientdet_d1_coco17_tpu-32
│ │ ├── checkpoint
│ │ │ ├── checkpoint
│ │ │ ├── ckpt-0.data-00000-of-00001
│ │ │ └── ckpt-0.index
│ │ ├── pipeline.config
│ │ ├── saved_model
│ │ │ ├── assets
│ │ │ ├── saved_model.pb
│ │ │ └── variables
│ │ │ ├── variables.data-00000-of-00001
│ │ │ └── variables.index
│ ├── faster_rcnn_resnet101_v1_640x640_coco17_tpu-8
│ │ ├── checkpoint
│ │ │ ├── checkpoint
│ │ │ ├── ckpt-0.data-00000-of-00001
│ │ │ └── ckpt-0.index
│ │ ├── pipeline.config
│ │ ├── saved_model
│ │ │ ├── saved_model.pb
│ │ │ └── variables
│ │ │ ├── variables.data-00000-of-00001
│ │ │ └── variables.index
│ └── ssd_resnet152_v1_fpn_640x640_coco17_tpu-8
│ ├── checkpoint
│ │ ├── checkpoint
│ │ ├── ckpt-0.data-00000-of-00001
│ │ └── ckpt-0.index
│ ├── pipeline.config
│ ├── saved_model
│ │ ├── assets
│ │ ├── saved_model.pb
│ │ └── variables
│ │ ├── variables.data-00000-of-00001
│ │ └── variables.index
├── tools
│ ├── parse_polytrack.py
│ ├── polytrack_csv_to_tfrecord.py
│ ├── raccoon_labels_test.csv
│ ├── raccoon_labels_train.csv
│ ├── split_dataset.py
│ ├── urban_tracker_test.csv
│ └── urban_tracker_train.csv
我已使用TF v1和v2 API将数据集转换为TFRecord。另外，我一直在尝试不同的训练参数，但是没有运气。为了检查我的数据集，以防万一我生成了错误的数据，我尝试了另一个数据集，即基本的Raccoon Dataset，但是得到了相同的结果。
感谢您的关注。
解决方法
已解决：对于诸如 efficiencydet_d1_coco17_tpu-32 之类的模型，只需将 pipeline.config 参数从fine_tune_checkpoint_type: "classification"更改为fine_tune_checkpoint_type: "detection"，请选中{ {3}}
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。