使用对象检测 API 微调具有不同数量 类 的模型
Finetune model with different number of classes using object detection API
范围
我正在尝试使用对象检测 API 迁移学习 SSD MobileNet v3（小型）模型，但我的数据集只有 8 个 类，而提供的模型是预训练的在可可 (90 类) 上。如果我保留模型的 类 个数不变，我可以毫无问题地进行训练。
问题
更改 pipeline.config num_classes 会产生分配错误，因为图层形状与检查点变量不匹配：
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: Assign requires shapes of both tensors to match. lhs shape= [1,1,288,27] rhs shape= [1,1,288,273]
[[{{node save/Assign_15}}]]
(1) Invalid argument: Assign requires shapes of both tensors to match. lhs shape= [1,1,288,27] rhs shape= [1,1,288,273]
[[{{node save/Assign_15}}]]
[[save/RestoreV2/_404]]
问题
- 有什么方法可以改变 类 的数量并仍然进行迁移学习（比如只加载大小匹配的变量）？或者我是否必须在仅使用 8 类 从头开始训练或使用 90 类 进行微调之间应对？
- 是否有任何工具可以手动“trim”预训练的检查点变量？
数据集：ITD Dataset
型号：SSD MobileNetV3 - small (from the Model Zoo)
pipeline.config:
# SSDLite with Mobilenet v3 small feature extractor.
# Trained on COCO14, initialized from scratch.
# TPU-compatible.
# 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 {
ssd {
inplace_batchnorm_update: true
freeze_batchnorm: false
num_classes: 8
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 {
}
}
encode_background_as_zeros: 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
}
}
image_resizer {
fixed_shape_resizer {
height: 320
width: 320
}
}
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
class_prediction_bias_init: -4.6
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
random_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.97,
epsilon: 0.001,
}
}
}
}
feature_extractor {
type: 'ssd_mobilenet_v3_small'
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: 0.97,
epsilon: 0.001,
}
}
override_base_feature_extractor_hyperparams: true
}
loss {
classification_loss {
weighted_sigmoid_focal {
alpha: 0.75,
gamma: 2.0
}
}
localization_loss {
weighted_smooth_l1 {
delta: 1.0
}
}
classification_weight: 1.0
localization_weight: 1.0
}
normalize_loss_by_num_matches: true
normalize_loc_loss_by_codesize: true
post_processing {
batch_non_max_suppression {
score_threshold: 1e-8
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
use_static_shapes: true
}
score_converter: SIGMOID
}
}
}
train_config: {
batch_size: 16 #512
sync_replicas: true
startup_delay_steps: 0
replicas_to_aggregate: 32
num_steps: 0
data_augmentation_options {
ssd_random_crop_pad_fixed_aspect_ratio {
}
}
data_augmentation_options {
random_horizontal_flip {
}
}
optimizer {
momentum_optimizer: {
learning_rate: {
cosine_decay_learning_rate {
learning_rate_base: 0.4
total_steps: 800000
warmup_learning_rate: 0.13333
warmup_steps: 2000
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
fine_tune_checkpoint: "./model/model.ckpt"
fine_tune_checkpoint_type: "detection"
fine_tune_checkpoint_version: V1
keep_checkpoint_every_n_hours: 2.0
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
}
train_input_reader: {
tf_record_input_reader {
input_path: "./data/train.record"
}
label_map_path: "./annotations/label_map.pbtxt"
shuffle: true
}
eval_config: {
num_examples: 1296
}
eval_input_reader: {
tf_record_input_reader {
input_path: "./data/val.record"
}
label_map_path: "./annotations/label_map.pbtxt"
shuffle: true
num_readers: 1
}
是的，主要是Tensorflow object detection garden对fine-tune模型的想法！你应该改变 :
fine_tune_checkpoint_type = "detection"
至：
fine_tune_checkpoint_type = "fine_tune"
然后当你调用 object_detection/model_main*.py 时，你应该注意作为参数传递的 model_dir 是空的。通过这种方式，脚本将能够加载您在配置中使用 90 类 指向的 fine_tune_checkpoint，并且它将在您的空模型目录中创建一个新的检查点，其中包含保存的权重和您的 8 类。之后，您甚至可以加载之前的自定义检查点，以防您的训练停止。
编辑：fine-tune 输入参考检查此答案：https://github.com/tensorflow/models/issues/8892#issuecomment-680207038
范围
我正在尝试使用对象检测 API 迁移学习 SSD MobileNet v3（小型）模型，但我的数据集只有 8 个 类，而提供的模型是预训练的在可可 (90 类) 上。如果我保留模型的 类 个数不变，我可以毫无问题地进行训练。
问题
更改 pipeline.config num_classes 会产生分配错误，因为图层形状与检查点变量不匹配：
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: Assign requires shapes of both tensors to match. lhs shape= [1,1,288,27] rhs shape= [1,1,288,273]
[[{{node save/Assign_15}}]]
(1) Invalid argument: Assign requires shapes of both tensors to match. lhs shape= [1,1,288,27] rhs shape= [1,1,288,273]
[[{{node save/Assign_15}}]]
[[save/RestoreV2/_404]]
问题
- 有什么方法可以改变 类 的数量并仍然进行迁移学习（比如只加载大小匹配的变量）？或者我是否必须在仅使用 8 类 从头开始训练或使用 90 类 进行微调之间应对？
- 是否有任何工具可以手动“trim”预训练的检查点变量？
数据集：ITD Dataset
型号：SSD MobileNetV3 - small (from the Model Zoo)
pipeline.config:
# SSDLite with Mobilenet v3 small feature extractor.
# Trained on COCO14, initialized from scratch.
# TPU-compatible.
# 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 {
ssd {
inplace_batchnorm_update: true
freeze_batchnorm: false
num_classes: 8
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 {
}
}
encode_background_as_zeros: 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
}
}
image_resizer {
fixed_shape_resizer {
height: 320
width: 320
}
}
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
class_prediction_bias_init: -4.6
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
random_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.97,
epsilon: 0.001,
}
}
}
}
feature_extractor {
type: 'ssd_mobilenet_v3_small'
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: 0.97,
epsilon: 0.001,
}
}
override_base_feature_extractor_hyperparams: true
}
loss {
classification_loss {
weighted_sigmoid_focal {
alpha: 0.75,
gamma: 2.0
}
}
localization_loss {
weighted_smooth_l1 {
delta: 1.0
}
}
classification_weight: 1.0
localization_weight: 1.0
}
normalize_loss_by_num_matches: true
normalize_loc_loss_by_codesize: true
post_processing {
batch_non_max_suppression {
score_threshold: 1e-8
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
use_static_shapes: true
}
score_converter: SIGMOID
}
}
}
train_config: {
batch_size: 16 #512
sync_replicas: true
startup_delay_steps: 0
replicas_to_aggregate: 32
num_steps: 0
data_augmentation_options {
ssd_random_crop_pad_fixed_aspect_ratio {
}
}
data_augmentation_options {
random_horizontal_flip {
}
}
optimizer {
momentum_optimizer: {
learning_rate: {
cosine_decay_learning_rate {
learning_rate_base: 0.4
total_steps: 800000
warmup_learning_rate: 0.13333
warmup_steps: 2000
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
fine_tune_checkpoint: "./model/model.ckpt"
fine_tune_checkpoint_type: "detection"
fine_tune_checkpoint_version: V1
keep_checkpoint_every_n_hours: 2.0
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
}
train_input_reader: {
tf_record_input_reader {
input_path: "./data/train.record"
}
label_map_path: "./annotations/label_map.pbtxt"
shuffle: true
}
eval_config: {
num_examples: 1296
}
eval_input_reader: {
tf_record_input_reader {
input_path: "./data/val.record"
}
label_map_path: "./annotations/label_map.pbtxt"
shuffle: true
num_readers: 1
}
是的，主要是Tensorflow object detection garden对fine-tune模型的想法！你应该改变 :
fine_tune_checkpoint_type = "detection"
至：
fine_tune_checkpoint_type = "fine_tune"
然后当你调用 object_detection/model_main*.py 时，你应该注意作为参数传递的 model_dir 是空的。通过这种方式，脚本将能够加载您在配置中使用 90 类 指向的 fine_tune_checkpoint，并且它将在您的空模型目录中创建一个新的检查点，其中包含保存的权重和您的 8 类。之后，您甚至可以加载之前的自定义检查点，以防您的训练停止。
编辑：fine-tune 输入参考检查此答案：https://github.com/tensorflow/models/issues/8892#issuecomment-680207038