Commit db24ed83 authored by Oksana Belyaeva's avatar Oksana Belyaeva
Browse files

added configs and readme

parent bfdd7584
......@@ -21,6 +21,17 @@ PubLayNet/labeled - изображения с нарисованным GT, ге
и описание тренируемых классов (label_map.pbtxt), которые используются для обучения
* /pretrain_models - расположены претреннерованные модели, которые скачены из зоопарка Tensorflow
Установка TensorFlow API
```bash
git clone https://github.com/tensorflow/models.git
cd models/research/
protoc object_detection/protos/*.proto --python_out=.
export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim
cd ..
cd ..
```
2 Конвертация json в csv
```bash
cd DataSet
......
# Faster R-CNN with Resnet-101 (v1), configuration for MSCOCO 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: 3
image_resizer {
fixed_shape_resizer {
height: 800
width: 600
}
}
feature_extractor {
type: 'faster_rcnn_resnet101'
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: 4
optimizer {
momentum_optimizer: {
learning_rate: {
manual_step_learning_rate {
initial_learning_rate: 0.003
schedule {
step: 1
learning_rate: .0001
}
schedule {
step: 900000
learning_rate: .00003
}
schedule {
step: 1200000
learning_rate: .000003
}
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "pretrain_models/my_publaynet/model.ckpt-396043"
from_detection_checkpoint: true
data_augmentation_options {
random_horizontal_flip {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "tfrecord_data/train-gen-10pad.record"
}
label_map_path: "configs/label_map_3cl.pbtxt"
}
eval_config: {
num_examples: 8000
# 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: "tfrecord_data/test-gen-10pad.record"
}
label_map_path: "configs/label_map_3cl.pbtxt"
shuffle: false
num_readers: 1
}
......@@ -82,7 +82,7 @@ model {
}
train_config: {
batch_size: 4
batch_size: 1
optimizer {
momentum_optimizer: {
learning_rate: {
......
......@@ -82,7 +82,7 @@ model {
}
train_config: {
batch_size: 1
batch_size: 4
optimizer {
momentum_optimizer: {
learning_rate: {
......@@ -107,7 +107,7 @@ train_config: {
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "pretrain_models/faster_rcnn_resnet101_publaynet/model.ckpt-105527"
fine_tune_checkpoint: "pretrain_models/my_publaynet/model.ckpt-396043"
from_detection_checkpoint: true
data_augmentation_options {
random_horizontal_flip {
......@@ -117,7 +117,7 @@ train_config: {
train_input_reader: {
tf_record_input_reader {
input_path: "tfrecord_data/train-012_3cl.record"
input_path: "tfrecord_data/train-gen-10pad.record"
}
label_map_path: "configs/label_map_3cl.pbtxt"
}
......@@ -131,7 +131,7 @@ eval_config: {
eval_input_reader: {
tf_record_input_reader {
input_path: "tfrecord_data/test_3cl.record"
input_path: "tfrecord_data/test-gen-10pad.record"
}
label_map_path: "configs/label_map_3cl.pbtxt"
shuffle: false
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment