tensorflow / tensorflow/models
Loss increases with training
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
I am trying to train faster_rcnn_resnet101_v1_640x640_coco17_tpu-8 on custom data set.
The loss increases with each training step.


Using the below config file.
`
model {
faster_rcnn {
num_classes: 1
image_resizer {
fixed_shape_resizer {
height: 640
width: 640
}
}
feature_extractor {
type: 'faster_rcnn_inception_resnet_v2_keras'
batch_norm_trainable: true
}
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: 17
maxpool_kernel_size: 1
maxpool_stride: 1
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
}
}
}
share_box_across_classes: true
}
}
second_stage_post_processing {
batch_non_max_suppression {
score_threshold: 0.0
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SOFTMAX
}
second_stage_localization_loss_weight: 2.0
second_stage_classification_loss_weight: 1.0
use_static_shapes: true
use_matmul_crop_and_resize: true
clip_anchors_to_image: true
use_static_balanced_label_sampler: true
use_matmul_gather_in_matcher: true
}
}
train_config: {
batch_size: 4
sync_replicas: true
startup_delay_steps: 0
replicas_to_aggregate: 8
num_steps: 100000
optimizer {
momentum_optimizer: {
learning_rate: {
cosine_decay_learning_rate {
learning_rate_base: .16
total_steps: 100000
warmup_learning_rate: 0
warmup_steps: 2500
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
fine_tune_checkpoint_version: V2
fine_tune_checkpoint: "/home/ubuntu/sangeeth/object_detection/faster_rcnn_inception_resnet_v2_640x640_coco17_tpu-8/checkpoint/ckpt-0"
fine_tune_checkpoint_type: "detection"
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
random_adjust_hue {
}
}
data_augmentation_options {
random_adjust_contrast {
}
}
data_augmentation_options {
random_adjust_saturation {
}
}
data_augmentation_options {
random_square_crop_by_scale {
scale_min: 0.6
scale_max: 1.3
}
}
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
use_bfloat16: true # works only on TPUs
}
train_input_reader: {
label_map_path: "/home/ubuntu/sangeeth/object_detection/label_map.txt"
tf_record_input_reader {
input_path: "/home/ubuntu/sangeeth/object_detection/smoke.record"
}
}
eval_config: {
metrics_set: "coco_detection_metrics"
use_moving_averages: false
batch_size: 1;
}
eval_input_reader: {
label_map_path: "/home/ubuntu/sangeeth/object_detection/label_map.txt"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "/home/ubuntu/sangeeth/object_detection/smoke.record"
}
}
`
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.