Please provide the following information when requesting support.
• Hardware (T4/V100/Xavier/Nano/etc)
T4
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)
Faster_rcnn
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
docker_tag: v3.21.08-py3
• Training spec file(If have, please share here)
Copyright (c) 2017-2020, NVIDIA CORPORATION. All rights reserved.
random_seed: 42
enc_key: ‘NXVodTI0MXNnZGtzdXBic2o0cTIwbmp0bnA6N2IwZDEyMGYtMGZiOS00MDNlLTllOGMtOGMzOTJiYmRlMzk0’
verbose: True
model_config {
input_image_config {
image_type: RGB
image_channel_order: ‘bgr’
size_height_width {
#height: 2160
#width: 3840
height: 384
width: 1248
}
image_channel_mean {
key: ‘b’
value: 103.939
}
image_channel_mean {
key: ‘g’
value: 116.779
}
image_channel_mean {
key: ‘r’
value: 123.68
}
image_scaling_factor: 1.0
max_objects_num_per_image: 100
}
arch: “resnet:18”
anchor_box_config {
scale: 64.0
scale: 128.0
scale: 256.0
ratio: 1.0
ratio: 0.5
ratio: 2.0
}
freeze_bn: False
roi_mini_batch: 256
rpn_stride: 16
use_bias: False
roi_pooling_config {
pool_size: 7
pool_size_2x: False
}
all_projections: True
use_pooling:False
}
dataset_config {
data_sources: {
tfrecords_path: “/home/ubuntu/cv_samples_v1.2.0/data/tfrecords/kitti_trainval/kitti_trainval*”
image_directory_path: “/home/ubuntu/cv_samples_v1.2.0/data/training/”
}
image_extension: ‘jpg’
target_class_mapping {
key: ‘car’
value: ‘car’
}
target_class_mapping {
key: ‘hvac’
value: ‘hvac’
}
target_class_mapping {
key: ‘person’
value: ‘person’
}
validation_fold: 0
}
augmentation_config {
preprocessing {
output_image_width: 1248
output_image_height: 384
output_image_channel: 3
min_bbox_width: 1.0
min_bbox_height: 1.0
enable_auto_resize: True
}
spatial_augmentation {
hflip_probability: 0.5
vflip_probability: 0.0
zoom_min: 1.0
zoom_max: 1.0
translate_max_x: 0
translate_max_y: 0
}
color_augmentation {
hue_rotation_max: 0.0
saturation_shift_max: 0.0
contrast_scale_max: 0.0
contrast_center: 0.5
}
}
training_config {
enable_augmentation: True
enable_qat: False
#batch_size_per_gpu: 1
batch_size_per_gpu: 1
num_epochs: 50
pretrained_weights: “/home/ubuntu/cv_samples_v1.2.0/faster_rcnn/resnet_18.hdf5”
#resume_from_model: “/home/ubuntu/cv_samples_v1.2.0/faster_rcnn/frcnn_kitti_resnet18.epoch2.tlt”
output_model: “/home/ubuntu/cv_samples_v1.2.0/faster_rcnn/frcnn_kitti_resnet18.tlt”
rpn_min_overlap: 0.3
rpn_max_overlap: 0.7
classifier_min_overlap: 0.0
classifier_max_overlap: 0.5
gt_as_roi: False
std_scaling: 1.0
classifier_regr_std {
key: ‘x’
value: 10.0
}
classifier_regr_std {
key: ‘y’
value: 10.0
}
classifier_regr_std {
key: ‘w’
value: 5.0
}
classifier_regr_std {
key: ‘h’
value: 5.0
}
rpn_mini_batch: 256
rpn_pre_nms_top_N: 12000
rpn_nms_max_boxes: 2000
rpn_nms_overlap_threshold: 0.7
regularizer {
type: L2
weight: 1e-4
}
optimizer {
sgd {
lr: 0.002
momentum: 0.9
decay: 0.0
nesterov: False
}
}
learning_rate {
soft_start {
base_lr: 0.02
start_lr: 0.002
soft_start: 0.1
annealing_points: 0.8
annealing_points: 0.9
annealing_divider: 10.0
}
}
lambda_rpn_regr: 1.0
lambda_rpn_class: 1.0
lambda_cls_regr: 1.0
lambda_cls_class: 1.0
}
inference_config {
images_dir: ‘/home/ubuntu/cv_samples_v1.2.0/data/training/resize_images’
model: ‘/home/ubuntu/cv_samples_v1.2.0/faster_rcnn/frcnn_kitti_resnet18.epoch50.tlt’
batch_size: 1
detection_image_output_dir: ‘/home/ubuntu/cv_samples_v1.2.0/faster_rcnn/inference_results_imgs’
labels_dump_dir: ‘/home/ubuntu/cv_samples_v1.2.0/faster_rcnn/inference_dump_labels’
rpn_pre_nms_top_N: 6000
rpn_nms_max_boxes: 300
rpn_nms_overlap_threshold: 0.7
object_confidence_thres: 0.0001
bbox_visualize_threshold: 0.6
classifier_nms_max_boxes: 100
classifier_nms_overlap_threshold: 0.3
}
evaluation_config {
model: ‘/home/ubuntu/cv_samples_v1.2.0/faster_rcnn/frcnn_kitti_resnet18.epoch50.tlt’
batch_size: 1
validation_period_during_training: 1
rpn_pre_nms_top_N: 6000
rpn_nms_max_boxes: 300
rpn_nms_overlap_threshold: 0.7
classifier_nms_max_boxes: 100
classifier_nms_overlap_threshold: 0.3
object_confidence_thres: 0.0001
use_voc07_11point_metric:False
gt_matching_iou_threshold: 0.5
}
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)
I can not share the data
Hi,
I am running the fasterRCNN with a custom dataset, I have three classes called car, person, and hvac, I barely change the configuration file except for the learning rate from 0.02 to 0.2, I have all the mapping lower case and trained the model for 50 epochs, but in all the epochs the AP precision and recall are zero. In total, I have 120 images and I am just going to fine-tune the model The following is the format of the labels in one image
car 0 0 0 621 98 638 91 0 0 0 0 0 0 0
car 0 0 0 473 33 477 30 0 0 0 0 0 0 0
car 0 0 0 493 51 498 47 0 0 0 0 0 0 0
The file names are starting from 0 and all resized to the default input of the model
Am I missing something?
However, I am wondering to know that if the model will resize images on fly or if I can set different image sizes ( change the model input and output size)
Regards