@Morganh I have a dateaset containing 22,00 training images and 700 testing images of a single class "person.
All my images are of dimension (1280*720).
I used the below resnet18_kitti_train_file for training.
random_seed: 42
dataset_config {
data_sources {
tfrecords_path: "/workspace/tlt-experiments/data/tfrecords/kitti_trainval/*"
image_directory_path: "/workspace/tlt-experiments/data/training"
}
image_extension: "jpg"
target_class_mapping {
key: "person"
value: "person"
}
validation_fold : 0
}
augmentation_config {
preprocessing {
output_image_width: 1280
output_image_height: 720
min_bbox_width: 1.0
min_bbox_height: 1.0
output_image_channel: 3
}
spatial_augmentation {
hflip_probability: 0.5
zoom_min: 1.0
zoom_max: 1.0
translate_max_x: 8.0
translate_max_y: 8.0
}
color_augmentation {
hue_rotation_max: 25.0
saturation_shift_max: 0.2
contrast_scale_max: 0.1
contrast_center: 0.5
}
}
postprocessing_config {
target_class_config {
key: "person"
value {
clustering_config {
clustering_algorithm: DBSCAN
dbscan_confidence_threshold: 0.9
coverage_threshold: 0.005
dbscan_eps: 0.20
dbscan_min_samples: 0.05
minimum_bounding_box_height: 6
}
}
}
}
model_config {
pretrained_model_file: "/workspace/tlt-experiments/detectnet_v2/pretrained_resnet18/tlt_pretrained_detectnet_v2_vresnet18/resnet18.hdf5"
num_layers: 18
use_batch_norm: True
objective_set {
bbox {
scale: 35.0
offset: 0.5
}
cov {
}
}
training_precision {
backend_floatx: FLOAT32
}
arch: "resnet"
}
evaluation_config {
validation_period_during_training: 20
first_validation_epoch: 10
minimum_detection_ground_truth_overlap {
key: "person"
value: 0.4
}
evaluation_box_config {
key: "person"
value {
minimum_height: 20
maximum_height: 9999
minimum_width: 10
maximum_width: 9999
}
}
average_precision_mode: INTEGRATE
}
cost_function_config {
target_classes {
name: "person"
class_weight: 1.0
coverage_foreground_weight: 0.05
objectives {
name: "cov"
initial_weight: 1.0
weight_target: 1.0
}
objectives {
name: "bbox"
initial_weight: 10.0
weight_target: 10.0
}
}
max_objective_weight: 0.999899983406
min_objective_weight: 9.99999974738e-05
}
training_config {
batch_size_per_gpu: 16
num_epochs: 80
learning_rate {
soft_start_annealing_schedule {
min_learning_rate: 5e-06
max_learning_rate: 5e-04
soft_start: 0.10
annealing: 0.7
}
}
regularizer {
type: L1
weight: 3e-9
}
optimizer {
adam {
epsilon: 9.99999993923e-09
beta1: 0.9
beta2: 0.999
}
}
cost_scaling {
initial_exponent: 20.0
increment: 0.005
decrement: 1.0
}
checkpoint_interval: 5
}
bbox_rasterizer_config {
target_class_config {
key: "person"
value {
cov_center_x: 0.5
cov_center_y: 0.5
cov_radius_x: 1.0
cov_radius_y: 1.0
bbox_min_radius: 1.0
}
}
deadzone_radius:0.4
}
In training, When I tested with 1st checkpoint (after 10 epochs) and with the 2nd checkpoint (after 20 epochs), the detection was good (Almost 70%), but it has given a lot of false positives as well. I am really confused, why this happened. Thanks.