Hi,
I have train my model with resnet18 for single class(person). training file detectnet_v2_train_resnet18_kitti.txt is:
random_seed: 42
dataset_config {
data_sources {
tfrecords_path: "/workspace/tlt-experiments/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: 0.20000000298
contrast_scale_max: 0.10000000149
contrast_center: 0.5
}
}
postprocessing_config {
target_class_config {
key: "person"
value {
clustering_config {
coverage_threshold: 0.00499999988824
dbscan_eps: 0.20000000298
dbscan_min_samples: 0.0500000007451
minimum_bounding_box_height: 20
}
}
}
}
model_config {
pretrained_model_file: "/workspace/tlt-experiments/pretrained_resnet18/tlt_resnet18_detectnet_v2_v1/resnet18.hdf5"
num_layers: 18
use_batch_norm: true
activation {
activation_type: "relu"
}
objective_set {
bbox {
scale: 35.0
offset: 0.5
}
cov {
}
}
training_precision {
backend_floatx: FLOAT32
}
arch: "resnet"
}
evaluation_config {
validation_period_during_training: 10
first_validation_epoch: 1
minimum_detection_ground_truth_overlap {
key: "person"
value: 0.699999988079
}
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: 0.0500000007451
objectives {
name: "cov"
initial_weight: 1.0
weight_target: 1.0
}
objectives {
name: "bbox"
initial_weight: 10.0
weight_target: 10.0
}
}
enable_autoweighting: true
max_objective_weight: 0.999899983406
min_objective_weight: 9.99999974738e-05
}
training_config {
batch_size_per_gpu: 12
num_epochs: 3500
learning_rate {
soft_start_annealing_schedule {
min_learning_rate: 5e-06
max_learning_rate: 5e-04
soft_start: 0.10000000149
annealing: 0.699999988079
}
}
regularizer {
type: L1
weight: 3.00000002618e-09
}
optimizer {
adam {
epsilon: 9.99999993923e-09
beta1: 0.899999976158
beta2: 0.999000012875
}
}
cost_scaling {
initial_exponent: 20.0
increment: 0.005
decrement: 1.0
}
checkpoint_interval: 10
}
bbox_rasterizer_config {
target_class_config {
key: "person"
value {
cov_center_x: 0.5
cov_center_y: 0.5
cov_radius_x: 0.40000000596
cov_radius_y: 0.40000000596
bbox_min_radius: 1.0
}
}
deadzone_radius: 0.400000154972
}
logs after training completed :
INFO:tensorflow:Saving checkpoints for step-399000.
2020-02-02 14:23:51,160 [INFO] tensorflow: Saving checkpoints for step-399000.
2020-02-02 14:23:51,496 [INFO] iva.detectnet_v2.evaluation.evaluation: step 0 / 18, 0.00s/step
2020-02-02 14:23:53,434 [INFO] iva.detectnet_v2.evaluation.evaluation: step 10 / 18, 0.19s/step
Matching predictions to ground truth, class 1/1.: 100%|#| 319/319 [00:00<00:00, 9364.71it/s]
Epoch 3500/3500
=========================
Validation cost: 0.000086
Mean average_precision (in %): 82.3062
class name average precision (in %)
------------ --------------------------
person 82.3062
Median Inference Time: 0.013935
2020-02-02 14:23:55,099 [INFO] /usr/local/lib/python2.7/dist-packages/iva/detectnet_v2/tfhooks/sample_counter_hook.pyc: Samples / sec: 21.359
Time taken to run iva.detectnet_v2.scripts.train:main: 1 day, 23:34:05.290584.
json file detectnet_v2_clusterfile_kitti.json for inference is :
{
"dbscan_criterion": "IOU",
"dbscan_eps": {
"person": 0.25,
"default": 0.15
},
"dbscan_min_samples": {
"person": 0.05,
"default": 0.0
},
"min_cov_to_cluster": {
"person": 0.005,
"default": 0.005
},
"min_obj_height": {
"person": 4,
"default": 2
},
"target_classes": ["person"],
"confidence_th": {
"person": 0.8
},
"confidence_model": {
"person": { "kind": "aggregate_cov"},
"default": { "kind": "aggregate_cov"}
},
"output_map": {
"person" : "person"
},
"color": {
"person": "green",
"default": "blue"
},
"postproc_classes": ["perosn"],
"image_height": 720,
"image_width": 720,
"stride": 16
}
I am not able to see even single B-BOX on test images. and also i have generated file and tested the resnet18_detector.etlt
calibration.bin
calibration.tensor
on DS-3 but not getting B-BOX on a single frames.
please help where i am wrong.
I had also train model using resnet18 last time but last time i was getting result and that time training precision was 58 but this time precision is 82 + but not getting result.
Thanks.