Docker instantiation failed with error: 500 Server Error: Internal Server Error (“OCI runtime create failed: container_linux.go:367: starting container process caused: process_linux.go:495: container init caused: Running hook #0:: error running hook: exit status 1, stdout: , stderr: nvidia-container-cli: detection error: nvml error: unknown error: unknown”)
• Hardware: RTX 2080
• Network Type: Dashcamnet
• TLT Version: Configuration of the TLT Instance
dockers: [‘nvidia/tlt-streamanalytics’, ‘nvidia/tlt-pytorch’]
format_version: 1.0
tlt_version: 3.0
•Config specs:
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: “png”
target_class_mapping {
key: “pedestrian”
value: “pedestrian”
}
target_class_mapping {
key: “person”
value: “pedestrian”
}
target_class_mapping {
key: “car”
value: “car”
}
target_class_mapping {
key: “two_wheels”
value: “two_wheels”
}
target_class_mapping {
key: “head_covered”
value: “head_covered”
}
validation_fold: 0
}
augmentation_config {
preprocessing {
output_image_width: 960
output_image_height: 544
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: “pedestrian”
value {
clustering_config {
clustering_algorithm: DBSCAN
dbscan_confidence_threshold: 0.9
coverage_threshold: 0.00749999983236
dbscan_eps: 0.230000004172
dbscan_min_samples: 0.0500000007451
minimum_bounding_box_height: 20
}
}
}
target_class_config {
key: “car”
value: {
clustering_config {
coverage_threshold: 0.005
dbscan_eps: 0.1
dbscan_min_samples: 0.05
minimum_bounding_box_height: 4
}
}
}
target_class_config {
key: “two_wheels”
value: {
clustering_config {
coverage_threshold: 0.005
dbscan_eps: 0.1
dbscan_min_samples: 0.05
minimum_bounding_box_height: 4
}
}
}
}
target_class_config {
key: “head_covered”
value: {
clustering_config {
coverage_threshold: 0.005
dbscan_eps: 0.1
dbscan_min_samples: 0.05
minimum_bounding_box_height: 4
}
}
}
}
model_config {
pretrained_model_file: “/workspace/tlt-experiments/detectnet_v2/pretrained_dashcam/tlt_dashcamnet_vunpruned_v1.0/resnet18_dashcamnet.tlt”
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: 10
first_validation_epoch: 30
minimum_detection_ground_truth_overlap {
key: “pedestrian”
value: 0.5
}
minimum_detection_ground_truth_overlap {
key: “car”
value: 0.699999988079
}
minimum_detection_ground_truth_overlap {
key: “two_wheels”
value: 0.5
}
minimum_detection_ground_truth_overlap {
key: “head_covered”
value: 0.5
}
evaluation_box_config {
key: “pedestrian”
value {
minimum_height: 20
maximum_height: 9999
minimum_width: 10
maximum_width: 9999
}
}
evaluation_box_config {
key: “car”
value {
minimum_height: 20
maximum_height: 9999
minimum_width: 10
maximum_width: 9999
}
}
evaluation_box_config {
key: “two_wheels”
value {
minimum_height: 20
maximum_height: 9999
minimum_width: 10
maximum_width: 9999
}
}
evaluation_box_config {
key: “head_covered”
value {
minimum_height: 5
maximum_height: 9999
minimum_width: 5
maximum_width: 9999
}
}
average_precision_mode: INTEGRATE
}
cost_function_config {
target_classes {
name: “pedestrian”
class_weight: 4.0
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
}
}
target_classes {
name: “car”
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
}
}
target_classes {
name: “two_wheels”
class_weight: 8.0
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: 1.0
}
}
target_classes {
name: “head_covered”
class_weight: 4.0
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: 4
num_epochs: 80
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: “pedestrian”
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
}
}
target_class_config {
key: “car”
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
}
}
target_class_config {
key: “two_wheels”
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
}
}
target_class_config {
key: “head_covered”
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: 0.400000154972
}
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)
When running:
!tlt detectnet_v2 train -e $SPECS_DIR/dashcamnet_train_resnet18_kitti.txt
-r $USER_EXPERIMENT_DIR/dashcam_dir_unpruned
-k $KEY
-n dashcam_detector
–gpus $NUM_GPUS}
I get:
Docker instantiation failed with error: 500 Server Error: Internal Server Error (“OCI runtime create failed: container_linux.go:367: starting container process caused: process_linux.go:495: container init caused: Running hook #0:: error running hook: exit status 1, stdout: , stderr: nvidia-container-cli: detection error: nvml error: unknown error: unknown”)
Tfrecords were generated successfully, images have been resized offline to 960x544, .png extension.