Hi,
I’m trying to train a detectnet_v2 object detector with the mobilenet_v2 backbone.
Once the training process has started I get the following error:
Traceback (most recent call last):
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 797, in <module>
File "<decorator-gen-2>", line 2, in main
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/utilities/timer.py", line 46, in wrapped_fn
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 790, in main
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 691, in run_experiment
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 576, in train_gridbox
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 387, in build_gridbox_model
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/model/detectnet_model.py", line 106, in construct_model
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/model/detectnet_model.py", line 235, in _construct_feature_extractor
IndexError: tuple index out of range
Traceback (most recent call last):
File "/usr/local/bin/detectnet_v2", line 8, in <module>
sys.exit(main())
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/entrypoint/detectnet_v2.py", line 12, in main
File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/common/entrypoint/entrypoint.py", line 296, in launch_job
AssertionError: Process run failed.
2021-04-20 20:57:57,443 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.
I can’t seem to reproduce the issue with any other backbone, even though they’re using roughly the same spec file (aside from the “arch” and “pretrained_model_file” options). The spec file in this case is as follows:
random_seed: 42
dataset_config {
data_sources {
tfrecords_path: "/workspace/tlt-experiments/tfrecords/*"
image_directory_path: "/workspace/tlt-experiments/data/train/"
}
image_extension: "png"
target_class_mapping {
key: "pedestrian"
value: "pedestrian"
}
target_class_mapping {
key: "person"
value: "pedestrian"
}
target_class_mapping {
key: "person_sitting"
value: "pedestrian"
}
validation_fold: 0
}
augmentation_config {
preprocessing {
output_image_width: 640
output_image_height: 480
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: "car"
value {
clustering_config {
clustering_algorithm: DBSCAN
dbscan_confidence_threshold: 0.9
coverage_threshold: 0.00499999988824
dbscan_eps: 0.20000000298
dbscan_min_samples: 0.0500000007451
minimum_bounding_box_height: 20
}
}
}
target_class_config {
key: "cyclist"
value {
clustering_config {
clustering_algorithm: DBSCAN
dbscan_confidence_threshold: 0.9
coverage_threshold: 0.00499999988824
dbscan_eps: 0.15000000596
dbscan_min_samples: 0.0500000007451
minimum_bounding_box_height: 20
}
}
}
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
}
}
}
}
model_config {
pretrained_model_file: "/workspace/tlt-experiments/mobilenet_v2.hdf5"
use_batch_norm: true
objective_set {
bbox {
scale: 35.0
offset: 0.5
}
cov {
}
}
training_precision {
backend_floatx: FLOAT32
}
arch: "mobilenet_v2"
}
evaluation_config {
validation_period_during_training: 5
first_validation_epoch: 30
minimum_detection_ground_truth_overlap {
key: "car"
value: 0.699999988079
}
minimum_detection_ground_truth_overlap {
key: "cyclist"
value: 0.5
}
minimum_detection_ground_truth_overlap {
key: "pedestrian"
value: 0.5
}
evaluation_box_config {
key: "car"
value {
minimum_height: 10
maximum_height: 9999
minimum_width: 10
maximum_width: 9999
}
}
evaluation_box_config {
key: "cyclist"
value {
minimum_height: 10
maximum_height: 9999
minimum_width: 10
maximum_width: 9999
}
}
evaluation_box_config {
key: "pedestrian"
value {
minimum_height: 10
maximum_height: 9999
minimum_width: 10
maximum_width: 9999
}
}
average_precision_mode: SAMPLE
}
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
}
}
enable_autoweighting: true
max_objective_weight: 0.999899983406
min_objective_weight: 9.99999974738e-05
}
training_config {
batch_size_per_gpu: 4
num_epochs: 40
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: 5
}
bbox_rasterizer_config {
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: "cyclist"
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: "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
}
}
deadzone_radius: 0.400000154972
}
Is there something wrong with the spec file, or I should provide more information about the setup?
Thanks for helping out.
Edit:
The tlt command I’m using for launching this task is as follows:
tlt detectnet_v2 train -e /workspace/tlt-experiments/detectnet_v2/specs/detectnet_v2_train_mobilenet_v2_kitti.txt -r /workspace/tlt-experiments/unpruned -k tlt_encode --gpus 1