apologies for the mistake, I lost some info while copy-pasting some information from a terminal.
The command I originally used is.
tao detectnet_v2 train -k 7221 -r /home/saiteja/results -e /home/saiteja/scripts/train/task2_detectNet_train.cfg
2022-07-06 08:01:41,067 [INFO] iva.detectnet_v2.dataio.kitti_converter_lib: Num images in
Train: 5487 Val: 0
Please change to “val_split: 12”. If you set “val_split: 0” , and also set “validation_fold: 0”, thus, there will be no training images because all the -fold-000-of-002-xxx files be considered as validation dataset.
So, please modify val_split to split train/val dataset and generate tfrecords again.
kitti_config {
root_directory_path: "/home/saiteja/"
image_dir_name: "data/images"
label_dir_name: "data/labels"
image_extension: ".jpg"
partition_mode: "random"
num_partitions: 2
val_split: 0 --> 12
num_shards: 10
}
Now it can access the TFrecords but it shows,
2022-07-07 06:44:36,190 [INFO] root: Registry: ['nvcr.io']
2022-07-07 06:44:36,544 [INFO] tlt.components.instance_handler.local_instance: Running command in container: nvcr.io/nvidia/tao/tao-toolkit-tf:v3.22.05-tf1.15.4-py3
2022-07-07 06:44:36,658 [WARNING] tlt.components.docker_handler.docker_handler:
Docker will run the commands as root. If you would like to retain your
local host permissions, please add the "user":"UID:GID" in the
DockerOptions portion of the "/home/saiteja/.tao_mounts.json" file. You can obtain your
users UID and GID by using the "id -u" and "id -g" commands on the
terminal.
Using TensorFlow backend.
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
/usr/local/lib/python3.6/dist-packages/requests/__init__.py:91: RequestsDependencyWarning: urllib3 (1.26.5) or chardet (3.0.4) doesn't match a supported version!
RequestsDependencyWarning)
Using TensorFlow backend.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:43: The name tf.train.SessionRunHook is deprecated. Please use tf.estimator.SessionRunHook instead.
2022-07-07 06:44:48,641 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:43: The name tf.train.SessionRunHook is deprecated. Please use tf.estimator.SessionRunHook instead.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/tfhooks/checkpoint_saver_hook.py:25: The name tf.train.CheckpointSaverHook is deprecated. Please use tf.estimator.CheckpointSaverHook instead.
2022-07-07 06:44:48,763 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/tfhooks/checkpoint_saver_hook.py:25: The name tf.train.CheckpointSaverHook is deprecated. Please use tf.estimator.CheckpointSaverHook instead.
2022-07-07 06:44:49,715 [INFO] iva.common.logging.logging: Log file already exists at /home/saiteja/DetectTech/results/status.json
2022-07-07 06:44:49,715 [INFO] root: Starting DetectNet_v2 Training job
2022-07-07 06:44:49,715 [INFO] __main__: Loading experiment spec at /home/saiteja/DetectTech/scripts/train/task2_detectNet_train.cfg.
2022-07-07 06:44:49,717 [INFO] iva.detectnet_v2.spec_handler.spec_loader: Merging specification from /home/saiteja/DetectTech/scripts/train/task2_detectNet_train.cfg
2022-07-07 06:44:49,723 [INFO] root: Training gridbox model.
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:153: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
2022-07-07 06:44:49,724 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:153: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
2022-07-07 06:44:50,298 [INFO] root: Sampling mode of the dataloader was set to user_defined.
2022-07-07 06:44:50,298 [INFO] __main__: Cannot iterate over exactly 4829 samples with a batch size of 16; each epoch will therefore take one extra step.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:107: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.
2022-07-07 06:44:50,301 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:107: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:110: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.
2022-07-07 06:44:50,302 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:110: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:113: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.
2022-07-07 06:44:50,305 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:113: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.
2022-07-07 06:44:50,365 [INFO] root: Building DetectNet V2 model
2022-07-07 06:44:51,357 [INFO] __main__: Training was interrupted.
2022-07-07 06:44:51,357 [INFO] root: Training was interrupted
Time taken to run __main__:main: 0:00:02.591388.
2022-07-07 06:44:53,300 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.
There should be something wrong path for images or labels.
Please login the docker and run again to check the log.
$ tao detectnet_v2 run /bin/bash
then
# detectnet_v2 train xxx
This is the output I got.
Using TensorFlow backend.
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
/usr/local/lib/python3.6/dist-packages/requests/__init__.py:91: RequestsDependencyWarning: urllib3 (1.26.5) or chardet (3.0.4) doesn't match a supported version!
RequestsDependencyWarning)
Using TensorFlow backend.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:43: The name tf.train.SessionRunHook is deprecated. Please use tf.estimator.SessionRunHook instead.
2022-07-07 06:50:39,920 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:43: The name tf.train.SessionRunHook is deprecated. Please use tf.estimator.SessionRunHook instead.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/tfhooks/checkpoint_saver_hook.py:25: The name tf.train.CheckpointSaverHook is deprecated. Please use tf.estimator.CheckpointSaverHook instead.
2022-07-07 06:50:40,044 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/tfhooks/checkpoint_saver_hook.py:25: The name tf.train.CheckpointSaverHook is deprecated. Please use tf.estimator.CheckpointSaverHook instead.
2022-07-07 06:50:40,949 [INFO] iva.common.logging.logging: Log file already exists at /home/saiteja/results/status.json
2022-07-07 06:50:40,949 [INFO] root: Starting DetectNet_v2 Training job
2022-07-07 06:50:40,949 [INFO] __main__: Loading experiment spec at /home/saiteja/scripts/train/task2_detectNet_train.cfg.
2022-07-07 06:50:40,951 [INFO] iva.detectnet_v2.spec_handler.spec_loader: Merging specification from /home/saiteja/scripts/train/task2_detectNet_train.cfg
2022-07-07 06:50:40,956 [INFO] root: Training gridbox model.
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:153: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
2022-07-07 06:50:40,957 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:153: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
2022-07-07 06:50:41,466 [INFO] root: Sampling mode of the dataloader was set to user_defined.
2022-07-07 06:50:41,466 [INFO] __main__: Cannot iterate over exactly 4829 samples with a batch size of 16; each epoch will therefore take one extra step.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:107: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.
2022-07-07 06:50:41,469 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:107: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:110: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.
2022-07-07 06:50:41,469 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:110: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:113: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.
2022-07-07 06:50:41,472 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:113: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.
2022-07-07 06:50:41,527 [INFO] root: Building DetectNet V2 model
2022-07-07 06:50:42,504 [INFO] __main__: Training was interrupted.
2022-07-07 06:50:42,505 [INFO] root: Training was interrupted
Time taken to run __main__:main: 0:00:02.458243.
I am wondering if this has to do anything with training
2022-07-07 06:50:41,466 [INFO] __main__: Cannot iterate over exactly 4829 samples with a batch size of 16; each epoch will therefore take one extra step.
No, it is not related.
Can you share the command and spec file?
got it, the key is wrong in the training time. But I am facing a new issue.
Traceback (most recent call last):
File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 917, in <module>
File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 906, in <module>
File "<decorator-gen-2>", line 2, in main
File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/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 "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 893, in main
File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 757, in run_experiment
File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 645, in train_gridbox
File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 454, in build_gridbox_model
File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/model/detectnet_model.py", line 364, in load_model_weights
File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 358, in get_layer
raise ValueError('No such layer: ' + name)
ValueError: No such layer: output_cov
2022-07-07 07:02:08,719 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.
Spec File:
# Sample model config for to instantiate a resnet18 model with pretrained weights and freeze blocks 0, 1
# with all shortcuts having projection layers.
model_config {
arch: "resnet"
pretrained_model_file: "/home/saiteja/models/resnetarch.tlt"
all_projections: True
num_layers: 18
use_pooling: False
use_batch_norm: True
dropout_rate: 0.0
load_graph: True
objective_set: {
cov {}
bbox {
scale: 35.0
offset: 0.5
}
}
}
# Sample rasterizer configs to instantiate a 2 class bbox rasterizer
bbox_rasterizer_config {
target_class_config {
key: "pedestrian"
value: {
cov_center_x: 0.5
cov_center_y: 0.5
cov_radius_x: 0.4
cov_radius_y: 0.4
bbox_min_radius: 1.0
}
}
target_class_config {
key: "bicycle"
value: {
cov_center_x: 0.5
cov_center_y: 0.5
cov_radius_x: 0.4
cov_radius_y: 0.4
bbox_min_radius: 1.0
}
}
deadzone_radius: 0.67
}
postprocessing_config {
target_class_config {
key: "pedestrian"
value: {
clustering_config {
coverage_threshold: 0.005
dbscan_eps: 0.15
dbscan_min_samples: 0.05
minimum_bounding_box_height: 20
}
}
}
target_class_config {
key: "bicycle"
value: {
clustering_config {
coverage_threshold: 0.005
dbscan_eps: 0.15
dbscan_min_samples: 0.05
minimum_bounding_box_height: 20
}
}
}
}
cost_function_config {
target_classes {
name: "pedestrian"
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
}
}
target_classes {
name: "bicycle"
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: 1.0
}
}
enable_autoweighting: True
max_objective_weight: 0.9999
min_objective_weight: 0.0001
}
training_config {
batch_size_per_gpu: 16
num_epochs: 20
learning_rate {
soft_start_annealing_schedule {
min_learning_rate: 5e-6
max_learning_rate: 5e-4
soft_start: 0.1
annealing: 0.7
}
}
regularizer {
type: NO_REG
weight: 3e-9
}
optimizer {
adam {
epsilon: 1e-08
beta1: 0.9
beta2: 0.999
}
}
cost_scaling {
enabled: False
initial_exponent: 20.0
increment: 0.005
decrement: 1.0
}
}
# Sample augementation config for
augmentation_config {
preprocessing {
output_image_width: 1088
output_image_height: 544
output_image_channel: 3
min_bbox_width: 1.0
min_bbox_height: 1.0
}
spatial_augmentation {
hflip_probability: 0.5
vflip_probability: 0.0
zoom_min: 1.0
zoom_max: 1.0
translate_max_x: 8.0
translate_max_y: 8.0
}
color_augmentation {
color_shift_stddev: 0.0
hue_rotation_max: 25.0
saturation_shift_max: 0.2
contrast_scale_max: 0.1
contrast_center: 0.5
}
}
# Sample evaluation config to run evaluation in integrate mode for the given 2 class model,
# at every 10th epoch starting from the epoch 1.
evaluation_config {
average_precision_mode: INTEGRATE
validation_period_during_training: 20
first_validation_epoch: 5
minimum_detection_ground_truth_overlap {
key: "pedestrian"
value: 0.7
}
minimum_detection_ground_truth_overlap {
key: "bicycle"
value: 0.5
}
evaluation_box_config {
key: "pedestrian"
value {
minimum_height: 4
maximum_height: 9999
minimum_width: 4
maximum_width: 9999
}
}
evaluation_box_config {
key: "bicycle"
value {
minimum_height: 4
maximum_height: 9999
minimum_width: 4
maximum_width: 9999
}
}
}
dataset_config {
data_sources: {
tfrecords_path: "/home/saiteja/tf/-fold*"
image_directory_path: "/home/saiteja/data/images/"
}
image_extension: "jpg"
target_class_mapping {
key: "pedestrian"
value: "pedestrian"
}
target_class_mapping {
key: "bicycle"
value: "bicycle"
}
validation_fold: 0
}
What is resnetarch.tlt?
It’s a resnet18 model that I used during the classification training.
Please remove “load_graph: True” and retry.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.