Can not convert *.etlt to *.engine [[ERROR] Number of optimization profiles does not match model input node number.]

Please provide the following information when requesting support.

• Hardware (RTX2080Ti)
• Network Type: plrnet
• TLT Version
• Training spec file
random_seed: 42
lpr_config {
hidden_units: 512
max_label_length: 15
arch: “baseline”
nlayers: 18 #setting nlayers to be 10 to use baseline10 model
}
training_config {
batch_size_per_gpu: 32
num_epochs: 100
learning_rate {
soft_start_annealing_schedule {
min_learning_rate: 1e-6
max_learning_rate: 1e-4
soft_start: 0.001
annealing: 0.5
}
}
regularizer {
type: L2
weight: 5e-4
}
}
eval_config {
validation_period_during_training: 5
batch_size: 1
}
augmentation_config {
output_width: 96
output_height: 48
output_channel: 3
keep_original_prob: 0.3
transform_prob: 0.5
rotate_degree: 5
}
dataset_config {
data_sources: {
label_directory_path: “/workspace/tlt-experiments/dataset/train/labels”
image_directory_path: “/workspace/tlt-experiments/dataset/train/images”
}
characters_list_file: “/workspace/tlt-experiments/plate_characters_list.txt”
validation_data_sources: {
label_directory_path: “/workspace/tlt-experiments/dataset/val/labels”
image_directory_path: “/workspace/tlt-experiments/dataset/val/images”
}
}
• *When I convert to .engine by using cmd: ./tlt-converter -k nvidia_tlt -p image_input,1x3x48x96,4x3x48x96,16x3x48x96 lprnet_epoch-03.etlt -t fp16 -e lpr_us_onnx_b16.engine
There are error below:
[libprotobuf ERROR /home/jenkins/workspace/OSS/L0_MergeRequest/oss/build/third_party.protobuf/src/third_party.protobuf/src/google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 2:1: Invalid control characters encountered in text.
[libprotobuf ERROR /home/jenkins/workspace/OSS/L0_MergeRequest/oss/build/third_party.protobuf/src/third_party.protobuf/src/google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 2:2: Interpreting non ascii codepoint 145.
[libprotobuf ERROR /home/jenkins/workspace/OSS/L0_MergeRequest/oss/build/third_party.protobuf/src/third_party.protobuf/src/google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 2:2: Expected identifier, got: �
Failed to parse ONNX model from file: /tmp/fileaS0lYk
[ERROR] Number of optimization profiles does not match model input node number.
Aborted (core dumped)

How I can fix it? Many thanks!

To narrow down, can you download the official etlt model and try? See deepstream_lpr_app/download_us.sh at master · NVIDIA-AI-IOT/deepstream_lpr_app · GitHub
wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_lprnet/versions/deployable_v1.0/files/us_lprnet_baseline18_deployable.etlt

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.