Nvidia TAO Emotion Model File Not Loaded

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hello,

I’m having trouble loading the TAO Model.

APP: deepstream-emotion-app

CONFIG FILE:

enginePath=/models/emotion.etlt_b32_gpu0_fp16.engine
etltPath=/models/emotion.etlt
etltKey=nvidia_tlt

#tlt-model-key=nvidia_tlt
#tlt-encoded-model=/models/emotion.tlt

#networkMode can be int8, fp16 or fp32
networkMode=fp16
batchSize=32
inputWidth=136
inputHeight=1
inputType=
label=0,neutral
label=1,happy
label=2,surprise
label=3,squint
label=4,disgust
label=5,scream

image

ERROR:

NvDsInferCudaEngineGetFromTltModel: Failed to open TLT encoded model file /models/emotion.etlt
ERROR: [TRT]: 3: [builder.cpp::~Builder::341] Error Code 3: API Usage Error (Parameter check failed at: optimizer/api/builder.cpp::~Builder::341, condition: mObjectCounter.use_count() == 1. Destroying a builder object before destroying objects it created leads to undefined behavior.
)

3

Could you refer to our demo code: sample_emotion_model_config.txt？You need to ensure that the absolute or relative path you configured is correct.

4

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.