Please provide the following information when requesting support.
• Hardware (RTX3090)
• Network Type (Classification)
• TLT Version (latest)
Running the Image classification jupyter notebook inference is done on the trained and retrained model. I want to evaluate how my model performs after exporting it to INT8. When changing the Julyter notebok from
!tao classification inference -e $SPECS_DIR/classification_retrain_spec.cfg
-m $USER_EXPERIMENT_DIR/output_rertrain/weights/resnet_$EPOCH.tlt \
to
!tao classification inference -e $SPECS_DIR/classification_retrain_spec.cfg
-m $USER_EXPERIMENT_DIR/export/final_model.etlt \ (or the created final_model.trt
I’m getting this error: “Invalid model file extension. /workspace/tao-experiments/classification/export/final_model.tlt”
Is it possible to do inference on a etlt or trt model and if so, how?