Eason

Do I have to do PTQ before QAT with pytorch_quantization toolkit?

7

In the only example provided in the toolkit, it loaded the PTQ calibrated weights and did the QAT based on it. There isn't a standalone QAT example without PTQ. I...

Mismatched type error when generating an engine for a quantized stereo-depth model

11

onnx model : [link](https://drive.google.com/file/d/1xJyU7CnVqzc8tBU0_ruewTD1fgxrz1EA/view?usp=sharing) used trtexec to generate the engine: trtexec --onnx=test_quant_sim.onnx --saveEngine=test_quant_sim.engine --workspace=4096 --int8 --fp16 --noTF32 --verbose --noDataTransfers --separateProfileRun --dumpProfile --useCudaGraph > test_quant_sim.log When generating the engine for this...

Subnormal FP16 value detected

6

When using TRT8.4 to generate a model with FP16 precision, following warning occurred: [07/27/2022-23:16:56] [W] [TRT] Weights [name=Conv_13703 + Add_13709 + onnx::Mul_4732_clone_3 + (Unnamed Layer* 7047) [Shuffle] + Mul_13729.weight] had...

How will TRT utilize the optical flow accelerator?

1

the new announcement says that the Ada architecture will come with 300 OFA units that is dedicated to accelerate optical flow applications (according to the documentation, stereo matching can use...

question about excluding "seasonsforest_winter_easy" from the "tartan_air" training dataset

1

Hi, I realized that you excluded this subset from the tartan_air, could you share the reason why you did so? and why only "easy" not "hard"? Thanks!