Questions on TensorRT 2.1.2


Some questions on TensorRT 2.1.2 :

I have read the user guide for the TensorRT 2.1.2 Section 3.5 : SampleInt8 - Calibration and 8-bit inference
I have some doubts now:

  1. What does 1000 batch files batch0 to batch999 contain ?
  2. If there are 1000 batch files, how many images are there inside it ? I guess 10000 images since I built batches with the test dataset.
  3. “The calibration dataset must be representative of input data at runtime” - To validate this arguement, How does TensorRT selects all possible input images representatives since it only takes first 0-500 images for calibration dataset.
  4. If the first 10 batches of size 50, (500 images) are taken as calibration dataset, does TensorRT runs inference on the images except calibration dataset ?
  5. The user guide mentions 1000 iterations to generate 1003 batch files, why is it so ? Why 1000 ? What does it affect if I do only 1 iteration ?
  6. What is the role batch size play in inference in TensorRT ? I saw some presentations which indicates batch size is a major factor for inference time improvement. Why ?
  7. Can sampleInt8 example be used for inference for CIFAR and IMAGENET?

Thanks in advance

Still waiting

Can anyone please answer?