Support multiple batches for exporting ONNX with pre-processing

[zhiqwang]

The batch-size argument / parameter is only used for models that include pre-processing. You need to specify the batch sizes and ensure that the number of input images is the same as the batches when inferring if you want to export multiple batches ONNX models.

[codecov]

Codecov Report

Merging #320 (2e0ffe3) into main (61a6e62) will increase coverage by 0.27%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main     #320      +/-   ##
==========================================
+ Coverage   95.10%   95.38%   +0.27%     
==========================================
  Files          11       11              
  Lines         736      759      +23     
==========================================
+ Hits          700      724      +24     
+ Misses         36       35       -1     

Flag	Coverage Δ
unittests	95.38% <100.00%> (+0.27%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
test/test_runtime_ort.py	98.61% <100.00%> (+2.69%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 61a6e62...2e0ffe3. Read the comment docs.