Amit Dedhia

Sorry about that. ``` Python version 3.9.12 (tags/v3.9.12:b28265d, Mar 23 2022, 23:52:46) [MSC v.1929 64 bit (AMD64)] Platform win32 PyMuPDF 1.20.0: Python bindings for the MuPDF 1.20.1 library. Version date:...

Using option PDF_REDACT_IMAGES_NONE or PDF_REDACT_IMAGES_REMOVE did not work. Tried like this: `page.apply_redactions(images=PDF_REDACT_IMAGE_NONE)` However, the original code in my yesterday's post works fine with PyMuPdf version 1.19.6 So not sure if...

The issue did not occur with the document I had attached in this conversation previously. However, that document was generated by taking out one page from the original document and...

Okay here is the new document. This one results in access violation error. [new_20220816.pdf](https://github.com/pymupdf/PyMuPDF/files/9347932/new_20220816.pdf) Environment details: ``` PyMuPDF 1.20.2: Python bindings for the MuPDF 1.20.3 library. Version date: 2022-08-13 00:00:01....

Okay, thank you for the information. When is the next version of MuPDF likely to release? Is there any tentative date?

I tried setting up the command from django admin UI instead of manual settings, got the same behaviour and results. I can see the task results for first successful run.

**Question** - typically how many epochs are good enough for QAT fine tuning? And do we need to supply loads of images for training (like say 5000), or few can...

_***Question***_ - suppose I performed QAT for say n epochs. Then (before calling `torch.quantization.Convert`) generated model output. Then called `torch.quantization.Convert`. And again generated output. Will the two outputs be same?...

I raised this issue on discussion forum as well. Please refer [here ](https://discuss.pytorch.org/t/qnnpack-accuracy-very-poor-on-unet-model/93601) for more details on the issue.