Twilighter9527

inference

4

when I run the generate_beam for the caption,there are many space in the caption，Do you know why, thank you. 

Evaluate problem

4

It's a very nice work,can you provide the code for evaluation it? I don't know how to evaluate it. Thank you!

when i follow this [https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/LayoutLMv2/RVL-CDIP/Fine_tuning_LayoutLMv2ForSequenceClassification_on_RVL_CDIP.ipynb](url) load the RVL_CDIP for LayoutLMv3ForSequenceClassification. I find the load time is very slow(For hours) and have some warning. Change the batch_size still don't work. Can...

The model size does not change

3

When I follow this [https://www.deepspeed.ai/tutorials/model-compression/#2-tutorial-for-zeroquant-efficient-and-affordable-post-training-quantization](url) run the zero_quant.sh or (quant_activation.sh and quant_weight.sh), the model size still is 418mb as the bert-base.  the clean_model weight still save as float32? Can...