Jimes

how to train PRN with my own scanned 3d face data?

1

if I have lots of scanned 3d face datas using 3d camera , how to train the pr net ? what is the pipeline and how to build the new...

How to deploy the quantized model?

1

When we have trained the quantization model, how to deploy it in cpu backend?

How to deploy the quantized model?

5

When we have trained the quantization model, how to deploy it?

A bug is about "SO_TORCH_LIBRARY_FRAGMENT " when I install the tool

3

torchlsq/csrc/ops/lsq.cpp:137:26: error: expected constructor, destructor, or type conversion before ‘(’ token SO_TORCH_LIBRARY_FRAGMENT(torchlsq, m)

how to get the train file?

2

I can't find the train data files of "BLIVA/bliva/data/llava/bliva_llava_150k.json" and "BLIVA/bliva/data/ocrVQA/cleaned_train_dataset.json". Can you tell me how to download them? Thanks!

how about the ablation study

2

In your paper, from the table of “Results of adding individual techniques of our framework in text-rich VQA benchmarks“，I get the improvement vals of +7.40% ，+31.72%，etc. I want to know...

about instructBlip run scripts file

1

Can you provide the run scripts of the instructBlip for us to train and evaluate?

provide the models for evaluation

2

Can you provide BoxSup-C2_Lbase_CLIP_R5021k_640b64_4x_mlr.pth，Detic_LbaseI_CLIP_R5021k_640b64_4x_ft4x_max-size_mlr.pth and Detic_OVCOCO_CLIP_R50_1x_max-size_caption_mlr.pth for us to evaluate directly?

How to get resources/coco_there_is_a_cls_vitb32.pt?

1

I want to know where you get the file resource/coco_there_is_a_cls_vitb32.pt . And if you create it by yourself , please tell me how to do that. Thanks a lot!