Zihan Zhong

Hard to reproduce the results of GLUE benchmark

15

Thanks for your excellent work. I tried to do grid search on the settings that you described in your paper and codes, but it is still hard for me to...

[WIP] Inference function of MMOCRAutoModelForTextRecognition

2

Implementation of MMOCR ([Kuang et al, (2021)](https://arxiv.org/pdf/2108.06543.pdf)) in automm for ocr text recognition. This implementation supports single-image inference. The model can be accessed through specifying the checkpoint's name, like "abinet_academic"....

Evaluation code

1

Thank you for your excellent work. I wonder if you have a plan to release the evaluation code.

The text label on the visualization image is not complete

1

Hi, thank you for your excellent work. When I run the Grounded-Segment-Anything demo, the text prompt that I use is "pottedplant"; however, the text label that appears on the resulting...

[WIP] Code implementation of Conv-LoRA

1

*Issue #, if available:* *Description of changes:* By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

Hard to reproduce the zero-shot results on COCO dataset.

2

Hi, could you please provide the range of the learning rate, or other hyper-parameter settings for the zero-shot experiments on the COCO-20i dataset? It is difficult to reproduce the results...

Evaluation problem on zero-shot COCO dataset

3

Thank you for your excellent work. But I have one question about evaluation. When I run evaluation on COCO dataset for zero-shot setting, I found that if I set the...

禁止访问：“project-367116221053”的请求无效

3

点开授权时的返回的网址，会报错。

Hi, I try `python repmlpnet.py`, and set the size of x at [100, 3, 224, 224]. But I find the deviation between the new_y and origin_y is 0.0019, which is...

[WIP][AutoMM] Add the trick that dropping the modality randomly during training.

4

*Issue #, if available:* *Description of changes:* By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.