Origin_Light issues

Results 11 issues of


                                            Origin_Light

CondaSSLError: Encountered an SSL error. Most likely a certificate verification issue. Exception: [SSL: DECRYPTION_FAILED_OR_BAD_RECORD_MAC] decryption failed or bad record mac (_ssl.c:2548)

when i want to create a new python enviroment,a error i can not solve by my own: CondaSSLError: Encountered an SSL error. Most likely a certificate verification issue. Exception: [SSL:...

I think the performance of your model is not as high as Condinst

conditional convolutions for instance segmentation.it's ap(mean) on coco test is 40.1.

Which config corresponds to the centernet * proposed in the paper

## 📚 Documentation Issue Which config corresponds to the centernet * proposed in the paper? Is there a config for this model? You mentioned in your paper that you were...

documentation

What is your split of the dataset?

The download dataset: ![2](https://github.com/yumingj/Text2Human/assets/55913193/3c9c0acc-c592-45ce-9074-ebb68f3412a8) But your instruction has train and test, how do you split it? very thanks! ![1](https://github.com/yumingj/Text2Human/assets/55913193/f999c57b-7c30-4e09-96a2-6a908a530817)

Errors occurred while training and evaluating the model During training: TypeError: init () missing 2 required keyword-only arguments: 'bg_ cls_ loss_ weight' and 'openset_ test' When profiling: KeyError: 'naiveSyncBN_ N'

During training： Traceback (most recent call last): File "train_net.py", line 246, in args=(args,), File "/media/cheng/dataset4/annaconda3/envs/clip/lib/python3.7/site-packages/detectron2-RegionCLIP-py3.7-linux-x86_64.egg/detectron2/engine/launch.py", line 82, in launch main_func(*args) File "train_net.py", line 203, in main model = build_model(cfg) File...

Origin_Light

CondaSSLError: Encountered an SSL error. Most likely a certificate verification issue. Exception: [SSL: DECRYPTION_FAILED_OR_BAD_RECORD_MAC] decryption failed or bad record mac (_ssl.c:2548)

I think the performance of your model is not as high as Condinst

Which config corresponds to the centernet * proposed in the paper

What is your split of the dataset?

Errors occurred while training and evaluating the model During training: TypeError: init () missing 2 required keyword-only arguments: 'bg_ cls_ loss_ weight' and 'openset_ test' When profiling: KeyError: 'naiveSyncBN_ N'

how to run the train without comet apikey?

where is the pretrained CLIP model? Thank you!

Are you ready to release the pretrained model?

Do you have plan to release train code?

How to evaluate the performance?