wangpichao

排序能出个专题介绍吗？谢谢

Could you share the training script for training volo_d5 ↑512? how long will it take on 8 GPUs?

how to get Annocations/DET/train/ILSVRC2013_train_extra0/ILSVRC2013_train_0000001.xml

2

how to get such files as Annocations/DET/train/ILSVRC2013_train_extra0/ILSVRC2013_train_0000001.xml? many thanks.

You do not use NativeScaler and ModelEma for training?

3

You do not use NativeScaler and ModelEma for training?

Could you provide the codes for qualitative analysis? like the demo in your project? Thanks.

what does the upgrade accuracy mean?

1

what does the upgrade accuracy mean? do you mean your released code can directly reproduce the upgraded accuracy?

Missing key(s) in state_dict when testing using predict_downstream_condition.py

7

python predict_downstream_condition.py --ckpt_path model_name_roberta-base_taskname_qqp_lr_3e-05_seed_42_numsteps_2000_sample_Categorical_schedule_mutual_hybridlambda_0.0003_wordfreqlambda_0.0_fromscratch_False_timestep_none_ckpts/best\(38899\).th using standard schedule with num_steps: 2000. Traceback (most recent call last): File "predict_downstream_condition.py", line 101, in model.load_state_dict(ckpt['model']) File "/opt/conda/envs/diff/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1672, in load_state_dict self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError:...

When will release the codes?

1

Do you plan to release the codes? if yes, when will you release it? Thanks.