DiffusionDet

DiffusionDet copied to clipboard

Training time

1

Hi, Thanks for sharing your great work. May I know the training time of each model if possible? Many thanks!

jxhuang0508

What the `ddim_step` does in the Algorithm 2 of the paper

5

Hi~, I wonder to know what the DDIM does in the `ddim_step` of Algorithm 2 of the paper. Could you describe intuitionally how the DDIM changes the `pred_bboxes`. I don't...

GT9505

Because this repo has just been created and has not been edited much yet, I wanted to edit it with Black so that the format is clear.

SadeghPouriyanZadeh

Inference Speed

5

Hi, I have used pretrained model but its inference speed is not good. (using COLAB) (Tesla T4 GPU) video dimensions: 4096 × 1080 getting speed (1.20s/it) 1.20 sec per frame....

fa16-030

The signal scaling in the training stage

3

Hi, Thanks for sharing your wonderful work. I can't understand the signal scaling equation `pb = (pb * 2 - 1) * scale` in the training stage, can you explain...

pengxinliu

add a notebook inference file

SadeghPouriyanZadeh

About training loss

5

In DDIM or DDPM, there are losses (KL-Divergence) to constrain the diffused outputs during training steps to be Gaussian distributions. I thought it is the base for DDIM sampling (the...

huilicici

cannot import name 'create_ddp_model' from 'detectron2.engine'

1

I encountered an error in training: ImportError: cannot import name 'create_ddp_model' from 'detectron2.engine' (/home/jddx/wxp/sizecnn/detectron2/engine/__init__.py) can you help me ?

wmrenr

Questions about DDIM's performance

1

Hi, Thanks for sharing your wonderful work. I have trouble figuring out the effectiveness of the DDIM process discussed in the paper. Since there is no related ablation study in...

LOLTATQAQ

log about training

3

Thanks for your great work! I want to reproduce the result but I don't know what the proper loss (l1, giou...) will be trained to at the final epoch. Could...

AmadeusSTQ