Chengjian Feng
Chengjian Feng
As shown in Figure 5, the final depth is sampled from the real depth, so the range of the real depth (i.e., [0, dr]) must contain the range of the...
I also get a worse performance (mAP: 63.06). Did you find the factors of the performance drop and reproduce the performance of the paper? Thanks.
Same question
@X-Lai where is the interface website?
@Fang-2021 We fine-tune Stable Diffusion on 8 A100.
The off-the-shelf detectors are solely trained on images from a restricted set of base categories, resulting in their limited capacity to detect novel categories. In contrast, InstaGen has the capability...
> > The off-the-shelf detectors are solely trained on images from a restricted set of base categories, resulting in their limited capacity to detect novel categories. In contrast, InstaGen has...
Package Version Location ---------------------- --------------- ------------------------------------------------------------------------------------------------------------------------- addict 2.4.0 albumentations 1.2.1 appdirs 1.4.4 argon2-cffi 21.3.0 argon2-cffi-bindings 21.2.0 asynctest 0.13.0 attributee 0.1.5 attrs 21.4.0 backcall 0.2.0 beautifulsoup4 4.11.1 bleach 5.0.0 braceexpand 0.1.7...
Hi @LeonG7, you can refer to the 'Image demo' and 'Video demo' in the [docs](https://github.com/fcjian/promptdet/blob/master/docs/1_exist_data_model.md).
Could you please send me the path of your COCO dataset？