SMAP

SMAP copied to clipboard

"If you want to display the visual interface of the root depth graph, how do you write the visualization code? Also, how can you obtain depth information from the root...

lml125

关于遮挡 论文中说有一个refineNet做强化，请问 这种遮挡的点在数据集里如何表示呢？真值如何获得的

tribeband

Pre-trained weights for Panoptic CMU

8

Thanks for the release of your excellent work, could you please provide the model's weights trained with the Panoptic CMU dataset as the first table in your paper presents results...

nicolasugrinovic

Hi, there First of all, thanks for your elaborated work. It helps me a lot :) I found your training sequences over here [#1 comment](https://github.com/zju3dv/SMAP/issues/1#issuecomment-681169368). But, it seems like "160226_ultimatum1"...

shawnpark07

你好，在使用SMAP推断人体根深度我们应该在哪里设置我们的相机参数，FOV？代码中 depth_roots_pred[i] = root_d_upsamp[int(pred_body[root_n][1]), int(pred_body[root_n][0])] * scale['scale'] * scale['f_x'] root_n=2表示的是哪个关节点？ scale['scale'] 与scale['f_x']似乎也是直接从图片中的得到的。 打扰了

simonyy1

I'm not sure that how to ensure that 50% of data in each mini-batch is from COCO in your code?

Darkdawner

I want to use the aug_scale function defined in ImageAugmentation.py, however, some parameters are not provided. Could you please tell me what params_transform['target_dist'] and meta['scale_provided'] means? Thanks!

Zhangjzh

Question about CMU Panoptic dataset sampling configuration

1

Hi, it mentioned that "2400 frames are uniformly sampled". However, not all the number of activity are multiples of 2400. For fair comparion, could provide the index of frame? or...

Juzezhang

Head or nose annotations of CMU Panoptic dataset

4

Hello, it seems some activity used coco19 format, so may different in the annotations of head or nose? Could you tell me how to handle tihis ? or which format...

Juzezhang

Evaluation

5

Thanks for your share. The evaluation metrics used in your paper are very reasonable, and I want to use them to test my own model. Could you share the relevant...

HuiliCui