prismformore/Multi-Task-Transformer
Code of ICLR2023 paper "TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding" and ECCV2022 paper "Inverted Pyramid Multi-task Transformer for Dense Scene Understanding"
PythonMIT
Issues
- 1
Metric of edge detection
#34 opened by Wyt-ong - 0
configs file of InvPT based on ViT-Base
#33 opened by Rook1ex - 3
Where is the code of paper TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts
#28 opened by hongge831 - 1
Channel Task Prompts Wrong
#32 opened by AaronCIH - 1
- 0
- 0
cannot import name 'iou3d_cuda'
#27 opened by bizheyandebing - 2
depth files on NYUDv2
#25 opened by HIT-LiuChen - 0
- 2
TypeError: TaskPrompter.__init__() got an unexpected keyword argument 'default_cfg'
#24 opened by op1009 - 2
Dataset link is down
#22 opened by zsh2000 - 1
- 4
- 7
The inference process is stuck.
#20 opened by PengtaoJiang - 3
how to get bodyparts from images?
#18 opened by hosnasattar - 5
- 8
- 0
model weigths
#17 opened by hosnasattar - 3
odsf code.
#5 opened by tb2-sy - 1
Error with reading pre trained weight
#14 opened by sevaraMS - 3
ViT-B version
#13 opened by tb2-sy - 9
- 1
Human Parts
#12 opened by 187185537 - 7
Inference
#10 opened by sumantha-NTS - 1
- 1
script error
#8 opened by cenchaojun - 1
Script for swin baselines
#7 opened by tb2-sy - 7
odsF get the better results 76.8
#6 opened by tb2-sy - 7
RuntimeError: value cannot be converted to type float without overflow: (1.37209e-09,-4.45819e-10)
#4 opened by tb2-sy - 2
load state_dict failed
#1 opened by nomorecoding - 5
- 4
Questions regarding code for DAVIS demo
#2 opened by j2k0618