|
a |
|
b/configs/dpt/dpt.yml |
|
|
1 |
Collections: |
|
|
2 |
- Name: dpt |
|
|
3 |
Metadata: |
|
|
4 |
Training Data: |
|
|
5 |
- ADE20K |
|
|
6 |
Paper: |
|
|
7 |
URL: https://arxiv.org/abs/2103.13413 |
|
|
8 |
Title: Vision Transformer for Dense Prediction |
|
|
9 |
README: configs/dpt/README.md |
|
|
10 |
Code: |
|
|
11 |
URL: https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/decode_heads/dpt_head.py#L215 |
|
|
12 |
Version: v0.17.0 |
|
|
13 |
Converted From: |
|
|
14 |
Code: https://github.com/isl-org/DPT |
|
|
15 |
Models: |
|
|
16 |
- Name: dpt_vit-b16_512x512_160k_ade20k |
|
|
17 |
In Collection: dpt |
|
|
18 |
Metadata: |
|
|
19 |
backbone: ViT-B |
|
|
20 |
crop size: (512,512) |
|
|
21 |
lr schd: 160000 |
|
|
22 |
inference time (ms/im): |
|
|
23 |
- value: 96.06 |
|
|
24 |
hardware: V100 |
|
|
25 |
backend: PyTorch |
|
|
26 |
batch size: 1 |
|
|
27 |
mode: FP32 |
|
|
28 |
resolution: (512,512) |
|
|
29 |
Training Memory (GB): 8.09 |
|
|
30 |
Results: |
|
|
31 |
- Task: Semantic Segmentation |
|
|
32 |
Dataset: ADE20K |
|
|
33 |
Metrics: |
|
|
34 |
mIoU: 46.97 |
|
|
35 |
mIoU(ms+flip): 48.34 |
|
|
36 |
Config: configs/dpt/dpt_vit-b16_512x512_160k_ade20k.py |
|
|
37 |
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/dpt/dpt_vit-b16_512x512_160k_ade20k/dpt_vit-b16_512x512_160k_ade20k-db31cf52.pth |