52 lines
2.0 KiB
YAML
52 lines
2.0 KiB
YAML
Collections:
|
|
- Name: MILAN
|
|
Metadata:
|
|
Training Data: ImageNet-1k
|
|
Training Techniques:
|
|
- AdamW
|
|
Training Resources: 16x A100-80G GPUs
|
|
Architecture:
|
|
- ViT
|
|
Paper:
|
|
URL: https://arxiv.org/pdf/2208.06049
|
|
Title: "MILAN: Masked Image Pretraining on Language Assisted Representation"
|
|
README: configs/milan/README.md
|
|
|
|
Models:
|
|
- Name: milan_vit-base-p16_16xb256-amp-coslr-400e_in1k
|
|
In Collection: MILAN
|
|
Metadata:
|
|
Epochs: 400
|
|
Batch Size: 4096
|
|
Results: null
|
|
Config: configs/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py
|
|
Weights: https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth
|
|
Downstream:
|
|
- vit-base-p16_milan-pre_8xb128-coslr-100e_in1k
|
|
- vit-base-p16_milan-pre_8xb2048-linear-coslr-100e_in1k
|
|
|
|
- Name: vit-base-p16_milan-pre_8xb128-coslr-100e_in1k
|
|
In Collection: MILAN
|
|
Metadata:
|
|
Epochs: 100
|
|
Batch Size: 1024
|
|
Results:
|
|
- Task: Image Classification
|
|
Dataset: ImageNet-1k
|
|
Metrics:
|
|
Top 1 Accuracy: 85.3
|
|
Config: configs/milan/benchmarks/vit-base-p16_8xb128-coslr-100e_in1k.py
|
|
Weights: https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth
|
|
- Name: vit-base-p16_milan-pre_8xb2048-linear-coslr-100e_in1k
|
|
In Collection: MILAN
|
|
Metadata:
|
|
Epochs: 100
|
|
Batch Size: 16384
|
|
Results:
|
|
- Task: Image Classification
|
|
Dataset: ImageNet-1k
|
|
Metrics:
|
|
Top 1 Accuracy: 78.9
|
|
Config: configs/milan/benchmarks/vit-base-p16_8xb2048-linear-coslr-100e_in1k.py
|
|
Weights: https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth
|