36 lines
1.3 KiB
YAML
36 lines
1.3 KiB
YAML
Collections:
|
|
- Name: CAE
|
|
Metadata:
|
|
Training Data: ImageNet-1k
|
|
Training Techniques:
|
|
- AdamW
|
|
Training Resources: 16x A100-80G GPUs
|
|
Architecture:
|
|
- ViT
|
|
Paper:
|
|
URL: https://arxiv.org/abs/2202.03026
|
|
Title: "Context Autoencoder for Self-Supervised Representation Learning"
|
|
README: configs/selfsup/cae/README.md
|
|
|
|
Models:
|
|
- Name: cae_vit-base-p16_8xb256-fp16-coslr-300e_in1k
|
|
In Collection: CAE
|
|
Metadata:
|
|
Epochs: 300
|
|
Batch Size: 2048
|
|
Results: null
|
|
Config: configs/selfsup/cae/cae_vit-base-p16_16xb128-amp-coslr-300e_in1k.py
|
|
Weights: https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220825-404a1929.pth
|
|
Downstream:
|
|
- Type: Image Classification
|
|
Metadata:
|
|
Epochs: 100
|
|
Batch Size: 1024
|
|
Results:
|
|
- Task: Fine-tuning
|
|
Dataset: ImageNet-1k
|
|
Metrics:
|
|
Top 1 Accuracy: 60.8
|
|
Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k.py
|
|
Weights: https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.pth
|