Add model
Browse files- README.md +51 -0
- config.json +35 -0
- pytorch_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- image-classification
|
| 4 |
+
- timm
|
| 5 |
+
library_tag: timm
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
datasets:
|
| 8 |
+
- imagenet-1k
|
| 9 |
+
- imagenet-12k
|
| 10 |
+
---
|
| 11 |
+
# Model card for convnext_tiny.in12k_ft_in1k_384
|
| 12 |
+
|
| 13 |
+
A ConvNeXt image classification model. Pretrained in `timm` on ImageNet-12k (a 11821 class subset of full ImageNet-22k) and fine-tuned on ImageNet-1k by Ross Wightman.
|
| 14 |
+
|
| 15 |
+
ImageNet-12k training done on TPUs thanks to support of the [TRC](https://sites.research.google/trc/about/) program.
|
| 16 |
+
|
| 17 |
+
Fine-tuning performed on 8x GPU [Lambda Labs](https://lambdalabs.com/) cloud instances.
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
## Model Details
|
| 21 |
+
- **Model Type:** Image classification / feature backbone
|
| 22 |
+
- **Model Stats:**
|
| 23 |
+
- Params (M): 28.6
|
| 24 |
+
- GMACs: 13.1
|
| 25 |
+
- Activations (M): 39.5
|
| 26 |
+
- Image size: 384 x 384
|
| 27 |
+
- **Dataset:** ImageNet-1k
|
| 28 |
+
- **Pretrain Dataset:** ImageNet-12k
|
| 29 |
+
- **Papers:**
|
| 30 |
+
- A ConvNet for the 2020s: https://arxiv.org/abs/2201.03545
|
| 31 |
+
|
| 32 |
+
## Citation
|
| 33 |
+
```
|
| 34 |
+
@misc{rw2019timm,
|
| 35 |
+
author = {Ross Wightman},
|
| 36 |
+
title = {PyTorch Image Models},
|
| 37 |
+
year = {2019},
|
| 38 |
+
publisher = {GitHub},
|
| 39 |
+
journal = {GitHub repository},
|
| 40 |
+
doi = {10.5281/zenodo.4414861},
|
| 41 |
+
howpublished = {\url{https://github.com/rwightman/pytorch-image-models}}
|
| 42 |
+
}
|
| 43 |
+
```
|
| 44 |
+
```
|
| 45 |
+
@article{liu2022convnet,
|
| 46 |
+
author = {Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
|
| 47 |
+
title = {A ConvNet for the 2020s},
|
| 48 |
+
journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
|
| 49 |
+
year = {2022},
|
| 50 |
+
}
|
| 51 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architecture": "convnext_tiny",
|
| 3 |
+
"num_classes": 1000,
|
| 4 |
+
"num_features": 768,
|
| 5 |
+
"pretrained_cfg": {
|
| 6 |
+
"tag": "in12k_ft_in1k_384",
|
| 7 |
+
"custom_load": false,
|
| 8 |
+
"input_size": [
|
| 9 |
+
3,
|
| 10 |
+
384,
|
| 11 |
+
384
|
| 12 |
+
],
|
| 13 |
+
"fixed_input_size": false,
|
| 14 |
+
"interpolation": "bicubic",
|
| 15 |
+
"crop_pct": 1.0,
|
| 16 |
+
"crop_mode": "squash",
|
| 17 |
+
"mean": [
|
| 18 |
+
0.485,
|
| 19 |
+
0.456,
|
| 20 |
+
0.406
|
| 21 |
+
],
|
| 22 |
+
"std": [
|
| 23 |
+
0.229,
|
| 24 |
+
0.224,
|
| 25 |
+
0.225
|
| 26 |
+
],
|
| 27 |
+
"num_classes": 1000,
|
| 28 |
+
"pool_size": [
|
| 29 |
+
12,
|
| 30 |
+
12
|
| 31 |
+
],
|
| 32 |
+
"first_conv": "stem.0",
|
| 33 |
+
"classifier": "head.fc"
|
| 34 |
+
}
|
| 35 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c60d9c01a01d9d7acfb74b84e707b6d894b47010176e8d6b73b4eeef0f668fb
|
| 3 |
+
size 114420885
|