Upload README.md with huggingface_hub

README.md

@@ -1,6 +1,3 @@
----
-license: apache-2.0
----
 # ADDP
 The official implementation of the [paper](https://arxiv.org/abs/2306.05423) "ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process" (ICLR 2024).
 
@@ -18,21 +15,6 @@ Image recognition and generation have long been developed independently of each
 
 
 
-## Citation
-
-If this work is helpful for your research, please consider citing the following BibTeX entry.
-
-```
-@article{tian2023addp,
-  title={Addp: Learning general representations for image recognition and generation with alternating denoising diffusion process},
-  author={Tian, Changyao and Tao, Chenxin and Dai, Jifeng and Li, Hao and Li, Ziheng and Lu, Lewei and Wang, Xiaogang and Li, Hongsheng and Huang, Gao and Zhu, Xizhou},
-  journal={arXiv preprint arXiv:2306.05423},
-  year={2023}
-}
-```
-
-
-
 ## Setup
 
 Step 1, download [ImageNet](http://image-net.org/download) dataset, and place it in your `IMAGENET_DIR`.
@@ -59,7 +41,7 @@ The following table provides the performance and weights of the pre-trained chec
 
 |                                    |  ViT-Large    | ViT-Base |
 | ---------------------------------- | ---- | -------- |
-| Checkpoint                         |      |          |
+| Checkpoint                         |  <a href="https://huggingface.co/Changyao/ADDP/blob/main/addp-vit-large-16.pth">this link</a>  |   <a href="https://huggingface.co/Changyao/ADDP/blob/main/addp-vit-base-16.pth">this link</a>    |
 | Class-unconditional Generation FID |  7.6    | 8.9      |
 | Class-unconditional Generation IS  |  105.1    | 95.3     |
 | Fine-tuning Top-1 Accuracy         |  85.9    | 83.9     |
@@ -102,7 +84,6 @@ bash configs/release/base/pretrain_addp_base_1600ep.sh ${GPUS} ${GPUS_PER_NODE}
 ## finetune
 bash configs/release/base/finetune_addp_base_100ep.sh ${GPUS} ${GPUS_PER_NODE} ${JOB_NAME} ${QUOTATYPE} ${PARATITION} exp/release/addp-vit-base-16.pth
 
-
 ## generate
 bash configs/release/base/generate_addp_base_steps20.sh ${GPUS} ${GPUS_PER_NODE} ${JOB_NAME} ${QUOTATYPE} ${PARATITION} exp/release/addp-vit-base-16.pth
 ```
@@ -127,7 +108,18 @@ Then use the above package to evaluate FID/IS of the images generated by our mod
 fidelity --isc --fid --input1 ${GENERATED_IMAGES_DIR} --input2 ${IMAGENET256X256_DIR}
 ```
 
+## Citation
 
+If this work is helpful for your research, please consider citing the following BibTeX entry.
+
+```
+@article{tian2023addp,
+  title={Addp: Learning general representations for image recognition and generation with alternating denoising diffusion process},
+  author={Tian, Changyao and Tao, Chenxin and Dai, Jifeng and Li, Hao and Li, Ziheng and Lu, Lewei and Wang, Xiaogang and Li, Hongsheng and Huang, Gao and Zhu, Xizhou},
+  journal={arXiv preprint arXiv:2306.05423},
+  year={2023}
+}
+```
 
 
 ## License
@@ -136,4 +128,4 @@ This repository is released under the Apache 2.0 license as found in the [LICENS
 
 ## Contact
 
-If you have any questions, feel free to contact me through email (tcyhost@link.cuhk.edu.hk) directly.
+If you have any questions, feel free to contact me through email (tcyhost@link.cuhk.edu.hk) directly.