Duplicate from timm/vit_base_patch32_clip_448.laion2b_ft_in12k_in1k

Co-authored-by: Ross Wightman <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,168 @@
+---
+tags:
+- image-classification
+- timm
+library_name: timm
+license: apache-2.0
+datasets:
+- imagenet-1k
+- laion-2b
+- imagenet-12k
+---
+# Model card for vit_base_patch32_clip_448.laion2b_ft_in12k_in1k
+
+A Vision Transformer (ViT) image classification model. Pretrained on LAION-2B image-text pairs using OpenCLIP. Fine-tuned on ImageNet-12k and then ImageNet-1k in `timm`. See recipes in [Reproducible scaling laws](https://arxiv.org/abs/2212.07143).
+
+
+## Model Details
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 88.3
+  - GMACs: 17.2
+  - Activations (M): 16.5
+  - Image size: 448 x 448
+- **Papers:**
+  - OpenCLIP: https://github.com/mlfoundations/open_clip
+  - Reproducible scaling laws for contrastive language-image learning: https://arxiv.org/abs/2212.07143
+  - LAION-5B: An open large-scale dataset for training next generation image-text models: https://arxiv.org/abs/2210.08402
+  - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
+- **Dataset:** ImageNet-1k
+- **Pretrain Dataset:**
+  - LAION-2B
+  - ImageNet-12k
+
+## Model Usage
+### Image Classification
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model('vit_base_patch32_clip_448.laion2b_ft_in12k_in1k', pretrained=True)
+model = model.eval()
+
+# get model specific transforms (normalization, resize)
+data_config = timm.data.resolve_model_data_config(model)
+transforms = timm.data.create_transform(**data_config, is_training=False)
+
+output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1
+
+top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
+```
+
+### Image Embeddings
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model(
+    'vit_base_patch32_clip_448.laion2b_ft_in12k_in1k',
+    pretrained=True,
+    num_classes=0,  # remove classifier nn.Linear
+)
+model = model.eval()
+
+# get model specific transforms (normalization, resize)
+data_config = timm.data.resolve_model_data_config(model)
+transforms = timm.data.create_transform(**data_config, is_training=False)
+
+output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor
+
+# or equivalently (without needing to set num_classes=0)
+
+output = model.forward_features(transforms(img).unsqueeze(0))
+# output is unpooled, a (1, 197, 768) shaped tensor
+
+output = model.forward_head(output, pre_logits=True)
+# output is a (1, num_features) shaped tensor
+```
+
+## Model Comparison
+Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
+
+## Citation
+```bibtex
+@software{ilharco_gabriel_2021_5143773,
+  author       = {Ilharco, Gabriel and
+                  Wortsman, Mitchell and
+                  Wightman, Ross and
+                  Gordon, Cade and
+                  Carlini, Nicholas and
+                  Taori, Rohan and
+                  Dave, Achal and
+                  Shankar, Vaishaal and
+                  Namkoong, Hongseok and
+                  Miller, John and
+                  Hajishirzi, Hannaneh and
+                  Farhadi, Ali and
+                  Schmidt, Ludwig},
+  title        = {OpenCLIP},
+  month        = jul,
+  year         = 2021,
+  note         = {If you use this software, please cite it as below.},
+  publisher    = {Zenodo},
+  version      = {0.1},
+  doi          = {10.5281/zenodo.5143773},
+  url          = {https://doi.org/10.5281/zenodo.5143773}
+}
+```
+```bibtex
+@article{cherti2022reproducible,
+  title={Reproducible scaling laws for contrastive language-image learning},
+  author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
+  journal={arXiv preprint arXiv:2212.07143},
+  year={2022}
+}
+```
+```bibtex
+@inproceedings{schuhmann2022laionb,
+  title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
+  author={Christoph Schuhmann and
+          Romain Beaumont and
+          Richard Vencu and
+          Cade W Gordon and
+          Ross Wightman and
+          Mehdi Cherti and
+          Theo Coombes and
+          Aarush Katta and
+          Clayton Mullis and
+          Mitchell Wortsman and
+          Patrick Schramowski and
+          Srivatsa R Kundurthy and
+          Katherine Crowson and
+          Ludwig Schmidt and
+          Robert Kaczmarczyk and
+          Jenia Jitsev},
+  booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
+  year={2022},
+  url={https://openreview.net/forum?id=M3Y74vmsMcY}
+}
+```
+```bibtex
+@article{dosovitskiy2020vit,
+  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
+  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
+  journal={ICLR},
+  year={2021}
+}
+```
+```bibtex
+@misc{rw2019timm,
+  author = {Ross Wightman},
+  title = {PyTorch Image Models},
+  year = {2019},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  doi = {10.5281/zenodo.4414861},
+  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
+}
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "architecture": "vit_base_patch32_clip_448",
+  "num_classes": 1000,
+  "num_features": 768,
+  "global_pool": "token",
+  "pretrained_cfg": {
+    "tag": "laion2b_ft_in12k_in1k",
+    "custom_load": false,
+    "input_size": [
+      3,
+      448,
+      448
+    ],
+    "fixed_input_size": true,
+    "interpolation": "bicubic",
+    "crop_pct": 1.0,
+    "crop_mode": "center",
+    "mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "num_classes": 1000,
+    "pool_size": null,
+    "first_conv": "patch_embed.proj",
+    "classifier": "head"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b637111126f3557cd93e1b33af80dd1a7ae713e74cc30aa41abefe6f6b2312b
+size 353365756

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c080dbc3ae19656bbba11616f67fc53fc7b9c1aaf60627bb0591e762c41262d0
+size 353372645

train_args.yaml

@@ -0,0 +1,119 @@
+aa: rand-m10-inc1-mstd101
+amp: true
+aot_autograd: false
+apex_amp: false
+aug_repeats: 0
+aug_splits: 0
+batch_size: 512
+bce_loss: false
+bce_target_thresh: null
+bn_eps: null
+bn_momentum: null
+channels_last: false
+checkpoint_hist: 10
+class_map: ''
+clip_grad: 3.0
+clip_mode: norm
+color_jitter: 0.4
+cooldown_epochs: 10
+crop_pct: 1.0
+cutmix: 0.0
+cutmix_minmax: null
+data_dir: /data/imagenet/
+dataset: ''
+dataset_download: false
+decay_epochs: 100
+decay_milestones:
+- 30
+- 60
+decay_rate: 0.1
+dist_bn: reduce
+drop: 0.0
+drop_block: null
+drop_connect: null
+drop_path: 0.1
+epoch_repeats: 0.0
+epochs: 50
+eval_metric: top1
+experiment: ''
+fast_norm: false
+fuser: ''
+gp: null
+grad_checkpointing: true
+hflip: 0.5
+img_size: 448
+in_chans: null
+initial_checkpoint: ''
+input_size: null
+interpolation: ''
+jsd_loss: false
+layer_decay: 0.75
+local_rank: 0
+log_interval: 50
+log_wandb: false
+lr: 0.0001
+lr_cycle_decay: 0.5
+lr_cycle_limit: 1
+lr_cycle_mul: 1.0
+lr_k_decay: 1.0
+lr_noise: null
+lr_noise_pct: 0.67
+lr_noise_std: 1.0
+mean: null
+min_lr: 5.0e-07
+mixup: 0.0
+mixup_mode: batch
+mixup_off_epoch: 0
+mixup_prob: 1.0
+mixup_switch_prob: 0.5
+model: vit_base_patch32_clip.laion2b_ft_in12k
+model_ema: true
+model_ema_decay: 0.9998
+model_ema_force_cpu: false
+momentum: 0.9
+native_amp: false
+no_aug: false
+no_ddp_bb: false
+no_prefetcher: false
+no_resume_opt: false
+num_classes: 1000
+opt: adamw
+opt_betas: null
+opt_eps: null
+output: ''
+patience_epochs: 10
+pin_mem: false
+pretrained: true
+ratio:
+- 0.75
+- 1.3333333333333333
+recount: 1
+recovery_interval: 0
+remode: pixel
+reprob: 0.3
+resplit: false
+resume: ''
+save_images: false
+scale:
+- 0.08
+- 1.0
+sched: cosine
+seed: 42
+smoothing: 0.1
+split_bn: false
+start_epoch: null
+std: null
+sync_bn: false
+torchscript: false
+train_interpolation: random
+train_split: train
+tta: 0
+use_multi_epochs_loader: false
+val_split: validation
+validation_batch_size: null
+vflip: 0.0
+warmup_epochs: 10
+warmup_lr: 1.0e-06
+weight_decay: 0.01
+worker_seeding: all
+workers: 8