Views
No views yet
MobileCLIP2-S4 matches the accuracy of SigLIP-SO400M/14 with 2x fewer parameters and surpasses DFN ViT-L/14 at 2.5x lower latency measured on iPhone12 Pro Max.MobileCLIP-S3/S4 are our new architectures trained on MobileCLIP’s training dataset, DataCompDR-1B (dashed lines).MobileCLIP-S0 obtains similar zero-shot performance as OpenAI's ViT-B/16 model while being 4.8x faster and 2.8x smaller.MobileCLIP-S2 obtains better avg zero-shot performance than SigLIP's ViT-B/16 model while being 2.3x faster and 2.1x smaller, and trained with 3x less seen samples.MobileCLIP-B (LT) attains zero-shot ImageNet performance of 77.2% which is significantly better than recent works like DFN and SigLIP with similar architectures or even OpenAI's ViT-L/14@336.| Model | # Seen Samples (B) | # Params (M) (img + txt) | Latency (ms) (img + txt) | IN-1k Zero-Shot Top-1 Acc. (%) | Avg. Perf. (%) on 38 datasets |
|---|---|---|---|---|---|
| MobileCLIP2-S0 | 13 | 11.4 + 63.4 | 1.5 + 3.3 | 71.5 | 59.7 |
| MobileCLIP2-S2 | 13 | 35.7 + 63.4 | 3.6 + 3.3 | 77.2 | 64.1 |
| MobileCLIP2-B | 13 | 86.3 + 63.4 | 10.4 + 3.3 | 79.4 | 65.8 |
| MobileCLIP2-S3 | 13 | 125.1 + 123.6 | 8.0 + 6.6 | 80.7 | 66.8 |
| MobileCLIP2-L/14 | 13 | 304.3 + 123.6 | 57.9 + 6.6 | 81.9 | 67.8 |
| MobileCLIP2-S4 | 13 | 321.6 + 123.6 | 19.6 + 6.6 | 81.9 | 67.5 |
| MobileCLIP-S0 | 13 | 11.4 + 42.4 | 1.5 + 1.6 | 67.8 | 58.1 |
| MobileCLIP-S1 | 13 | 21.5 + 63.4 | 2.5 + 3.3 | 72.6 | 61.3 |
| MobileCLIP-S2 | 13 | 35.7 + 63.4 | 3.6 + 3.3 | 74.4 | 63.7 |
| MobileCLIP-B | 13 | 86.3 + 63.4 | 10.4 + 3.3 | 76.8 | 65.2 |
| MobileCLIP-B (LT) | 36 | 86.3 + 63.4 | 10.4 + 3.3 | 77.2 | 65.8 |
| MobileCLIP-S3 | 13 | 125.1 + 123.6 | 8.0 + 6.6 | 78.3 | 66.3 |
| MobileCLIP-L/14 | 13 | 304.3 + 123.6 | 57.9 + 6.6 | 79.5 | 66.9 |
| MobileCLIP-S4 | 13 | 321.6 + 123.6 | 19.6 + 6.6 | 79.4 | 68.1 |
Files and versions tab, and download the PyTorch checkpoint.
For programmatic downloading, if you have huggingface_hub installed, you can also run:hf download apple/mobileclip2_coca_dfn2b_s13b_<finetune-dataset>_context<length>config.json to src/open_clip/model_configs/coca_ViT-L-14-context$len.json and change the model name in below example to coca_ViT-L-14-context$len.1import torch
2import open_clip
3from PIL import Image
4
5model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
6model.eval()
7
8image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)
9
10with torch.no_grad(), torch.cuda.amp.autocast():
11 syn_text = model.generate(
12 image,
13 generation_type="top_p",
14 top_p=0.9,
15 fixed_output_length=True
16 )[0]
17 syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
18print("Caption:", syn_text)