jn12/2026LPCV-Track1-MobileCLIP2-B-Best is the exported ONNX version of the best current MobileCLIP2-B checkpoint used in this LPCV 2026 Track 1 image-to-text retrieval project.
Fuente del modelo
Descripción de la fuente
jn12/2026LPCV-Track1-MobileCLIP2-B-Best is the exported ONNX version of the best current MobileCLIP2-B checkpoint used in this LPCV 2026 Track 1 image-to-text retrieval project.
The full project code is available here:
https://github.com/jn12-29/LPCV-Track1-EfficientAI
That repository contains the complete model training pipeline, together with dataset preparation, ONNX export, local evaluation, and deployment-oriented evaluation code.
Fuentes
1 fuenteVerificado 17 sept
Artefactos del modelo
2 artefactosExtractos de fuentes
2 extractosThe repository provides separated image and text encoders in ONNX format so they can be evaluated locally with ONNX Runtime or compiled further for Qualcomm device workflows.
MobileCLIP2-BThis repository currently provides exported encoder files:
image_encoder.onnximage_encoder.onnx.datatext_encoder.onnxtext_encoder.onnx.dataThese files can be consumed directly by the local evaluation pipeline in this repository.
hf download jn12/2026LPCV-Track1-MobileCLIP2-B-Best \
--local-dir ./pretrained/2026LPCV-Track1-MobileCLIP2-B-Best
Expected local layout:
pretrained/2026LPCV-Track1-MobileCLIP2-B-Best/
├── image_encoder.onnx
├── image_encoder.onnx.data
├── text_encoder.onnx
└── text_encoder.onnx.data
Install dependencies:
pip install onnxruntime pillow numpy torch torchvision transformers
hf download openai/clip-vit-base-patch32
Run evaluation with plain ONNX Runtime:
from pathlib import Path
import numpy as np
import onnxruntime as ort
import torch
import torch.nn.functional as F
from PIL import Image
from torchvision import transforms
from transformers import CLIPTokenizer
MODEL_DIR = Path("./pretrained/2026LPCV-Track1-MobileCLIP2-B-Best")
IMAGE_PATHS = [
"examples/image1.jpg",
"examples/image2.jpg",
]
TEXTS = [
"a red bus on the street",
"a group of people near a building",
"a dog running on grass",
]
def preprocess_image(image_path: str) -> np.ndarray:
transform = transforms.Compose(
[
transforms.Resize((224, 224)),
transforms.ToTensor(),
]
)
image = Image.open(image_path).convert("RGB")
image_tensor = transform(image).unsqueeze(0)
return image_tensor.numpy().astype(np.float32)
def l2_normalize(x: np.ndarray) -> np.ndarray:
return x / np.linalg.norm(x, axis=-1, keepdims=True)
def recall_at_k(image_features: np.ndarray, text_features: np.ndarray, positives, k: int) -> float:
similarities = image_features @ text_features.T
topk = np.argsort(-similarities, axis=1)[:, :k]
hits = 0
for i, gt in enumerate(positives):
if any(j in gt for j in topk[i]):
hits += 1
return hits / len(positives)
image_session = ort.InferenceSession(
str(MODEL_DIR / "image_encoder.onnx"),
providers=["CPUExecutionProvider"],
)
text_session = ort.InferenceSession(
str(MODEL_DIR / "text_encoder.onnx"),
providers=["CPUExecutionProvider"],
)
tokenizer = CLIPTokenizer.from_pretrained(
"openai/clip-vit-base-patch32",
local_files_only=True,
)
tokenizer.add_special_tokens({"cls_token": tokenizer.eos_token})
image_embeddings = []
for image_path in IMAGE_PATHS:
image_input = preprocess_image(image_path)
image_output = image_session.run(None, {"image": image_input})[0]
image_embeddings.append(image_output[0])
image_embeddings = l2_normalize(np.stack(image_embeddings, axis=0))
text_embeddings = []
for text in TEXTS:
token_ids = tokenizer(
[text],
padding="max_length",
truncation=True,
max_length=77,
return_tensors="pt",
)["input_ids"].numpy().astype(np.int32)
text_output = text_session.run(None, {"text": token_ids})[0]
text_embeddings.append(text_output[0])
text_embeddings = l2_normalize(np.stack(text_embeddings, axis=0))
# Example ground-truth mapping:
# image 0 matches text 0, image 1 matches text 1.
positive_text_indices = [{0}, {1}]
r_at_1 = recall_at_k(image_embeddings, text_embeddings, positive_text_indices, k=1)
r_at_2 = recall_at_k(image_embeddings, text_embeddings, positive_text_indices, k=2)
print(f"Recall@1: {r_at_1:.4f}")
print(f"Recall@2: {r_at_2:.4f}")
This repository follows the preprocessing used by the project codebase:
224x224[0, 1] by dividing by 255CLIPTokenizer from openai/clip-vit-base-patch32max_length=77Before running local evaluation, make sure the tokenizer is available in the local Hugging Face cache:
hf download openai/clip-vit-base-patch32
The exported ONNX files come from the LPCV 2026 Track 1 training workflow built around:
MobileCLIP2-B as the base modelThe corresponding image-source dataset is available at:
https://huggingface.co/datasets/jn12/VG100K4CL
Use this model if you want to:
This repository is not intended to be a generic sentence-embedding model release or a universal CLIP drop-in replacement.
If you use this model, please cite the Hugging Face repository and the project code:
Authors:
Hui Xie, Jinyang Du, Jiacheng Wang, Xiaoze Ge, Fengjun Zhong, Yejun Zeng, Ruihao Gong#, Xiaoning Liu, Shenghao Jin, Jinyang Guo#, Xianglong Liu
@misc{mobileclip2b_lpcv2026,
title = {2026LPCV-Track1-MobileCLIP2-B-Best},
author = {Hui Xie and Jinyang Du and Jiacheng Wang and Xiaoze Ge and Fengjun Zhong and Yejun Zeng and Ruihao Gong and Xiaoning Liu and Shenghao Jin and Jinyang Guo and Xianglong Liu},
year = {2026},
howpublished = {\url{https://huggingface.co/jn12/2026LPCV-Track1-MobileCLIP2-B-Best}}
}
Project repository:
https://github.com/jn12-29/LPCV-Track1-EfficientAI
--- license: apple-amlr datasets: - jn12/VG100K4CL metrics: - recall base_model: - timm/MobileCLIP2-B-OpenCLIP library_name: open_clip pipeline_tag: zero-shot-image-classification tags: - clip - mobileclip2 - mobileclip - image-text-retrieval - onnx - qualcomm - qai-hub - lpcv language: - en --- # 2026LPCV-Track1-MobileCLIP2-B-Best `jn12/2026LPCV-Track1-MobileCLIP2-B-Best` is the exported ONNX version of the best current `MobileCLIP2-B` checkpoint used in this LPCV 2026 Track 1 image-to-text retrieval project. The full project code is available here: `https://github.com/jn12-29/LPCV-Track1-EfficientAI` That repository contains the complete model training pipeline, together with dataset preparation, ONNX export, local evaluation, and deployment-oriented evaluation code. The repository provides separated image and text encoders in ONNX format so they can be evaluated locally with ONNX Runtime or compiled further for Qualcomm device workflows. ## Model overview - Base architecture: `MobileCLIP2-B` - Task: image-to-text retrieval - Export format: ONNX - Runtime target: local ONNX evaluation and Qualcomm deployment flow ## Repository contents This repository currently provides exported encoder files: - `image_encoder.onnx` - `image_encoder.onnx.data` - `text_encoder.onnx` - `text_encoder.onnx.data` These files can be consumed directly by the local evaluation pipeline in this repository. ## Download ```bash hf download jn12/2026LPCV-Track1-MobileCLIP2-B-Best \ --local-dir ./pretrained/2026LPCV-Track1-MobileCLIP2-B-Best ``` Expected local layout: ```text pretrained/2026LPCV-Track1-MobileCLIP2-B-Best/ ├── image_encoder.onnx ├── image_encoder.onnx.data ├── text_encoder.onnx └── text_encoder.onnx.data ``` ## Quick usage ### Evaluate locally with ONNX Runtime Install dependencies: ```bash pip install onnxruntime pillow numpy torch torchvision transformers hf download openai/clip-vit-base-patch32 ``` Run evaluation with plain ONNX Runtime: ```python from pathlib import Path import numpy as np import onnxruntime as ort import torch import torch.nn.functional as F from PIL import Image from torchvision import transforms from transformers import CLIPTokenizer MODEL_DIR = Path("./pretrained/2026LPCV-Track1-MobileCLIP2-B-Best") IMAGE_PATHS = [ "examples/image1.jpg", "examples/image2.jpg", ] TEXTS = [ "a red bus on the street", "a group of peo...
Source context: 0 downloads · 0 likes · Pipeline zero-shot-image-classification · Library open_clip · Repo jn12/2026LPCV-Track1-MobileCLIP2-B-Best