litert-community/convnext_large

Convnext Large

ConvNeXt Large model designed as a powerful, pure convolutional alternative to Vision Transformers (ViTs) for high-end computer vision tasks. Originally introduced by Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie. in the modernized paper, A ConvNet for the 2020s, this model adopts "Transformer-like" design choices—such as depthwise convolutions with large kernels, inverted bottlenecks, and GELU activation—to achieve state-of-the-art scalability. With approximately 198M parameters and 34.4 GFLOPs, it competes favorably with large-scale hierarchical Transformers like Swin-L, offering superior simplicity and efficiency for detection and segmentation.

Model description

The model was converted from a checkpoint from PyTorch Vision.

The original model has:
acc@1 (on ImageNet-1K): 84.414%
acc@5 (on ImageNet-1K): 96.976%
num_params: 197767336

Intended uses & limitations

The model files were converted from pretrained weights from PyTorch Vision. The models may have their own licenses or terms and conditions derived from PyTorch Vision and the dataset used for training. It is your responsibility to determine whether you have permission to use the models for your use case.

How to Use

​​1. Install Dependencies

Ensure your Python environment is set up with the required libraries. Run the following command in your terminal

pip install numpy Pillow huggingface_hub ai-edge-litert

2. Prepare Your Image

The script expects an image file to analyze. Make sure you have an image (e.g., cat.jpg or car.png) saved in the same working directory as your script.

3. Save the Script

Create a new file named classify.py, paste the script below into it, and save the file:

#!/usr/bin/env python3
import argparse, json
import numpy as np
from PIL import Image
from huggingface_hub import hf_hub_download
from ai_edge_litert.compiled_model import CompiledModel

def preprocess(img: Image.Image) -> np.ndarray:
    img = img.convert("RGB")
    w, h = img.size
    s = 232
    if w < h:
        img = img.resize((s, int(round(h * s / w))), Image.BILINEAR)
    else:
        img = img.resize((int(round(w * s / h)), s), Image.BILINEAR)
    left = (img.size[0] - 224) // 2
    top = (img.size[1] - 224) // 2
    img = img.crop((left, top, left + 224, top + 224))

    x = np.asarray(img, dtype=np.float32) / 255.0
    x = (x - np.array([0.485, 0.456, 0.406], dtype=np.float32)) / np.array(
        [0.229, 0.224, 0.225], dtype=np.float32
    )
    return np.expand_dims(x, axis=0)

def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--image", required=True)
    args = ap.parse_args()

    model_path = hf_hub_download("litert-community/convnext_large", “convnext_large.tflite")
    labels_path = hf_hub_download(
        "huggingface/label-files", "imagenet-1k-id2label.json", repo_type="dataset"
    )
    with open(labels_path, "r", encoding="utf-8") as f:
        id2label = {int(k): v for k, v in json.load(f).items()}

    img = Image.open(args.image)
    x = preprocess(img)

    model = CompiledModel.from_file(model_path)
    inp = model.create_input_buffers(0)
    out = model.create_output_buffers(0)

    inp[0].write(x)
    model.run_by_index(0, inp, out)

    req = model.get_output_buffer_requirements(0, 0)
    y = out[0].read(req["buffer_size"] // np.dtype(np.float32).itemsize, np.float32)

    pred = int(np.argmax(y))
    label = id2label.get(pred, f"class_{pred}")

    print(f"Top-1 class index: {pred}")
    print(f"Top-1 label: {label}")
if __name__ == "__main__":
    main()

4. Execute the Python Script

Run the below command

python classify.py --image cat.jpg

BibTeX entry and citation info

@misc{liu2022convnet2020s,
      title={A ConvNet for the 2020s}, 
      author={Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
      year={2022},
      eprint={2201.03545},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2201.03545}, 
}