Modelpublic

litert-community/shufflenet_v2_x2_0

sourceHugging Faceupdated 4mo agoView on Hugging Face

2likes14downloads

Model Card

ShuffleNet V2 x2.0

ShuffleNet V2 x2.0 model designed for high-performance applications on edge devices where both accuracy and latency are critical. Originally introduced by Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng, Jian Sun in the influential paper, **ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design** this model scales the architecture to a 2.0x complexity multiplier, doubling the feature channels to significantly boost representational power. It achieves a Top-1 accuracy of approximately 76.2% on ImageNet-1K with roughly 0.58 GFLOPs and 7.4M parameters, maintaining high hardware efficiency through its optimized "channel split" and "channel shuffle" building blocks.

Model description

The model was converted from a checkpoint from PyTorch Vision.

The original model has: acc@1 (on ImageNet-1K): 76.23% acc@5 (on ImageNet-1K): 93.006% num_params: 7393996

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:

bash

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:

python

#!/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/shufflenet_v2_x2_0", "shufflenet_v2_x2_0.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:

bash

python classify.py --image cat.jpg

BibTeX entry and citation info

bibtex

@misc{ma2018shufflenetv2practicalguidelines,
      title={ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design}, 
      author={Ningning Ma and Xiangyu Zhang and Hai-Tao Zheng and Jian Sun},
      year={2018},
      eprint={1807.11164},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/1807.11164}, 
}