RGBD-SOD/bbsnet

Model Card for Model ID

Model Details

Model Description

• Developed by: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

• Repository: https://github.com/DengPingFan/BBS-Net
• Paper [optional]: BBS-Net: RGB-D salient object detection with a bifurcated backbone strategy network, 2020
• Demo [optional]: [More Information Needed]

Uses

Direct Use

from typing import Dict

import numpy as np
from datasets import load_dataset
from matplotlib import cm
from PIL import Image
from torch import Tensor
from transformers import AutoImageProcessor, AutoModel

model = AutoModel.from_pretrained("RGBD-SOD/bbsnet", trust_remote_code=True)
image_processor = AutoImageProcessor.from_pretrained(
    "RGBD-SOD/bbsnet", trust_remote_code=True
)
dataset = load_dataset("RGBD-SOD/test", "v1", split="train", cache_dir="data")

index = 0

"""
Get a specific sample from the dataset

sample = {
    'depth': <PIL.PngImagePlugin.PngImageFile image mode=L size=640x360>, 
    'rgb': <PIL.PngImagePlugin.PngImageFile image mode=RGB size=640x360>, 
    'gt': <PIL.PngImagePlugin.PngImageFile image mode=L size=640x360>, 
    'name': 'COME_Train_5'
}
"""
sample = dataset[index]

depth: Image.Image = sample["depth"]
rgb: Image.Image = sample["rgb"]
gt: Image.Image = sample["gt"]
name: str = sample["name"]


"""
1. Preprocessing step

preprocessed_sample = {
    'rgb': tensor([[[[-0.8507, ....0365]]]]), 
    'gt': tensor([[[[0., 0., 0...., 0.]]]]), 
    'depth': tensor([[[[0.9529, 0....3490]]]])
}
"""
preprocessed_sample: Dict[str, Tensor] = image_processor.preprocess(sample)

"""
2. Prediction step

output = {
    'logits': tensor([[[[-5.1966, ...ackward0>)
}
"""
output: Dict[str, Tensor] = model(
    preprocessed_sample["rgb"], preprocessed_sample["depth"]
)

"""
3. Postprocessing step
"""
postprocessed_sample: np.ndarray = image_processor.postprocess(
    output["logits"], [sample["gt"].size[1], sample["gt"].size[0]]
)
prediction = Image.fromarray(np.uint8(cm.gist_earth(postprocessed_sample) * 255))

"""
Show the predicted salient map and the corresponding ground-truth(GT)
"""
prediction.show()
gt.show()

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

@inproceedings{fan2020bbs,
  title={BBS-Net: RGB-D salient object detection with a bifurcated backbone strategy network},
  author={Fan, Deng-Ping and Zhai, Yingjie and Borji, Ali and Yang, Jufeng and Shao, Ling},
  booktitle={Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XII},
  pages={275--292},
  year={2020},
  organization={Springer}
}

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]