xmba15 / yolov3_pytorch

bird detection by yolov3

Pytorch Implementation of Yolov3 For Bird Detection

---

This project provides a dataset for wild birds and yolov3 implementation in pytorch for training the dataset. This bird detection dataset is special in the sense that it also provides the dense labels of birds in flock. The images of birds are collected from the internet, partly by crawling. Label samples can be seen as followings.

Label Samples

TODO

---

• Train on Bird Dataset
• Export onnx weight and test inferencing on onnx weight
• Train on multiple scales
• Mish activation
• Onnx Model

Preparation

---

python3 -m pip install -r requirements.txt

• Download darknet53 backbone trained on imagenet dataset

python3 scripts/download_darknet_weight.py

After running this script, darknet53.conv.74 weights will be saved inside save_models directory.

• Download bird dataset

python3 scripts/download_bird_dataset.py

The bird dataset will be saved and extracted in data directory

Scripts

---

• Training (details for parameters please see train.py script)

python3 train.py --dataset bird_dataset --backbone_weight_path ./saved_models/darknet53.conv.74

Weights will be saved inside save_models directory.

• Testing

python3 test.py --dataset bird_dataset --snapshot [path/to/snapshot] --image_path [path/to/image] --conf_thresh [confidence/thresh] --nms_thresh [nms/thresh]

A sample trained weight can be download from HERE

Test Result

• Export to onnx model

python3 export_onnx.py --dataset bird_dataset --snapshot [path/to/weight/snapshot] --batch_size [batch/size] --onnx_weight_file [output/onnx/file]

• Inferece with onnx

python3 inference_onnx.py --dataset bird_dataset --img_h [img/input/height] --img_w [img/input/width] --image_path [image/path] --onnx_weight_file [onnx/weight] --conf_thresh [confidence/threshold] --nms_thresh [nms_threshold]

References

---

• Yolov3

yolov3_pytorch's Issues

Can you give me dataset for bird detection

Hello sir, can you give me dataset for project bird detection , because file download dataset in scripts can not run. Thanks sir.

Dataset

Can you provide me pls a link to the dataset you used?

how to run the training on multiple gpus?

Can't download bird dataset

Hi there,

Trying to set things up and it looks like I can't download the bird dataset zip. Here's the output when I run the download script:

1it [00:00, 1500.11it/s]
Archive:  bird_dataset.zip
  End-of-central-directory signature not found.  Either this file is not
  a zipfile, or it constitutes one disk of a multi-part archive.  In the
  latter case the central directory and zipfile comment will be found on
  the last disk(s) of this archive.
unzip:  cannot find zipfile directory in one of bird_dataset.zip or
        bird_dataset.zip.zip, and cannot find bird_dataset.zip.ZIP, period.

I'm assuming this has to do with how you download it from Drive, or maybe just that the zip isn't even available anymore.

TypeError: __init__() got an unexpected keyword argument 'multiscale' while training on custom dataset

Query about Source and Origin of Bird Dataset

Hello @xmba15 ,

Firstly, I want to express my appreciation for the hard work you've put into providing the bird dataset with bounding box annotations. It has been a great resource for my research.

However, I am writing this issue to inquire about the source or origin of this dataset. I couldn't find this information in the README or any other documentation, and I think it's crucial for my project to have a clear understanding of the data provenance.

Additionally, I'm curious whether the bounding box annotations are original to your dataset or if they've been added to an existing bird dataset. This is important for me to understand, as it may have implications for the usage and further development of my project.

Any information you can provide about the source of the dataset and the bounding box annotations would be greatly appreciated.

Looking forward to your response.

Best,
@jet-c-21