This PR addresses a mistake made in the iou calculation. The original method of calculating intersection will lead to incorrect iou value.

For example, considering two boxes that do not overlap each other in [x1, y1, x2, y2] format: [0, 0, 10, 10] and [20, 20, 30, 30]: using the original formula: inter = (min(10, 30) - max(0, 20)) * (min(10, 30) - max(0, 20)) = 100. However, it's clear that the intersection of [0, 0, 10, 10] and [20, 20, 30, 30] should be 0.

I believe the loss implementation uses the official Pytorch implementation as reference, from the intersection calculation of official implementation, you can see the correct way of calculating intersection:

inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
            (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)

This PR will make sure intersection calculation is the same as the official implementation, and will fix the #2

In the prepare_data.py line 151 we are calling VOCParser.parse_xml but there is no method parse_xml in the VOCParser class. I think it should be called the method parse in VOCParser class should be called here. I checked it by replacing with parse method and its working good.

Bumps pyyaml from 5.3.1 to 5.4.

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

❔Question

I exported a saved_model from YoloV5 and tried to use it with this. Using detect.py with the exported model, I got the following error:

InvalidArgumentError: cannot compute Pack as input #3(zero-based) was expected to be a float tensor but is a int32 tensor [Op:Pack] name: packed

at the following line in detect.py pred_bbox = [tf.reshape(x, (tf.shape(x)[0], -1, tf.shape(x)[-1])) for x in pred_bbox]

Have anyone had any success moving model from the other yolov5 to this one's?

EDIT: I included nms within the exported model, which isn't compatible with the code here.

Description

This PR ...

Checklist

• [ ] Linked issues (if existing)
• [ ] Added/modified tests
• [ ] Used pre-commit hooks when committing to ensure that code is compliant with hooks. Install hooks with pre-commit install. To run hooks independent of commit, execute pre-commit run --all-files

Make sure to have fun coding!

❔Question

Hello!

Thank you for the project! I'd be happy to know, do you plan to attach some kind of LICENSE to it? MIT perhaps?

Thank you, Ben

Additional context

when executing - ! python train.py, there's an error showing up - [Errno 2] No such file or directory: '../data/voc2012/VOCdevkit/VOC2012/train.txt'

I tried to look for the .txt file in the given directory, but I couldn't find it. Did anyone else have this same issue?

I also checked the read_data.py script, but I cant seem to find the directory linked to it. How to resolve this issue.

To be clear here's the entire error:

Traceback (most recent call last): File "/home/jovyan/Yolov5/yolo/train.py", line 153, in DataReader = DataReader(params['train_annotations_dir'], img_size=params['img_size'], transforms=transforms, File "/home/jovyan/Yolov5/yolo/dataset/read_data.py", line 21, in init self.annotations = self.load_annotations(annotations_dir) File "/home/jovyan/Yolov5/yolo/dataset/read_data.py", line 65, in load_annotations with open(annotations_dir, 'r') as f: FileNotFoundError: [Errno 2] No such file or directory: '../data/voc2012/VOCdevkit/VOC2012/train.txt'

❔Question

is it enough to change "yolo-m-mish.yaml" part, when i want to use different yolo structures (e.g yolo-s-mish.yaml or yolo-l-mish.yaml) in config.py in line: parser.add_argument('--yaml_dir', type=str, default='configs/yolo-m-mish.yaml', help='model.yaml path')

Additional context

❔Looking for weights for yolov5 and how to minimize training loss

Are there existing weights which can be used ? And I have seen that you linked the weights from yolov4, do you have any advice on how to use them with this model?

Additionally what would you consider a "good" loss ? I currently have a loss of about 200 which seems a bit high and yields results wich are not that good. How can i improve my loss ? Thank you for your help!

In Yolov5/yolo/dataset/augment_data.py Yolov5/yolo/dataset/augment_data.py", line 103 M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT What operation it is doing?

And can I save the trained model and use that for further uses.

Thanks

Thank you for the wonderful project. Can you please show what is the meaning of number 6 in this line of code?

https://github.com/LongxingTan/Yolov5/blob/88acfd988decc4cc78335cfb6eb50f1975294c1f/yolo/dataset/label_anchor.py#L35

❔Question

Which is working for your code? I have been looking around the internet and couldn't find the TensorFlow(2.x) or Keras's weights or model. It would be nice you could provide it. Otherwise, there is no way to see if your repo works or not. Thanks.

Additional context