To get started using this repo quickly using a Google Cloud Platform (GCP) Deep Learning Virtual Machine (VM) follow the instructions below. New GCP users are eligible for a $300 free credit offer. Other quickstart options for this repo include our [Google Colab Notebook](https://colab.research.google.com/github/ultralytics/yolov3/blob

hello大家好，我是该仓库的作者。鉴于我复现tensorflow-yolov3踩了太多坑，特此发个贴，帮助大家少走弯路。大家有问题可以在下面留言。

Thanks for your tutorial from scratch. It helps me a lot.
In article part 3, there are some codes you wrote. I copy that codes but some error for me.

model = Darknet("cfg/yolov3.cfg")
inp = get_test_input()
pred = model(inp)
print (pred)

TypeError: forward() missing 1 required positional argument: 'CUDA'

and I want to ask you that training module is the only left work

In model.py file https://github.com/wizyoung/YOLOv3_TensorFlow/blob/c8c40615e0cdf00deea065fc89c3e93909c1a88a/model.py#L123, you used rescaled anchors and then the output will be multiplied by the ratio.

And rescaled anchors are anchors divided by ratio.

So, If we are going to use (anchors / ratio) for multiplication and then (ratio) for again multiplying with output, then why are you using

with video_demo.py about 20% speed compared to your 1.0 repo. but thanks much for sharing!

The 2x down-sampling is one of the important operations in reference models. But, a convolution or a pooling with stride=2, padding='SAME' may result in different outputs over different deep learning libraries (e.g., TensorFlow, CNTK, Theano, Caffe, Torch, ...) due to their different padding behaviors.

For example (TensorNets syntax; but can be regarded as pseudo codes for other libraries),

original code :

img = ori_img.astype(np.float)/255.
img = cv2.resize(img, self.size)
img = torch.from_numpy(img).float().permute(2,0,1).unsqueeze(0)
img = img.to(self.device)
with torch.no_grad():
            out_boxes = self.net(img)

I suggest using：

from PIL import Image
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
from torch.au

I would like to pass the array values, inside the filtered_boxes dictionary, to the tf.image.crop_to_bounding_box() function, and crop the detected images.
But the format of the values in the array is unclear. That is, i am unsure which of the values are top left, top right, width and height. Could you please help with the format. Thanks.

I see you have added gaussian_yolov3_layer and yolo detection gaussian_box.(from this paper https://arxiv.org/abs/1904.04620)

can you provide a wiki or same example prototxts to explain how to use gaussian yolo correctly

thank you very much

I need to convert Yolo model to OpenVINO format for opencv/cvat/auto_annotation.
I use opencv CVAT for auto annotation https://github.com/opencv/cvat/tree/develop/cvat/apps/auto_annotation.

To annotate a task with a custom model I need to prepare 4 files:

1. Model config (*.xml) - a text file with network configuration.
2. Model weights (*.bin) - a binary file with trained weights.
3. Label