YOLO_v3_tutorial_from_scratch

YOLO_v3_tutorial_from_scratch copied to clipboard

Anchors scaling for each feature map output

1

https://github.com/ayooshkathuria/YOLO_v3_tutorial_from_scratch/blob/8264dfba39a866998b8936a24133f41f12bfbdb7/util.py#L59 I have a question since yolov3 has anchors for all three different scales. (as they mentioned in paper). Why again we need to down sample the anchors for each...

rjtshrm

> Object detection algorithms for real time car plate recognition

ZaynAlk

How to solve this runtime error problem?

1

I met the problem when I ran the instruction "python3 detect.py --images imgs --det det" What should I do to solve this problem and why it happened? Traceback (most recent...

sunshine-lcc

OpenCV(4.5.2) :-1: error: (-5:Bad argument) in function 'rectangle'

4

Objects Detected: bicycle truck dog ---------------------------------------------------------- Traceback (most recent call last): File "detect.py", line 201, in list(map(lambda x: write(x, loaded_ims), output)) File "detect.py", line 201, in list(map(lambda x: write(x, loaded_ims),...

vineeth357

RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #4 'other' added：prediction = prediction.cuda()

zhiweichen0012

I am trying to run the forward pass on my GPU but it is not working. I wrote a detector class and when I try to run the forward pass...

grok0n

Thanks, Ayoosh! Your Paperspace articles and YouTube videos on implementing YoloV3 from scratch were incredibly helpful. The way you walked through parsing the configuration file and rebuilding the model architecture...

david-littlefield

Run the video.py code

1

Hi ive got the detect.py working but think im using the wrong augments for video.py can someone show me a example thanks

roberthope6186

Why does batch norm layer has the parameter of weight and bias?

2

In this tutorial, when explaining the weight file, it mentioned that if a convolutional layer has batch norm, then it will get 4 parameters from the weight file. The 4...

SanftMonster

Why do we reverse the final dim of the image in "prep_image"?

1

In this tutorial, there is a function preparing the image as below: `def prep_image(img, inp_dim): """ Prepare image for inputting to the neural network. Returns a Variable """ img =...

SanftMonster