Hello, This is indeed a fascinating piece of work, and I appreciate the outstandin

Hi! <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url=

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

Why do you use segmentation labels instead of bounding boxes in the COCO dataset? about dynamicdet HOT 3 OPEN

vdigpku commented on August 17, 2024

Why do you use segmentation labels instead of bounding boxes in the COCO dataset?

from dynamicdet.

Comments (3)

LZHgrla commented on August 17, 2024

Hi! @gongyan1
We use the same loss from yolov7, and do not involve seg labels.

Could you show the related code about the seg labels?

from dynamicdet.

gongyan1 commented on August 17, 2024

@LZHgrla
Dear Lin,

Thank you for reaching out. However, when I downloaded the COCO labels mentioned in your readme, I found that they are not stored as four values of x, y, w, h as expected but rather as many values, and the number of values per line is inconsistent. Therefore, my question is, given that one txt file corresponds to one image and each line corresponds to one object, if these are bounding boxes, they should all be in the common format of class_id x y w h.

from dynamicdet.

LZHgrla commented on August 17, 2024

@gongyan1
The COCO labels mentioned in our README are for downloading segmentation labels. However, during the training process, the segmentation labels will be processed into bounding box labels.

DynamicDet/utils/datasets.py

Lines 488 to 496 in 4dbb9b2

 with open(lb_file, 'r') as f: 

 l = [x.split() for x in f.read().strip().splitlines()] 

 if any([len(x) > 8 for x in l]): # is segment 

 classes = np.array([x[0] for x in l], dtype=np.float32) 

 segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in l] # (cls, xy1...) 

 l = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh) 

 l = np.array(l, dtype=np.float32) 

 if len(l): 

 assert l.shape[1] == 5, 'labels require 5 columns each'

You can also directly download bounding box labels here, https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017labels.zip

from dynamicdet.

Recommend Projects

Why do you use segmentation labels instead of bounding boxes in the COCO dataset? about dynamicdet HOT 3 OPEN

Comments (3)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

	with open(lb_file, 'r') as f:
	l = [x.split() for x in f.read().strip().splitlines()]
	if any([len(x) > 8 for x in l]): # is segment
	classes = np.array([x[0] for x in l], dtype=np.float32)
	segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in l] # (cls, xy1...)
	l = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh)
	l = np.array(l, dtype=np.float32)
	if len(l):
	assert l.shape[1] == 5, 'labels require 5 columns each'