Skip to content

Test: nvidia_deeplearningexamples_ssd 번역 #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Test: nvidia_deeplearningexamples_ssd 번역 #1

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a8db3ca
Test: nvidia_deeplearningexamples_ssd 번역
cpprhtn Jul 20, 2022
a955521
nvidia_deeplearningexamples_ssd 피드백 반영
cpprhtn Jul 27, 2022
cf3e5d3
Fix: 피드백 재반영
cpprhtn Jul 27, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 10 additions & 15 deletions nvidia_deeplearningexamples_ssd.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,27 +20,22 @@ demo-model-link: https://huggingface.co/spaces/pytorch/SSD

### Model Description

This SSD300 model is based on the
[SSD: Single Shot MultiBox Detector](https://arxiv.org/abs/1512.02325) paper, which
describes SSD as “a method for detecting objects in images using a single deep neural network".
The input size is fixed to 300x300.
SSD300 모델은 "단일 심층 신경망을 사용하여 이미지에서 물체를 감지하는 방법"으로 설명 하는 [SSD: Single Shot MultiBox Detector](https://arxiv.org/abs/1512.02325) 논문을 기반으로 합니다. 입력 크기는 300x300으로 고정되어 있습니다.
Copy link

@woodywarhol9 woodywarhol9 Jul 27, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SSD300은 "단일 심층 신경망을 사용하여 이미지에서 물체를 감지하는 방법"인 [SSD: Single Shot MultiBox Detector](https://arxiv.org/abs/1512.02325)에 기반한 모델입니다.
라고 번역하면 어떨까요??!

Copy link
Author

@cpprhtn cpprhtn Jul 27, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

오. 읽기 편해졌네요!! 감사합니다 👍


The main difference between this model and the one described in the paper is in the backbone.
Specifically, the VGG model is obsolete and is replaced by the ResNet-50 model.
이 모델과 논문에 설명된 모델의 큰 차이점은 백본에 있습니다. 논문에서 사용한 VGG 모델은 더 이상 사용되지 않으며 ResNet-50 모델로 대체되었습니다.
Copy link

@Lee-JaeWon Lee-JaeWon Jul 25, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

튜토리얼 번역 규칙을 참고했는데, 백본(backbone) 처럼 백본 정도의 단어는 영어와 함께 작성하는 것이 도움이 될 것 같습니다.!

이 모델과 논문에 설명된 모델의 큰 차이점은 백본(backbone)에 있습니다. 논문에서 사용한 VGG 모델은 더 이상 사용되지 않으며 ResNet-50 모델로 대체되었습니다.

Copy link
Author

@cpprhtn cpprhtn Jul 25, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

오 좋은의견 감사합니다! 반영하겠습니다 :)


From the
[Speed/accuracy trade-offs for modern convolutional object detectors](https://arxiv.org/abs/1611.10012)
paper, the following enhancements were made to the backbone:
* The conv5_x, avgpool, fc and softmax layers were removed from the original classification model.
* All strides in conv4_x are set to 1x1.
[Speed/accuracy trade-offs for modern convolutional object detectors](https://arxiv.org/abs/1611.10012) 논문에서 , 백본에 대해 다음과 같은 개선이 이루어졌습니다.:

* conv5_x, avgpool, fc 및 softmax 레이어는 기존의 분류 모델에서 제거되었습니다.
* conv4_x의 모든 strides는 1x1로 설정됩니다.

백본 뒤에는 5개의 컨볼루션 레이어가 추가됩니다. 또한 컨볼루션 레이어 외에도 6개의 detection heads를 추가했습니다.
The backbone is followed by 5 additional convolutional layers.
In addition to the convolutional layers, we attached 6 detection heads:
* The first detection head is attached to the last conv4_x layer.
* The other five detection heads are attached to the corresponding 5 additional layers.
* 첫 번째 detection head는 마지막 conv4_x 레이어에 연결됩니다.
* 나머지 5개의 detection head는 추가되는 5개의 컨볼루션 레이어에 부착됩니다.

Detector heads are similar to the ones referenced in the paper, however,
they are enhanced by additional BatchNorm layers after each convolution.
Detector heads는 논문에서 언급된 것과 유사하지만, 각각의 컨볼루션 레이어 뒤에 BatchNorm 레이어를 추가함으로써 성능이 향상됩니다.

### Example

Expand Down