Darkflow: Is it possible to use yolov3 test and how to modify the code?

Created on 15 May 2018  路  8Comments  路  Source: thtrieu/darkflow

Is it possible to use yolov3 test and how to modify the code?

Most helpful comment

U must implement some new layers and some new features in the yolov3 paper which is not easy.
Until now it is unavailable.

All 8 comments

Hello, I am trying this as well and it looks that something is missing in the cfg
Parsing ../darknet/cfg/yolov3-tiny.cfg
Layer [yolo] not implemented

Hello, I am trying this as well and it looks that something is missing in the cfg
Parsing ./cfg/yolov3.cfg
Layer [shortcut] not implemented

U must implement some new layers and some new features in the yolov3 paper which is not easy.
Until now it is unavailable.

Parsing ./cfg/yolo.cfg
Layer [shortcut] not implemented

Parsing ./cfg/yolov3-tiny.cfg
Layer [yolo] not implemented

no solution yet?

Parsing ./cfg/yolov3.cfg
Layer [shortcut] not implemented

For those wanting to convert Yolo-v3 from Darknet to TensorFlow:

Yolo-v3 support was recently added to DW2TF (see this PR).

Worth noting that unlike Darkflow which is also a runtime env for training/inference, DW2TF can only convert a Darknet model & weights to TensorFlow. Running training/inference on it would then be up to the user.

Any solution to Layer [shortcut] not implemented??

Still facing the issue

Was this page helpful?
0 / 5 - 0 ratings

Related issues

ShawnDing1994 picture ShawnDing1994  路  4Comments

wonny2001 picture wonny2001  路  4Comments

Khobzer picture Khobzer  路  5Comments

pribadihcr picture pribadihcr  路  5Comments

Kowasaki picture Kowasaki  路  4Comments