I tried pytorch-caffe-darknet-convert but failed due to lack of reorg layer and issue of concate layer support (of course, I created an issue to ask but no one replied me). Next I think three available solutions below:
try to write code supporting reorg layer and fix the issue of concate layer in pytorch-caffe-darknet-convert
try to convert darknet-yolov2 to tensorflow first (darkflow gives concrete command about how to translate) such as darkflow and then to caffe next (use MMdnn)
As we know TensorFlow can't convert to coreml directly, but we found that we can convert TensorFlow mode to Caffe and then convert it to CoreML. is this possible ?
All the line CoreML are converter to CoreM not from CoreML.
If I'm right on the table organisation it need to be on the column coreML.
btw thanks for your work.
Thank you for this very helpful compilation of available converters! I came accross a conversion tool for caffe -> caffe2 that is not included in the table. You might want to add it. See python script and its description.
PaddlePaddle/X2Paddle: X2Paddle is a toolkit for converting trained model to PaddlePaddle from other deep learning frameworks. 支持主流深度学习框架模型转换至PaddlePaddle『飞桨』 https://github.com/PaddlePaddle/X2Paddle
I got yolov1 converted on caffe (protxt and caffe.model) usind darknet2caffe tool. How do I test them? Can you suggest detection example using the converted prototxt and caffe.model