Closed yaronmr closed 8 years ago
I have the same issue while trying to convert my fine-tuned AlexNet model to MatConvNet type.. I tried with different variants of --caffe-variant parameter but did not fix the problem.
Hi, could you try the new script import-caffe-dag.py and let us know whether that fixes the problem? It will give you a DAG instead of a SimpleNN but it will help us debugging the scripts.
Unfortunately Caffe is a bit of a moving target at the moment and we need to keep patching the import scripts.
On 7 Oct 2015, at 21:21, kilickaya notifications@github.com wrote:
I have the same issue while trying to convert my fine-tuned AlexNet model to MatConvNet type.. I tried with different variants of --caffe-variant parameter but did not fix the problem.
— Reply to this email directly or view it on GitHub https://github.com/vlfeat/matconvnet/issues/257#issuecomment-146316931.
Hi, I encountered the same issue. I seem to find only import-caffe.py file and not import-caffe-dag.py.
Hi, we recently consolidated the two scripts and merged in import-caffe.py.
Could you share your tuned model somewhere? Unfortunately Caffe is a bit of a moving target and it is sometimes difficult to guarantee compatibility with all the versions.
On 21 Jan 2016, at 15:28, naamarbel notifications@github.com wrote:
Hi, I encountered the same issue. I seem to find only import-caffe.py file and not import-caffe-dag.py.
— Reply to this email directly or view it on GitHub https://github.com/vlfeat/matconvnet/issues/257#issuecomment-173606142.
Hi Andrea,
I am facing the same error for a long time with no solution. I am sharing my .caffe model with you. https://drive.google.com/drive/folders/0B2a8WzvR-lOxWEU1UGVDSC1EM0E?usp=sharing
Could you please convert it or a working script provided so that I can convert my models if necessary in near future,
Thanks in advance best
Try replacing all 'layer' with 'layers' in deploy.prototxt
Hi everyone,
I'm trying to convert AlexNet using import-caffe.py getting the error below.
This is the default model from NVIDIA DIGITS/Caffe package. Anyone knows how to go about it?
Thanks
deploy.prototxt