Leo

It seems GenerateProposals was not implemented for CUDA, but device_type is set to 1. How did you make the caffe2 model?

You could try to change `device_option { device_type: 1 }` from GPU to CPU, using the `op.mutable_device_option()->set_device_type(CPU)`. You can find the op by iterating through the model (`NetDef`) with `for...

I'm afraid this goes a bit beyond my understanding of the detectron architecture. You could chase this down by selectively moving operation to the CPU/GPU they belong, but that might...

Hi, The `model.pb.h` header is generated by ProtoBuf compiler which is part of the Make process. If you did run `make` already, could you share the output of that after...

Hi, there's no such example available in this repo. Caffe2 has most of its training tools in Python, without any underlaying C++ counterpart. If you have some concise example code,...

hi, a pretrained googlenet model needs to be downloaded first. this requires the cURL library to be installed. On Thu, Jan 25, 2018 at 7:49 AM hoebd wrote: > Hi,...

This second issue seems to be related to the warning that is displayed at the top ending in `I will set the available devices to be zero`. Upon running the...

Thanks for persisting here. This is indeed a bug. I'll take a look today.

I pushed a fix in commit 94882795. Let me know if that works.

C-style arithmetic is not supported. This stems from the primary goal of Tosti, to _not_ be a C interpreter. I do plan to add support for infix operators like +-*/,...