jiaozizhao

Could you also release your annotation files for v2.1? Thanks a lot.

Message type "caffe.LayerParameter" has no field named "multi_stage_meanfield_param"

10

**Hi, when I compile the caffe, there is a warning for the function 'multi_stage_meanfield.cpp' as below:** "src/caffe/layers/multi_stage_meanfield.cpp: In instantiation of ‘void caffe::MultiStageMeanfieldLayer::LayerSetUp(const std::vector&, const std::vector&) [with Dtype = float]’: src/caffe/layers/multi_stage_meanfield.cpp:258:1:...

Hi, Thanks very much for the pytorch version. However, the the lib tensor_comprehensions is not maintained and cannot be installed successfully. Do you have an version not using tensor_comprehensions? Looking...

How to pretrain an optical flow model on COCO?

7

HI, As COCO just has RGB images, how did you pretrain your model for optical flow? Could you give some details? Thanks a lot.

pretrained models

1

Hi, Could you explain what are the pretrained model names meaning? For example, 'rgb_scratch.pkl' means the model is only pretrained on imagenet , and 'rgb_imagenet.pkl' means the model is pretrained...

When I do evaluation, there is an error like ' This error was detected while a MEX-file was running. If the MEX-file is not an official MathWorks function, please examine...

Parameters for finetuning on UCF101 and JHMDB

1

Hi, May I know what parameters are you used for finetuning on UCF101 and JHMDB? Like learning rate, momentum, weight_decay, and steps. Thanks

Hi, Thanks for the great work. In the pretrain_vast.json, the settings for "run_cfg" and "model_cfg" are respectively set to "./config/default_run_cfg.json" and "./config/newvlp/default_model_cfg.json". However, I did not find these two files...