涂云斌

run detection on my own images with pre-trained resnet model

2

Hi, I want to detect my own pictures with the resent-101 model trained by you on visual genome. I found several demo. py files in the 'tool' folder. Does demo_vg.py...

Thank you very much for your useful tutorial. So, could you kindly offer a a tutorial for video captioning with soft attention? For example, this paper, Describing videos by exploiting...

Firstly, thank you very much for your very useful tutorial, especially for image-captioning. And you have a Tensorflow Repo for "show-attend-and-tell", so, I hope you can offer a pytorch version...

invalid argument 0: Sizes of tensors must match except in dimension 0. Got 27 and 41 in dimension

1

Hi, I met a bug, but I haven't fixed it. I want to use this code to train model on the MSVD dataset. I can train the model on the...

How many GPU memory do you use?

1

Hi, thank you for your good work. I am trying to implement your code, but it always appears cuda out of memory. I have 3 RTX2080ti.

I want to konw whether someone has implemented code of this paper in pytorch? If so, I'd like you to kindly provided it to me? Thank you!

why don't you add <start> and <end> to the encoding ground truth?

2

Firstly, thank you very much for your very useful Repo. However, I have a question that why don't you add 'start' and 'end' to the encoding ground truth like other...

make all in C3D-v1.0 always failed

2

Hello, I git clone C3D and copied Makefile.config from caffe installed successful. Then, I make all in C3D-v1.0,but I always get fault result such as **:upgrade_proto.cppbase::(:.CheckOpMessageBuildertext:+:0xa3dNewString)(:) 'undefined buildreference/ libto/ libcaffe.a`(googleimage_io.o:)::protobuf...

rank parameter missing

1

Hi, I have met a problem. I have a single server which has 8 gpus. I used ubuntu16.04 and pytorch1.4 and my cuda is 10.0. The problem is that I...

Hi, can you provide the code for only implementing transformer of video caption?