Vladislav Artemyev

Human pose estimation.

1

As described in original paper there is some way to predict human pose keypoints. Can this version predict them?

About pairwise_predict

1

Is there some benefits if use pairwise_predict? Could it help to train shallow models better? Could you provide pairwise_stats.mat file? ;)

Another encoder

1

Have you tried to train the model with another non-resnet encoder? For example mobilenet? It will take realtime on CPU!

There was no way to use PSPNet as fully convolutional network because we had hardcoded AveragePooling builded in interp_block: ``` if input_shape == (473, 473): kernel_strides_map = {1: 60, 2:...

Is there some way to calculate anchor boxes for my own dataset?

4

I try to train this model on my own dataset. I created the structure of folder similar to kitti. I have the same size of image as KITTI. But my...

How to run demo.py on CPU

2

So that's all the question ;)

How to train my own dataset on GCN? Is there some best practices to train the model? Learning rate multiplication gets better accuracy?

Does it work with the latest versions of keras and caffe?

1

Hi. Really good converter, I have used it for half a year. But last time I updated caffe and keras versions, and it fails with the error: ``` ValueError: Input...

The `1st entry of padding` argument must be a tuple of 2 integers. Received: 3

1

python -m caffe2keras deploy_google_64.prototxt trained_google_64_v01_iter_8000.caffemodel keras-output-model.h5 Using Theano backend. Converting model... CREATING MODEL Traceback (most recent call last): File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main "__main__", fname, loader, pkg_name) File "/usr/lib/python2.7/runpy.py",...

Could you give an example of program that prints the same string even after any one character is deleted?

2

F.e. that prints "Hello World" ;)