Zichao Yang
Zichao Yang
I am having similar problems with high dimension. Moreover, the memory usage is very high, taking 100-200G for n around 3k-4k.
Hi, want to check if the OSQP solver is ready to use? I checked the branches and didn't find the one named `param_qp`. Thanks!
sorry its a typo, dilation = 2
I just tested For ```decoder```, if I change the original padding to ```padding = [[0, 0], [(filter_width - 1) * dilation/2, (filter_width -1) * dilation/2], [0, 0]]``` the result looks...
You are ignoring the padding from '''conv1d''' itself, the input is ''" 0 1 3 5 0 0 2 4 6 0 ''' becomes the input to conv1d, which will...
any update on this?
any update on this?
the default configuration is for vqa data set, not the daquar data set. You can directly download the vqa data (the link has been provided) and run the training, this...
`options['gamma']` is simply one hyper parameter, you can set it to `1` or anything else. I don't remember whether `options['gamma']=1` is optimal. Maybe you can tune it to make it...
The features are extracted with caffe, with the script: https://github.com/zcyang/imageqa-san/blob/master/data_vqa/feature_extract.py Since the features are sparse, they are stored in sparse matrix format: https://github.com/zcyang/imageqa-san/blob/master/src/data_provision_att_vqa.py#L74