python - How to correctly use Numpy's FFT function in PyTorch? -


i introduced pytorch , began running through library's documentation , tutorials. in "creating extensions using numpy , scipy" tutorial ( http://pytorch.org/tutorials/advanced/numpy_extensions_tutorial.html), under "parameter-less example", sample function created using numpy called "badfftfunction".

the description function states:

"this layer doesn’t particularly useful or mathematically correct.

it aptly named badfftfunction"

the function , usage given as:

from numpy.fft import rfft2, irfft2  class badfftfunction(function):      def forward(self, input):         numpy_input = input.numpy()         result = abs(rfft2(numpy_input))         return torch.floattensor(result)      def backward(self, grad_output):         numpy_go = grad_output.numpy()         result = irfft2(numpy_go)         return torch.floattensor(result)  def incorrect_fft(input):     return badfftfunction()(input)  input = variable(torch.randn(8, 8), requires_grad=true) result = incorrect_fft(input) print(result.data) result.backward(torch.randn(result.size())) print(input.grad)

unfortunately, introduced signal processing well, , unsure of (likely obvious) error in function.

i wondering, how might 1 go fixing function forward , backward outputs correct? how can badfftfunction fixed differentiable fft function can used in pytorch?

any appreciated. thank you.

i think errors are: first, function, despite having fft in name, returns amplitudes/absolute values of fft output, not full complex coefficients. also, using inverse fft compute gradient of amplitudes doesn't make sense mathematically (?).

there package called pytorch-fft tries make fft-function available in pytorch. can see experimental code autograd functionality here. note discussion in issue.


Comments

Post a Comment

Popular posts from this blog

Is there a better way to structure post methods in Class Based Views -

i'm using class based views in django , never specify url in ajax calls , omit action parameter in form because know these requests go through post method of class based view. notice view - profile page make many requests depending on user updating on page - post method become convoluted , if/else mess example: def post(self, request, *args, **kwargs): # handle user changing available date if request.post.get('availabledate') != none: self.updateavailabledate(request) return jsonresponse({'result':'success'}) if request.post.get('newprojectname') != none: creative_user = creativeuserprofile.objects.get(id = request.user.id) project = project.create_project(creative_user, request.post['newprojectname']) project.save() return jsonresponse({'projectid': project.id }) if request.post.get('projectimage') != none , request.files['file']: proj
Read more

performance - Why is XCHG reg, reg a 3 micro-op instruction on modern Intel architectures? -

i'm doing micro-optimization on performance critical part of code , came across sequence of instructions (in at&t syntax): add %rax, %rbx mov %rdx, %rax mov %rbx, %rdx i thought had use case xchg allow me shave instruction , write: add %rbx, %rax xchg %rax, %rdx however, dimay found agner fog's instruction tables , xchg 3 micro-op instruction 2 cycle latency on sandy bridge, ivy bridge, broadwell, haswell , skylake. 3 whole micro-ops , 2 cycles of latency! 3 micro-ops throws off 4-1-1-1 cadence , 2 cycle latency makes worse original in best case since last 2 instructions in original might execute in parallel. now... cpu might breaking instruction micro-ops equivalent to: mov %rax, %tmp mov %rdx, %rax mov %tmp, %rdx where tmp anonymous internal register , suppose last 2 micro-ops run in parallel latency 2 cycles. given register renaming occurs on these micro-architectures, though, doesn't make sense me done way. why wouldn't register renamer
Read more

jquery - Responsive Navbar with Sub Navbar -

good day, forgive me nav vocabulary not best. if question confusing apologize. i'm working on navigation bar needs centered on page @ 768px , above. items in nav open (or perhaps toggle) subnav lives directly below. these nav should appear centered on page. i have been able work through responsive portion of nav bar, having main items align vertically , sub nav menu of each item roll out below, , gave them indent separation. working well. however, issue not responsive side, behavior @ width greater 768px. happens toggling menu's sub navigation pushes other main items down page below sub nav. here's code: $(document).ready(function () { //stick in fixed 100% height behind navbar don't wrap $('#slide-nav.navbar-inverse').after($('<div class="inverse" id="navbar-height-col"></div>')); $('#slide-nav.navbar-default').after($('<div id="navbar-height-col"></d
Read more