Profile Summary

Jv (Calls: 216, Time: 568.474 s)
Generated 19-Jun-2021 04:01:57 using performance time.
function in file /nfs/inm_phd/07/d07944009/2021/0618-proj6/simpleNN/MATLAB/cnn/Jv.m
Copy to new window for comparing multiple runs

Parents (calling functions)

Function Name	Function Type	Calls
CG>R_JTBJv	subfunction	216

Lines where the most time was spent

Line Number	Code	Calls	Total Time	% Time	Time Plot
16	net.phiZ{m} = padding_and_phiZ...	648	142.605 s	25.1%
23	[net.Z{m+1}, net.idx_pool{m}, ...	648	141.716 s	24.9%
19	R_Z = padding_and_phiZ(model, ...	648	132.362 s	23.3%
20	R_Z = model.weight{m}*R_Z + v_...	648	102.944 s	18.1%
17	net.Z{m+1} = max(model.weight{...	648	46.569 s	8.2%
All other lines			2.278 s	0.4%
Totals			568.474 s	100%

Children (called functions)

Function Name	Function Type	Calls	Total Time	% Time	Time Plot
padding_and_phiZ	function	1296	264.881 s	46.6%
maxpooling	function	648	133.879 s	23.6%
gpu	function	432	0.270 s	0.0%
Self time (built-ins, overhead, etc.)			169.444 s	29.8%
Totals			568.474 s	100%

Code Analyzer results
No Code Analyzer messages.

Coverage results
Show coverage for parent directory

Total lines in function	43
Non-code lines (comments, blank lines)	10
Code lines (lines that can run)	33
Code lines that did run	31
Code lines that did not run	2
Coverage (did run/can run)	93.94 %

Function listing

time	Calls	line
		1	function [R_Z, net] = Jv(data, model, net, v)
		2
0.002	216	3	L = model.L;
< 0.001	216	4	LC = model.LC;
< 0.001	216	5	var_ptr = model.var_ptr;
< 0.001	216	6	num_data = size(data, 2);
		7
0.032	216	8	net.Z{1} = reshape(gpu(data), model.ch_input(1), []);
0.269	216	9	R_Z = gpu(@zeros, size(net.Z{1}));
		10
0.001	216	11	for m = 1 : LC
0.048	648	12	var_range = var_ptr(m) : var_ptr(m+1) - 1;
0.005	648	13	d = model.ch_input(m+1);
0.135	648	14	v_ = reshape(v(var_range), d, []);
		15
142.605	648	16	net.phiZ{m} = padding_and_phiZ(model, net, net.Z{m}, m, num_data);
46.569	648	17	net.Z{m+1} = max(model.weight{m}*net.phiZ{m} + model.bias{m}, 0);
		18
132.362	648	19	R_Z = padding_and_phiZ(model, net, R_Z, m, num_data);
102.944	648	20	R_Z = model.weight{m}R_Z + v_(:, 1:end-1)net.phiZ{m} + v_(:, end);
		21
0.010	648	22	if model.wd_subimage_pool(m) > 1
141.716	648	23	[net.Z{m+1}, net.idx_pool{m}, R_Z] = maxpooling(model, net, net.Z{m+1}, m, R_Z);
< 0.001	648	24	end
		25
0.002	648	26	if m == LC
0.009	216	27	net.Z{m+1} = reshape(net.Z{m+1}, [], num_data);
0.002	216	28	R_Z = reshape(R_Z, [], num_data);
< 0.001	648	29	end
1.516	648	30	R_Z = (net.Z{m+1} > 0).*R_Z;
0.005	648	31	end
		32
0.002	216	33	for m = LC+1 : L
0.009	216	34	var_range = var_ptr(m) : var_ptr(m+1) - 1;
0.002	216	35	n_m = model.full_neurons(m-LC);
0.018	216	36	v_ = reshape(v(var_range), n_m, []);
		37
0.205	216	38	R_Z = model.weight{m}R_Z + v_(:, 1:end-1)net.Z{m} + v_(:, end);
< 0.001	216	39	if m < L
		40	net.Z{m+1} = max(model.weight{m}*net.Z{m} + model.bias{m}, 0);
		41	R_Z = (net.Z{m+1} > 0).*R_Z;
< 0.001	216	42	end
0.003	216	43	end

Other subfunctions in this file are not included in this listing.