Mercurial > hg > segmentation
changeset 3:bac230fcd7bd
add linux build of levinsonext
| author | mitian |
|---|---|
| date | Tue, 07 Apr 2015 17:58:37 +0100 |
| parents | ef1fd8b0f3c4 |
| children | 56a2ca9359d0 |
| files | SegEval.py utils/levinsonext.so utils/levinsonext_linux.so utils/levinsonext_osx.so |
| diffstat | 4 files changed, 259 insertions(+), 49 deletions(-) [+] |
line wrap: on
line diff
--- a/SegEval.py Fri Apr 03 15:44:32 2015 +0100 +++ b/SegEval.py Tue Apr 07 17:58:37 2015 +0100 @@ -48,7 +48,7 @@ # Algorithm params h = 8 # Size of median filter for features in C-NMF R = 15 # Size of the median filter for the activation matrix C-NMF -rank = 4 # Rank of decomposition for the boundaries +rank = 8 # Rank of decomposition for the boundaries rank_labels = 6 # Rank of decomposition for the labels R_labels = 6 # Size of the median filter for the labels # Foote @@ -121,7 +121,7 @@ self.tempoWindow = 6.0 self.bpmBands = [30, 45, 60, 80, 100, 120, 180, 240, 400, 600] - '''Peak picking settings''' + '''Peak picking settings for novelty based method''' self.threshold = 50 self.confidence_threshold = 0.5 self.delta_threshold = 0.0 @@ -136,9 +136,12 @@ self.medianWin = 7 - def pairwiseF(self, annotation, detection, tolerance=3.0, combine=1.0): + def pairwiseF(self, annotation, detection, tolerance=3.0, combine=1.0, idx2time=None): '''Pairwise F measure evaluation of detection rates.''' - + + if idx2time: + # Map detected idxs to real time + detection = [idx2time[int(np.rint(i))] for i in detection] + [ao.gt[-1]] # print 'detection', detection detection = np.append(detection, annotation[-1]) res = EvalObj() @@ -175,7 +178,55 @@ res.F = 2 * res.P * res.R / (res.P + res.R) return res - + def wirteIndividualHeader(self, filename): + '''Write header of output files for individual features.''' + + with open(filename, 'a') as f: + csvwriter = csv.writer(f, delimiter=',') + csvwriter.writerow(['audio', 'gammatone_tp_05', 'gammatone_fp_05', 'gammatone_fn_05', 'gammatone_P_05', 'gammatone_R_05', 'gammatone_F_05', 'gammatone_AD_05', 'gammatone_DA_05', 'gammatone_tp_3', \ + 'gammatone_fp_3', 'gammatone_fn_3', 'gammatone_P_3', 'gammatone_R_3', 'gammatone_F_3', 'gammatone_AD_3', 'gammatone_DA_3', 'harmonic_tp_05', 'harmonic_fp_05', 'harmonic_fn_05', 'harmonic_P_05', \ + 'harmonic_R_05', 'harmonic_F_05', 'harmonic_AD_05', 'harmonic_DA_05', 'harmonic_tp_3', 'harmonic_fp_3', 'harmonic_fn_3', 'harmonic_P_3', 'harmonic_R_3', 'harmonic_F_3', 'harmonic_AD_3', 'harmonic_DA_3', \ + 'timbre_tp_05', 'timbre_fp_05', 'timbre_fn_05', 'timbre_P_05', 'timbre_R_05', 'timbre_F_05', 'timbre_AD_05', 'timbre_DA_05', 'timbre_tp_3', 'timbre_fp_3', 'timbre_fn_3', 'timbre_P_3', 'timbre_R_3', \ + 'timbre_F_3', 'timbre_AD_3', 'timbre_DA_3', 'tempo_tp_05', 'tempo_fp_05', 'tempo_fn_05', 'tempo_P_05', 'tempo_R_05', 'tempo_F_05', 'tempo_AD_05', 'tempo_DA_05', \ + 'tempo_tp_3', 'tempo_fp_3', 'tempo_fn_3', 'tempo_P_3', 'tempo_R_3', 'tempo_F_3', 'tempo_AD_3', 'tempo_DA_3']) + + def wirteIndividualRes(self, filename, ao_name, gt_res_05, gt_res_3, harmonic_res_05, harmonic_res_3, timbre_res_05, timbre_res_3, tempo_res_05, tempo_res_3): + '''Write result of single detection for individual features.''' + + with open(filename, 'a') as f: + csvwriter = csv.writer(f, delimiter=',') + csvwriter.writerow([ao_name, gt_res_05.TP, gt_res_05.FP, gt_res_05.FN, gt_res_05.P, gt_res_05.R, gt_res_05.F, gt_res_05.AD, gt_res_05.DA, gt_res_3.TP, gt_res_3.FP, gt_res_3.FN, gt_res_3.P, \ + gt_res_3.R, gt_res_3.F, gt_res_3.AD, gt_res_3.DA, harmonic_res_05.TP, harmonic_res_05.FP, harmonic_res_05.FN, harmonic_res_05.P, harmonic_res_05.R, harmonic_res_05.F, harmonic_res_05.AD, harmonic_res_05.DA, \ + harmonic_res_3.TP, harmonic_res_3.FP, harmonic_res_3.FN, harmonic_res_3.P, harmonic_res_3.R, harmonic_res_3.F, harmonic_res_3.AD, harmonic_res_3.DA, timbre_res_05.TP, timbre_res_05.FP, \ + timbre_res_05.FN, timbre_res_05.P, timbre_res_05.R, timbre_res_05.F, timbre_res_05.AD, timbre_res_05.DA, timbre_res_3.TP, timbre_res_3.FP, timbre_res_3.FN, timbre_res_3.P, timbre_res_3.R, timbre_res_3.F, \ + timbre_res_3.AD, timbre_res_3.DA, tempo_res_05.TP, tempo_res_05.FP, tempo_res_05.FN, tempo_res_05.P, tempo_res_05.R, tempo_res_05.F, tempo_res_05.AD, tempo_res_05.DA, tempo_res_3.TP, tempo_res_3.FP, \ + tempo_res_3.FN, tempo_res_3.P, tempo_res_3.R, tempo_res_3.F, tempo_res_3.AD, tempo_res_3.DA]) + + def writeCombinedHeader(self, filename): + '''Write header of output files for combined features.''' + + with open(filename, 'a') as f: + csvwriter = csv.writer(f, delimiter=',') + csvwriter.writerow(['audio', 'gt_tb_P_0.5', 'gt_tb_R_0.5', 'gt_tb_F_0.5', 'gt_tb_P_3', 'gt_tb_R_3', 'gt_tb_F_3', 'gt_tp_P_0.5', 'gt_tp_R_0.5', 'gt_tp_F_0.5', 'gt_tp_P_3', 'gt_tp_R_3', 'gt_tp_F_3',\ + 'gt_hm_P_0.5', 'gt_hm_R_0.5', 'gt_hm_F_0.5', 'gt_hm_P_3', 'gt_hm_R_3', 'gt_hm_F_3', 'tb_tp_P_0.5', 'tb_tp_R_0.5', 'tb_tp_F_0.5', 'tb_tp_P_3', 'tb_tp_R_3', 'tb_tp_F_3', 'tb_hm_P_0.5', 'tb_hm_R_0.5', 'tb_hm_F_0.5', \ + 'tb_hm_P_3', 'tb_hm_R_3', 'tb_hm_F_3', 'tp_hm_P_0.5', 'tp_hm_R_0.5', 'tp_hm_F_0.5', 'tp_hm_P_3', 'tp_hm_R_3', 'tp_hm_F_3', 'gt_tb_tp_P_0.5', 'gt_tb_tp_R_0.5', 'gt_tb_tp_F_0.5', 'gt_tb_tp_P_3', 'gt_tb_tp_R_3', \ + 'gt_tb_tp_F_3', 'gt_tb_hm_P_0.5', 'gt_tb_hm_R_0.5', 'gt_tb_hm_F_0.5', 'gt_tb_hm_P_3', 'gt_tb_hm_R_3', 'gt_tb_hm_F_3', 'gt_tp_hm_P_0.5', 'gt_tp_hm_R_0.5', 'gt_tp_hm_F_0.5', 'gt_tp_hm_P_3', 'gt_tp_hm_R_3', 'gt_tp_hm_F_3', \ + 'tb_tp_hm_P_0.5', 'tb_tp_hm_R_0.5', 'tb_tp_hm_F_0.5', 'tb_tp_hm_P_3', 'tb_tp_hm_R_3', 'tb_tp_hm_F_3', 'gt_tb_tp_hm_P_0.5', 'gt_tb_tp_hm_R_0.5', 'gt_tb_tp_hm_F_0.5', 'gt_tb_tp_hm_P_3', 'gt_tb_tp_hm_R_3', 'gt_tb_tp_hm_F_3']) + + def wirteCombinedRes(self, filename, ao_name, gt_hm_res_05, gt_hm_res_3, gt_tb_res_05, gt_tb_res_3, gt_tp_res_05, gt_tp_res_3, hm_tb_res_05, hm_tb_res_3, hm_tp_res_05, hm_tp_res_3, \ + tb_tp_res_05, tb_tp_res_3, gt_hm_tb_res_05, gt_hm_tb_res_3, gt_hm_tp_res_05, gt_hm_tp_res_3, gt_tb_tp_res_05, gt_tb_tp_res_3, hm_tb_tp_res_05, hm_tb_tp_res_3): + '''Write result of single detection for combined features.''' + + with open(filename, 'a') as f: + csvwriter = csv.writer(f, delimiter=',') + csvwriter.writerow([ao_name, gt_tb_res_05.P, gt_tb_res_05.R, gt_tb_res_05.F, gt_tb_res_3.P, gt_tb_res_3.R, gt_tb_res_3.F, gt_tp_res_05.P, gt_tp_res_05.R, gt_tp_res_05.F, gt_tp_res_3.P, gt_tp_res_3.R, gt_tp_res_3.F, \ + gt_hm_res_05.P, gt_hm_res_05.R, gt_hm_res_05.F, gt_hm_res_3.P, gt_hm_res_3.R, gt_hm_res_3.F, tb_tp_res_05.P, tb_tp_res_05.R, tb_tp_res_05.F, tb_tp_res_3.P, tb_tp_res_3.R, tb_tp_res_3.F, \ + tb_hm_res_05.P, tb_hm_res_05.R, tb_hm_res_05.F, tb_hm_res_3.P, tb_hm_res_3.R, tb_hm_res_3.F, tp_hm_res_05.P, tp_hm_res_05.R, tp_hm_res_05.F, tp_hm_res_3.P, tp_hm_res_3.R, tp_hm_res_3.F, \ + gt_tb_tp_res_05.P, gt_tb_tp_res_05.R, gt_tb_tp_res_05.F, gt_tb_tp_res_3.P, gt_tb_tp_res_3.R, gt_tb_tp_res_3.F, gt_tb_hm_res_05.P, gt_tb_hm_res_05.R, gt_tb_hm_res_05.F, gt_tb_hm_res_3.P, gt_tb_hm_res_3.R, gt_tb_hm_res_3.F, \ + gt_tp_hm_res_05.P, gt_tp_hm_res_05.R, gt_tp_hm_res_05.F, gt_tp_hm_res_3.P, gt_tp_hm_res_3.R, gt_tp_hm_res_3.F, tb_tp_hm_res_05.P, tb_tp_hm_res_05.R, tb_tp_hm_res_05.F, tb_tp_hm_res_3.P, tb_tp_hm_res_3.R, tb_tp_hm_res_3.F, \ + gt_tb_tp_hm_res_05.P, gt_tb_tp_hm_res_05.R, gt_tb_tp_hm_res_05.F, gt_tb_tp_hm_res_3.P, gt_tb_tp_hm_res_3.R, gt_tb_tp_hm_res_3.F]) + + def process(self): '''For the aggregated input features, discard a propertion each time as the pairwise distances within the feature space descending. In the meanwhile evaluate the segmentation result and track the trend of perfomance changing by measuring the feature selection @@ -317,59 +368,218 @@ audio_list.append(ao) - # Segment input audio using specified boundary retrieval method. + # Prepare output files. + outfile1 = join(options.OUTPUT, 'individual_novelty.csv') + outfile2 = join(options.OUTPUT, 'individual_foote.csv') + outfile3 = join(options.OUTPUT, 'individual_sf.csv') + outfile4 = join(options.OUTPUT, 'individual_cnmf.csv') + + outfile5 = join(options.OUTPUT, 'combined_novelty.csv') + outfile6 = join(options.OUTPUT, 'combined_foote.csv') + outfile7 = join(options.OUTPUT, 'combined_sf.csv') + outfile8 = join(options.OUTPUT, 'combined_cnmf.csv') + + self.wirteIndividualHeader(outfile1) + self.wirteIndividualHeader(outfile2) + self.wirteIndividualHeader(outfile3) + self.wirteIndividualHeader(outfile4) + + # self.wirteCombinedlHeader(outfile5) + # self.wirteCombinedlHeader(outfile6) + self.wirteCombinedlHeader(outfile7) + # self.wirteCombinedlHeader(outfile8) + print 'Segmenting using %s method' %options.BOUNDARY for i,ao in enumerate(audio_list): print 'processing: %s' %ao.name + + ############################################################################################################################################ + # Experiment 1: segmentation using individual features. + + gammatone_novelty, smoothed_gammatone_novelty, gammatone_novelty_idxs = novelty_S.process(ao.gammatone_ssm, self.kernel_size, peak_picker) + timbre_novelty, smoothed_timbre_novelty, timbre_novelty_idxs = novelty_S.process(ao.timbre_ssm, self.kernel_size, peak_picker) + tempo_novelty, smoothed_harmonic_novelty, tempo_novelty_idxs = novelty_S.process(ao.tempo_ssm, self.kernel_size, peak_picker) + harmonic_novelty, smoothed_tempo_novelty, harmonic_novelty_idxs = novelty_S.process(ao.harmonic_ssm, self.kernel_size, peak_picker) + + gammatone_cnmf_idxs = cnmf_S.segmentation(ao.gammatone_features, rank=rank, R=R, h=h, niter=300) + timbre_cnmf_idxs = cnmf_S.segmentation(ao.timbre_features, rank=rank, R=R, h=h, niter=300) + tempo_cnmf_idxs = cnmf_S.segmentation(ao.tempo_features, rank=rank, R=R, h=h, niter=300) + harmonic_cnmf_idxs = cnmf_S.segmentation(ao.harmonic_features, rank=rank, R=R, h=h, niter=300) + + gammatone_foote_idxs = foote_S.segmentation(ao.gammatone_features, M=M, Mg=Mg, L=L) + timbre_foote_idxs = foote_S.segmentation(ao.timbre_features, M=M, Mg=Mg, L=L) + tempo_foote_idxs = foote_S.segmentation(ao.tempo_features, M=M, Mg=Mg, L=L) + harmonic_foote_idxs = foote_S.segmentation(ao.harmonic_features, M=M, Mg=Mg, L=L) + + gammatone_sf_idxs = sf_S.segmentation(ao.gammatone_features) + timbre_sf_idxs = sf_S.segmentation(ao.timbre_features) + tempo_sf_idxs = sf_S.segmentation(ao.tempo_features) + harmonic_sf_idxs = sf_S.segmentation(ao.harmonic_features) - # Experiment 1: segmentation using individual features. - if options.BOUNDARY == 'novelty': - # Peak picking from the novelty curve - gammatone_novelty, smoothed_gammatone_novelty, gammatone_bound_idxs = novelty_S.process(ao.gammatone_ssm, self.kernel_size, peak_picker) - timbre_novelty, smoothed_timbre_novelty, timbre_bound_idxs = novelty_S.process(ao.timbre_ssm, self.kernel_size, peak_picker) - tempo_novelty, smoothed_harmonic_novelty, tempo_bound_idxs = novelty_S.process(ao.tempo_ssm, self.kernel_size, peak_picker) - harmonic_novelty, smoothed_tempo_novelty, harmonic_bound_idxs = novelty_S.process(ao.harmonic_ssm, self.kernel_size, peak_picker) - - if options.BOUNDARY == 'cnmf': - gammatone_bound_idxs = cnmf_S.segmentation(ao.gammatone_features, rank=rank, R=R, h=8, niter=300) - timbre_bound_idxs = cnmf_S.segmentation(ao.timbre_features, rank=rank, R=R, h=h, niter=300) - tempo_bound_idxs = cnmf_S.segmentation(ao.tempo_features, rank=rank, R=R, h=h, niter=300) - harmonic_bound_idxs = cnmf_S.segmentation(ao.harmonic_features, rank=rank, R=R, h=h, niter=300) - - if options.BOUNDARY == 'foote': - gammatone_bound_idxs = foote_S.segmentation(ao.gammatone_features, M=M, Mg=Mg, L=L) - timbre_bound_idxs = foote_S.segmentation(ao.timbre_features, M=M, Mg=Mg, L=L) - tempo_bound_idxs = foote_S.segmentation(ao.tempo_features, M=M, Mg=Mg, L=L) - harmonic_bound_idxs = foote_S.segmentation(ao.harmonic_features, M=M, Mg=Mg, L=L) + # Evaluate and write results. + gt_novelty_05 = self.pairwiseF(ao.gt, gammatone_novelty_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + gt_novelty_3 = self.pairwiseF(ao.gt, gammatone_novelty_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + harmonic_novelty_05 = self.pairwiseF(ao.gt, harmonic_novelty_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + harmonic_novelty_3 = self.pairwiseF(ao.gt, harmonic_novelty_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + tempo_novelty_05 = self.pairwiseF(ao.gt, tempo_novelty_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + tempo_novelty_3 = self.pairwiseF(ao.gt, tempo_novelty_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + timbre_novelty_05 = self.pairwiseF(ao.gt, timbre_novelty_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + timbre_novelty_3 = self.pairwiseF(ao.gt, timbre_novelty_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) - if options.BOUNDARY == 'sf': - gammatone_bound_idxs = sf_S.segmentation(ao.gammatone_features) - timbre_bound_idxs = sf_S.segmentation(ao.timbre_features) - tempo_bound_idxs = sf_S.segmentation(ao.tempo_features) - harmonic_bound_idxs = sf_S.segmentation(ao.harmonic_features) + gt_cnmf_05 = self.pairwiseF(ao.gt, gammatone_cnmf_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + gt_cnmf_3 = self.pairwiseF(ao.gt, gammatone_cnmf_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + harmonic_cnmf_05 = self.pairwiseF(ao.gt, harmonic_cnmf_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + harmonic_cnmf_3 = self.pairwiseF(ao.gt, harmonic_cnmf_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + tempo_cnmf_05 = self.pairwiseF(ao.gt, tempo_cnmf_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + tempo_cnmf_3 = self.pairwiseF(ao.gt, tempo_cnmf_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + timbre_cnmf_05 = self.pairwiseF(ao.gt, timbre_cnmf_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + timbre_cnmf_3 = self.pairwiseF(ao.gt, timbre_cnmf_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + + gt_sf_05 = self.pairwiseF(ao.gt, gammatone_sf_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + gt_sf_3 = self.pairwiseF(ao.gt, gammatone_sf_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + harmonic_sf_05 = self.pairwiseF(ao.gt, harmonic_sf_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + harmonic_sf_3 = self.pairwiseF(ao.gt, harmonic_sf_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + tempo_sf_05 = self.pairwiseF(ao.gt, tempo_sf_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + tempo_sf_3 = self.pairwiseF(ao.gt, tempo_sf_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + timbre_sf_05 = self.pairwiseF(ao.gt, timbre_sf_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + timbre_sf_3 = self.pairwiseF(ao.gt, timbre_sf_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + + gt_foote_05 = self.pairwiseF(ao.gt, gammatone_foote_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + gt_foote_3 = self.pairwiseF(ao.gt, gammatone_foote_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + harmonic_foote_05 = self.pairwiseF(ao.gt, harmonic_foote_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + harmonic_foote_3 = self.pairwiseF(ao.gt, harmonic_foote_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + tempo_foote_05 = self.pairwiseF(ao.gt, tempo_foote_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + tempo_foote_3 = self.pairwiseF(ao.gt, tempo_foote_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) + timbre_foote_05 = self.pairwiseF(ao.gt, timbre_foote_idxs, tolerance=0.5, combine=1.0, idx2time=ao.ssm_timestamps) + timbre_foote_3 = self.pairwiseF(ao.gt, timbre_foote_idxs, tolerance=3, combine=1.0, idx2time=ao.ssm_timestamps) - if options.LABEL == 'fmc2d': - gammatone_bound_labels = fmc2d_S.compute_similarity(gammatone_bound_idxs, xmeans=True, N=N) - timbre_bound_labels = fmc2d_S.compute_similarity(timbre_bound_idxs, xmeans=True, N=N) - tempo_bound_labels = fmc2d_S.compute_similarity(tempo_bound_idxs, xmeans=True, N=N) - harmonic_bound_labels = fmc2d_S.compute_similarity(harmonic_bound_idxs, xmeans=True, N=N) + self.writeIndividualRes(ao.name, outfile1, gt_novelty_05, gt_novelty_3, harmonic_novelty_05, harmonic_novelty_3, tempo_novelty_05, timbre_novelty_05, timbre_novelty_05, timbre_novelty_3) + self.writeIndividualRes(ao.name, outfile2, gt_cnmf_05, gt_cnmf_3, harmonic_cnmf_05, harmonic_cnmf_3, tempo_cnmf_05, timbre_cnmf_05, timbre_cnmf_05, timbre_cnmf_3) + self.writeIndividualRes(ao.name, outfile3, gt_sf_05, gt_sf_3, harmonic_sf_05, harmonic_sf_3, tempo_sf_05, timbre_sf_05, timbre_sf_05, timbre_sf_3) + self.writeIndividualRes(ao.name, outfile4, gt_foote_05, gt_foote_3, harmonic_foote_05, harmonic_foote_3, tempo_foote_05, timbre_foote_05, timbre_foote_05, timbre_foote_3) - if options.LABEL == 'cnmf': - gammatone_bound_labels = cnmf_S.compute_labels(gammatone_bound_idxs, est_bound_idxs, nFrames) - timbre_bound_labels = cnmf_S.compute_labels(timbre_bound_idxs, est_bound_idxs, nFrames) - tempo_bound_labels = cnmf_S.compute_labels(tempo_bound_idxs, est_bound_idxs, nFrames) - harmonic_bound_labels = cnmf_S.compute_labels(harmonic_bound_idxs, est_bound_idxs, nFrames) - - gammatone_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in gammatone_novelty_peaks] - timbre_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in timbre_novelty_peaks] - harmonic_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in harmonic_novelty_peaks] - tempo_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in tempo_novelty_peaks] - # Experiment 2: Trying combined features using the best boundary retrieval method - ao_featureset = [ao.gammatone_features, ao.harmonic_features, ao.timbre_features, ao.tempo_features] - feature_sel = [int(x) for x in options.FEATURES if x.isdigit()] - fused_featureset = [ao_featureset[i] for i in feature_sel] + ############################################################################################################################################ + # Experiment 2: segmentation using combined features. + # Dumping features. + gt_hm = np.hstack([ao.gammatone_features, ao.harmonic_features]) + gt_tb = np.hstack([ao.gammatone_features, ao.timbre_features]) + gt_tp = np.hstack([ao.gammatone_features, ao.tempo_features]) + hm_tb = np.hstack([ao.harmonic_features, ao.timbre_features]) + hm_tp = np.hstack([ao.harmonic_features, ao.tempo_features]) + tb_tp = np.hstack([ao.timbre_features, ao.tempo_features]) + gt_hm_tp = np.hstack([ao.gammatone_features, ao.harmonic_features, ao.tempo_features]) + gt_tb_tp = np.hstack([ao.gammatone_features, ao.timbre_features, ao.tempo_features]) + hm_tb_tp = np.hstack([ao.harmonic_features, ao.timbre_features, ao.tempo_features]) + gt_hm_tb_tp = np.hstack([ao.gammatone_features, ao.harmonic_features, ao.timbre_features, ao.tempo_features]) + + gt_hm_sf_idxs = sf_S.segmentation(gt_hm) + gt_tb_sf_idxs = sf_S.segmentation(gt_tb) + gt_tp_sf_idxs = sf_S.segmentation(gt_tp) + hm_tb_sf_idxs = sf_S.segmentation(hm_tb) + hm_tp_sf_idxs = sf_S.segmentation(hm_tp) + tb_tp_sf_idxs = sf_S.segmentation(tb_tp) + gt_hm_tb_sf_idxs = sf_S.segmentation(gt_hm_tb) + gt_hm_tp_sf_idxs = sf_S.segmentation(gt_hm_tp) + gt_tb_tp_sf_idxs = sf_S.segmentation(gt_tb_tp) + hm_tb_tp_sf_idxs = sf_S.segmentation(hm_tb_tp) + gt_hm_tb_tp_sf_idxs = sf_S.segmentation(gt_hm_tb_tp) + + gt_hm_05 = self.pairwiseF(ao.gt, gt_hm_sf_idxs, tolerance=0.5, combine=1.0) + gt_tb_05 = self.pairwiseF(ao.gt, gt_tb_sf_idxs, tolerance=0.5, combine=1.0) + gt_tp_05 = self.pairwiseF(ao.gt, gt_tp_sf_idxs, tolerance=0.5, combine=1.0) + hm_tb_05 = self.pairwiseF(ao.gt, hm_tb_sf_idxs, tolerance=0.5, combine=1.0) + hm_tp_05 = self.pairwiseF(ao.gt, hm_tp_sf_idxs, tolerance=0.5, combine=1.0) + tb_tp_05 = self.pairwiseF(ao.gt, tb_tp_sf_idxs, tolerance=0.5, combine=1.0) + gt_hm_tb_05 = self.pairwiseF(ao.gt, gt_hm_tb_sf_idxs, tolerance=0.5, combine=1.0) + gt_hm_tp_05 = self.pairwiseF(ao.gt, gt_hm_tp_sf_idxs, tolerance=0.5, combine=1.0) + gt_tb_tp_05 = self.pairwiseF(ao.gt, gt_tb_tp_sf_idxs, tolerance=0.5, combine=1.0) + hm_tb_tp_05 = self.pairwiseF(ao.gt, hm_tb_tp_sf_idxs, tolerance=0.5, combine=1.0) + gt_hm_tb_tp_05 = self.pairwiseF(ao.gt, gt_hm_tb_tp_sf_idxs, tolerance=0.5, combine=1.0) + + gt_hm_3 = self.pairwiseF(ao.gt, gt_hm_sf_idxs, tolerance=3, combine=1.0) + gt_tb_3 = self.pairwiseF(ao.gt, gt_tb_sf_idxs, tolerance=3, combine=1.0) + gt_tp_3 = self.pairwiseF(ao.gt, gt_tp_sf_idxs, tolerance=3, combine=1.0) + hm_tb_3 = self.pairwiseF(ao.gt, hm_tb_sf_idxs, tolerance=3, combine=1.0) + hm_tp_3 = self.pairwiseF(ao.gt, hm_tp_sf_idxs, tolerance=3, combine=1.0) + tb_tp_3 = self.pairwiseF(ao.gt, tb_tp_sf_idxs, tolerance=3, combine=1.0) + gt_hm_tb_3 = self.pairwiseF(ao.gt, gt_hm_tb_sf_idxs, tolerance=3, combine=1.0) + gt_hm_tp_3 = self.pairwiseF(ao.gt, gt_hm_tp_sf_idxs, tolerance=3, combine=1.0) + gt_tb_tp_3 = self.pairwiseF(ao.gt, gt_tb_tp_sf_idxs, tolerance=3, combine=1.0) + hm_tb_tp_3 = self.pairwiseF(ao.gt, hm_tb_tp_sf_idxs, tolerance=3, combine=1.0) + gt_hm_tb_tp_3 = self.pairwiseF(ao.gt, gt_hm_tb_tp_sf_idxs, tolerance=3, combine=1.0) + + self.writeCombinedRes(ao.name, outfile7, gt_hm_05, gt_hm_3, gt_tb_05, gt_tb_3, gt_tp_05, gt_tp_3, hm_tb_05, hm_tb_3, hm_tp_05, hm_tp_3, tb_tp_05, tb_tp_3\ + gt_hm_tb_05, gt_hm_tb_3, gt_hm_tp_05, gt_hm_tp_3, gt_tb_tp_05, gt_tb_tp_3, hm_tb_tp_05, hm_tb_tp_3, gt_hm_tb_tp_05, gt_hm_tb_tp_3) + + ############################################################################################################################################ + # Experiment 3: Pruning boundaries detected by individual boundary algorithms. + + + # if options.BOUNDARY == 'novelty': + # gammatone_novelty, smoothed_gammatone_novelty, gammatone_bound_idxs = novelty_S.process(ao.gammatone_ssm, self.kernel_size, peak_picker) + # timbre_novelty, smoothed_timbre_novelty, timbre_bound_idxs = novelty_S.process(ao.timbre_ssm, self.kernel_size, peak_picker) + # tempo_novelty, smoothed_harmonic_novelty, tempo_bound_idxs = novelty_S.process(ao.tempo_ssm, self.kernel_size, peak_picker) + # harmonic_novelty, smoothed_tempo_novelty, harmonic_bound_idxs = novelty_S.process(ao.harmonic_ssm, self.kernel_size, peak_picker) + # + # if options.BOUNDARY == 'cnmf': + # gammatone_cnmf_idxs = cnmf_S.segmentation(ao.gammatone_features, rank=rank, R=R, h=8, niter=300) + # timbre_cnmf_idxs = cnmf_S.segmentation(ao.timbre_features, rank=rank, R=R, h=h, niter=300) + # tempo_cnmf_idxs = cnmf_S.segmentation(ao.tempo_features, rank=rank, R=R, h=h, niter=300) + # harmonic_cnmf_idxs = cnmf_S.segmentation(ao.harmonic_features, rank=rank, R=R, h=h, niter=300) + # + # if options.BOUNDARY == 'foote': + # gammatone_foote_idxs = foote_S.segmentation(ao.gammatone_features, M=M, Mg=Mg, L=L) + # timbre_foote_idxs = foote_S.segmentation(ao.timbre_features, M=M, Mg=Mg, L=L) + # tempo_foote_idxs = foote_S.segmentation(ao.tempo_features, M=M, Mg=Mg, L=L) + # harmonic_foote_idxs = foote_S.segmentation(ao.harmonic_features, M=M, Mg=Mg, L=L) + # + # if options.BOUNDARY == 'sf': + # gammatone_sf_idxs = sf_S.segmentation(ao.gammatone_features) + # timbre_sf_idxs = sf_S.segmentation(ao.timbre_features) + # tempo_sf_idxs = sf_S.segmentation(ao.tempo_features) + # harmonic_sf_idxs = sf_S.segmentation(ao.harmonic_features) + # + # gammatone_novelty_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in gammatone_novelty_peaks] + # timbre_novelty_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in timbre_novelty_peaks] + # harmonic_novelty_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in harmonic_novelty_peaks] + # tempo_novelty_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in tempo_novelty_peaks] + # + # gammatone_cnmf_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in gammatone_cnmf_peaks] + # timbre_cnmf_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in timbre_cnmf_peaks] + # harmonic_cnmf_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in harmonic_cnmf_peaks] + # tempo_cnmf_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in tempo_cnmf_peaks] + # + # gammatone_sf_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in gammatone_sf_peaks] + # timbre_sf_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in timbre_sf_peaks] + # harmonic_sf_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in harmonic_sf_peaks] + # tempo_sf_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in tempo_sf_peaks] + # + # gammatone_foote_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in gammatone_foote_peaks] + # timbre_foote_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in timbre_foote_peaks] + # harmonic_foote_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in harmonic_foote_peaks] + # tempo_foote_detection = [0.0] + [ao.ssm_timestamps[int(np.rint(i))] for i in tempo_foote_peaks] + # + # # Experiment 2: Trying combined features using the best boundary retrieval method + # ao_featureset = [ao.gammatone_features, ao.harmonic_features, ao.timbre_features, ao.tempo_features] + # feature_sel = [int(x) for x in options.FEATURES if x.isdigit()] + # fused_featureset = [ao_featureset[i] for i in feature_sel] + + # if options.LABEL == 'fmc2d': + # gammatone_fmc2d_labels = fmc2d_S.compute_similarity(gammatone_bound_idxs, xmeans=True, N=N) + # timbre_fmc2d_labels = fmc2d_S.compute_similarity(timbre_bound_idxs, xmeans=True, N=N) + # tempo_fmc2d_labels = fmc2d_S.compute_similarity(tempo_bound_idxs, xmeans=True, N=N) + # harmonic_fmc2d_labels = fmc2d_S.compute_similarity(harmonic_bound_idxs, xmeans=True, N=N) + # + # if options.LABEL == 'cnmf': + # gammatone_cnmf_labels = cnmf_S.compute_labels(gammatone_bound_idxs, est_bound_idxs, nFrames) + # timbre_cnmf_labels = cnmf_S.compute_labels(timbre_bound_idxs, est_bound_idxs, nFrames) + # tempo_cnmf_labels = cnmf_S.compute_labels(tempo_bound_idxs, est_bound_idxs, nFrames) + # harmonic_cnmf_labels = cnmf_S.compute_labels(harmonic_bound_idxs, est_bound_idxs, nFrames) + # + # + def main():