def process_folder(folder_path, quantization, temporal_granularity):
# Get instrus and prs from a folder name name
pr0, instru0, _, name0, pr1, instru1, _, name1 = build_data_aux.get_instru_and_pr_from_folder_path(folder_path, quantization)
# Temporal granularity
if temporal_granularity == 'event_level':
pr0 = warp_pr_aux(pr0, get_event_ind_dict(pr0))
pr1 = warp_pr_aux(pr1, get_event_ind_dict(pr1))
# Get trace from needleman_wunsch algorithm
# Traces are binary lists, 0 meaning a gap is inserted
trace_0, trace_1, this_sum_score, this_nbId, this_nbDiffs = needleman_chord_wrapper(sum_along_instru_dim(pr0), sum_along_instru_dim(pr1))
# Wrap dictionnaries according to the traces
assert(len(trace_0) == len(trace_1)), "size mismatch"
pr0_warp = warp_dictionnary_trace(pr0, trace_0)
pr1_warp = warp_dictionnary_trace(pr1, trace_1)
# Get pr warped and duration# In fact we just discard 0 in traces for both pr
trace_prod = [e1 * e2 for (e1,e2) in zip(trace_0, trace_1)]
duration = sum(trace_prod)
if duration == 0:
return [None]*7
pr0_aligned = remove_zero_in_trace(pr0_warp, trace_prod)
pr1_aligned = remove_zero_in_trace(pr1_warp, trace_prod)
return pr0_aligned, instru0, name0, pr1_aligned, instru1, name1, duration
def align_tracks(pr0, pr1, unit_type, gapopen, gapextend):
# Get trace from needleman_wunsch algorithm
# First extract binary representation, whatever unit_type is
pr0_binary = Unit_type.from_type_to_binary(pr0, unit_type)
pr1_binary = Unit_type.from_type_to_binary(pr1, unit_type)
pr0_trace = sum_along_instru_dim(pr0_binary)
pr1_trace = sum_along_instru_dim(pr1_binary)
# Traces are computed from binaries matrices
# Traces are binary lists, 0 meaning a gap is inserted
trace_0, trace_1, this_sum_score, this_nbId, this_nbDiffs = needleman_chord_wrapper(pr0_trace, pr1_trace, gapopen, gapextend)
####################################
# Wrap dictionnaries according to the traces
assert(len(trace_0) == len(trace_1)), "size mismatch"
pr0_warp = warp_dictionnary_trace(pr0, trace_0)
pr1_warp = warp_dictionnary_trace(pr1, trace_1)
####################################
# Trace product
trace_prod = [e1 * e2 for (e1, e2) in zip(trace_0, trace_1)]
duration = sum(trace_prod)
if duration == 0:
return [None]*6
# Remove gaps
pr0_aligned = remove_zero_in_trace(pr0_warp, trace_prod)
pr1_aligned = remove_zero_in_trace(pr1_warp, trace_prod)
return pr0_aligned, trace_0, pr1_aligned, trace_1, trace_prod, duration
def check_orchestration_alignment(path_db, subfolder_names, quantization, gapopen, gapextend):
output_dir = 'DEBUG/' + str(quantization) +\
'_' + str(gapopen) +\
'_' + str(gapextend)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
else:
# Avoid re-running the algo on already tested parameters
return
counter = 0
sum_score = 0
nbFrame = 0
nbId = 0
nbDiffs = 0
# num_track_browsed = 30
for sub_db in subfolder_names:
print '#' * 30
print sub_db
sub_db_path = path_db + '/' + sub_db
if not os.path.isdir(sub_db_path):
continue
# list_tracks_dir = os.listdir(sub_db_path)
# ind_folder = np.random.permutation(len(list_tracks_dir))
# for ind in ind_folder[:num_track_browsed]:
# for ind in list_tracks_dir:
# folder_name = list_tracks_dir[ind]
for folder_name in os.listdir(sub_db_path):
print '#' * 20
print '#' + folder_name + '\n'
folder_path = sub_db_path + '/' + folder_name
if not os.path.isdir(folder_path):
continue
# Get instrus and prs from a folder name name
pr0, instru0, T0, path_0, pr1, instru1, T1, path_1 = build_data_aux.get_instru_and_pr_from_folder_path(folder_path, quantization=quantization, clip=True)
# name_0 = re.split('/', path_0)[-1]
# name_1 = re.split('/', path_1)[-1]
################################################
################################################
# def auxiaux(pr, limit):
# pr_bis = pr
# pr = {}
# for k,v in pr_bis.iteritems():
# pr[k] = v[:limit,:]
# return pr
# pr0 = auxiaux(pr0, 26)
# pr1 = auxiaux(pr1, 48)
################################################
################################################
# Get trace from needleman_wunsch algorithm
# Traces are binary lists, 0 meaning a gap is inserted
trace_0, trace_1, this_sum_score, this_nbId, this_nbDiffs = needleman_chord_wrapper(sum_along_instru_dim(pr0), sum_along_instru_dim(pr1))
# Wrap dictionnaries according to the traces
assert(len(trace_0) == len(trace_1)), "size mismatch"
pr0_warp = warp_dictionnary_trace(pr0, trace_0)
pr1_warp = warp_dictionnary_trace(pr1, trace_1)
# In fact we just discard 0 in traces for both pr
trace_prod = [e1 * e2 for (e1,e2) in zip(trace_0, trace_1)]
if sum(trace_prod) == 0:
# It's definitely not a match...
# Check for the files : are they really an piano score and its orchestration ??
with(open('log.txt', 'a')) as f:
f.write(folder_path + '\n')
continue
pr0_aligned = remove_zero_in_trace(pr0_warp, trace_prod)
pr1_aligned = remove_zero_in_trace(pr1_warp, trace_prod)
# Sum all instrument
AAA_warp = sum_along_instru_dim(pr0_warp)
BBB_warp = sum_along_instru_dim(pr1_warp)
OOO_warp = np.zeros((BBB_warp.shape[0], 30), dtype=np.int16)
CCC_warp = np.concatenate((AAA_warp, OOO_warp, BBB_warp), axis=1)
AAA_aligned = sum_along_instru_dim(pr0_aligned)
BBB_aligned = sum_along_instru_dim(pr1_aligned)
OOO_aligned = np.zeros((BBB_aligned.shape[0], 30), dtype=np.int16)
CCC_aligned = np.concatenate((AAA_aligned, OOO_aligned, BBB_aligned), axis=1)
# Update statistics
nbFrame += len(trace_0)
sum_score += this_sum_score
nbId += this_nbId
nbDiffs += this_nbDiffs
counter = counter + 1
# Save every 100 example
if not counter % 10 == 0:
continue
save_folder_name = output_dir +\
'/' + sub_db + '_' + folder_name
if not os.path.exists(save_folder_name):
os.makedirs(save_folder_name)
temp_csv = save_folder_name + '/warp.csv'
np.savetxt(temp_csv, CCC_warp, delimiter=',')
dump_to_csv(temp_csv, temp_csv)
write_numpy_array_html(save_folder_name + "/pr_warp.html", "warp")
temp_csv = save_folder_name + '/aligned.csv'
np.savetxt(temp_csv, CCC_aligned, delimiter=',')
dump_to_csv(temp_csv, temp_csv)
write_numpy_array_html(save_folder_name + "/pr_aligned.html", "aligned")
write_midi(pr={'piano1': sum_along_instru_dim(pr0)}, quantization=quantization, write_path=save_folder_name + '/0.mid', tempo=80)
write_midi(pr={'piano1': sum_along_instru_dim(pr1)}, quantization=quantization, write_path=save_folder_name + '/1.mid', tempo=80)
write_midi(pr={'piano1': AAA_warp, 'piano2': BBB_warp}, quantization=quantization, write_path=save_folder_name + '/both__warp.mid', tempo=80)
write_midi(pr={'piano1': AAA_aligned, 'piano2': BBB_aligned}, quantization=quantization, write_path=save_folder_name + '/both__aligned.mid', tempo=80)
# Write statistics
mean_score = float(sum_score) / nbFrame
nbId_norm = nbId / quantization
nbDiffs_norm = nbDiffs / quantization
with open(output_dir + '/log.txt', 'wb') as f:
f.write("##########################\n" +
"quantization = %d\n" % quantization +
"Gapopen = %d\n" % gapopen +
"Gapextend = %d\n" % gapextend +
"Number frame = %d\n" % nbFrame +
"\n\n\n" +
"Sum score = %d\n" % sum_score+
"Mean score = %f\n" % mean_score+
"Number id = %d\n" % nbId +
"Number id / quantization = %d\n" % nbId_norm+
"Number diffs = %d\n" % nbDiffs+
"Number diffs / quantization = %d\n" % nbDiffs_norm)
def align_tracks_removing_silences(pr0, pr1, unit_type, gapopen, gapextend):
# Mapping_0 is a vector of size pr0, with values of the index in the new pr and -1 for a silence
# Remove zeros
pr0_no_silence, mapping_0 = remove_silence(pr0)
pr1_no_silence, mapping_1 = remove_silence(pr1)
# Get trace from needleman_wunsch algorithm
# Traces are computed from binaries matrices
# Traces are binary lists, 0 meaning a gap is inserted
pr0_trace = sum_along_instru_dim(Unit_type.from_type_to_binary(pr0_no_silence, unit_type))
pr1_trace = sum_along_instru_dim(Unit_type.from_type_to_binary(pr1_no_silence, unit_type))
trace_0, trace_1, this_sum_score, this_nbId, this_nbDiffs = needleman_chord_wrapper(pr0_trace, pr1_trace, gapopen, gapextend)
####################################
####################################
# Wrap dictionnaries according to the traces
assert(len(trace_0) == len(trace_1)), "size mismatch"
pr0_warp = warp_dictionnary_trace(pr0_no_silence, trace_0)
pr1_warp = warp_dictionnary_trace(pr1_no_silence, trace_1)
####################################
####################################
####################################
####################################
# Trace product
trace_prod = [e1 * e2 for (e1, e2) in zip(trace_0, trace_1)]
duration = sum(trace_prod)
if duration == 0:
return [None]*5
# Remove gaps
pr0_aligned = remove_zero_in_trace(pr0_warp, trace_prod)
pr1_aligned = remove_zero_in_trace(pr1_warp, trace_prod)
# New mapping :
# some element are lost, replace them by silences
# and decrease the indices
def remove_gaps_mapping(mapping, trace, trace_prod):
index = 0
counter = 0
for (t, t_prod) in zip(trace, trace_prod):
if (t == 1) and (t_prod == 0):
# Element lost
while(mapping[index] == -1):
index += 1
# Replace i with a silence
mapping[index] = -1
elif (t == 1) and (t_prod == 1):
while(mapping[index] == -1):
index += 1
mapping[index] = counter
counter += 1
index += 1
return mapping
mapping_0_aligned = remove_gaps_mapping(mapping_0, trace_0, trace_prod)
mapping_1_aligned = remove_gaps_mapping(mapping_1, trace_1, trace_prod)
# Actually it is easier to have the indices of the non silent frames in the original score :
non_silent_0 = np.where(mapping_0_aligned != -1)[0]
non_silent_1 = np.where(mapping_1_aligned != -1)[0]
####################################
####################################
# # Remove zeros in one score, but not in the other
# pr0_no_unmatched_silence, pr1_no_unmatched_silence, duration = remove_unmatched_silence(pr0_aligned, pr1_aligned)
#
# # Remove zeros in both piano and orchestra : we don't want to learn mapping from zero to zero
# pr0_out, pr1_out, duration = remove_match_silence(pr0_no_unmatched_silence, pr1_no_unmatched_silence)
return pr0_aligned, non_silent_0, pr1_aligned, non_silent_1, duration