def last_pool(h1,p,l,c,percentiles):
m1, h0_births, h1_births = max_pooling_filtration(h1, p, l, c, percentile=percentiles[l])
enums = m1
comp_percentile = percentiles[l-1] if percentiles[l-1] < percentiles[l] else percentiles[l]
enums += [([spec_hash((l,c,i[0]%c))], h0_births[i].item()) for i in np.argwhere(h0_births > comp_percentile)]
enums += [([spec_hash((l+1,0,i[0]+(c*h1_births.shape[0])))], h1_births[i].item()) for i in np.argwhere(h1_births > percentiles[l])]
return enums
def first_layer(x,p,l,c,percentile,stride,nlc):
mat = conv_layer_as_matrix(p, x, stride)
m1, h0_births, h1_births = conv_filtration_fast2(x, mat, l, c, nlc, percentile=percentile)
enums = m1
enums += [([spec_hash((l,c,i[0]))], h0_births[i].item()) for i in np.argwhere(h0_births > percentile)]
enums += [([spec_hash((l+1,i[0]//nlc,i[0]%nlc))], h1_births[i].item()) for i in np.argwhere(h1_births > percentile)]
return enums
def mid_conv(h1,p,l,c,percentiles,stride,nlc):
mat = conv_layer_as_matrix(p, h1, stride)
m1, h0_births, h1_births = conv_filtration_fast2(h1, mat, l, c, nlc, percentile=percentiles[l])
enums = m1
comp_percentile = percentiles[l-1] if percentiles[l-1] < percentiles[l] else percentiles[l]
enums += [([spec_hash((l,c,i[0]))], h0_births[i].item()) for i in np.argwhere(h0_births > comp_percentile)]
enums += [([spec_hash((l+1,i[0]//nlc,i[0]%nlc))], h1_births[i].item()) for i in np.argwhere(h1_births > percentiles[l])]
return enums
def compute_induced_filtration_parallel(x,
hiddens,
params,
percentile=0,
stride=1):
pool = mp.Pool(mp.cpu_count())
print('cpu count: {}'.format(mp.cpu_count()))
global enums
global nm
global id
global f
percentiles = np.zeros((len(params)))
x = x.cpu().detach().numpy()
num_channels = x.shape[0]
l = 0
print('layer: {}'.format(l))
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
hn = hiddens[l].cpu().detach().numpy()
nlc = hn.reshape((hn.shape[0], -1)).shape[1]
for c in range(num_channels):
p = params[l].weight.data[:, c, :, :]
r = pool.apply_async(first_layer,
args=(x[c], p, l, c, percentiles[l], stride, nlc),
callback=collect_result)
pool.close()
pool.join()
h = hiddens[l].cpu().detach().numpy()
num_channels = h.shape[0]
l = 1
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
print('layer: {}'.format(l))
pool = mp.Pool(mp.cpu_count())
for c in range(num_channels):
h1 = h[c, :, :]
p = params[l]
r = pool.apply_async(max_pool_layer,
args=(h1, p, l, c, percentiles),
callback=collect_result)
pool.close()
pool.join()
h = hiddens[l].cpu().detach().numpy()
num_channels = h.shape[0]
l = 2
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
hn = hiddens[l].cpu().detach().numpy()
nlc = hn.reshape((hn.shape[0], -1)).shape[1]
print('layer: {}'.format(l))
pool = mp.Pool(mp.cpu_count())
for c in range(num_channels):
p = params[l].weight.data[:, c, :, :]
h1 = h[c, :, :]
r = pool.apply_async(mid_conv,
args=(h1, p, l, c, percentiles, stride, nlc),
callback=collect_result)
pool.close()
pool.join()
h = hiddens[l].cpu().detach().numpy()
num_channels = h.shape[0]
l = 3
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
print('layer: {}'.format(l))
pool = mp.Pool(mp.cpu_count())
for c in range(num_channels):
h1 = h[c, :, :]
p = params[l]
r = pool.apply_async(max_pool_layer,
args=(h1, p, l, c, percentiles),
callback=collect_result)
pool.close()
pool.join()
h = hiddens[l].cpu().detach().numpy()
num_channels = h.shape[0]
l = 4
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
hn = hiddens[l].cpu().detach().numpy()
nlc = hn.reshape((hn.shape[0], -1)).shape[1]
print('layer: {}'.format(l))
pool = mp.Pool(mp.cpu_count())
for c in range(num_channels):
p = params[l].weight.data[:, c, :, :]
h1 = h[c, :, :]
r = pool.apply_async(mid_conv,
args=(h1, p, l, c, percentiles, stride, nlc),
callback=collect_result)
pool.close()
pool.join()
h = hiddens[l].cpu().detach().numpy()
num_channels = h.shape[0]
l = 5
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
hn = hiddens[l].cpu().detach().numpy()
nlc = hn.reshape((hn.shape[0], -1)).shape[1]
print('layer: {}'.format(l))
pool = mp.Pool(mp.cpu_count())
for c in range(num_channels):
p = params[l].weight.data[:, c, :, :]
h1 = h[c, :, :]
r = pool.apply_async(mid_conv,
args=(h1, p, l, c, percentiles, stride, nlc),
callback=collect_result)
pool.close()
pool.join()
h = hiddens[l].cpu().detach().numpy()
num_channels = h.shape[0]
l = 6
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
hn = hiddens[l].cpu().detach().numpy()
nlc = hn.reshape((hn.shape[0], -1)).shape[1]
print('layer: {}'.format(l))
pool = mp.Pool(mp.cpu_count())
for c in range(num_channels):
p = params[l].weight.data[:, c, :, :]
h1 = h[c, :, :]
r = pool.apply_async(mid_conv,
args=(h1, p, l, c, percentiles, stride, nlc),
callback=collect_result)
pool.close()
pool.join()
h = hiddens[l].cpu().detach().numpy()
num_channels = h.shape[0]
l = 7
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
print('layer: {}'.format(l))
pool = mp.Pool(mp.cpu_count())
for c in range(num_channels):
h1 = h[c, :, :]
p = params[l]
r = pool.apply_async(last_pool,
args=(h1, p, l, c, percentiles),
callback=collect_result)
pool.close()
pool.join()
h1 = hiddens[l].cpu().detach().numpy()
l = 8
print('layer: {}'.format(l))
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
p = params[l]
m1, h0_births, h1_births = linear_filtration_fast2(
h1, p, l, 0, percentile=percentiles[l])
enums += m1
comp_percentile = percentiles[
l - 1] if percentiles[l - 1] < percentiles[l] else percentiles[l]
enums += [([spec_hash((l, c, i[0]))], h0_births[i])
for i in np.argwhere(h0_births > comp_percentile)]
h1 = hiddens[l].cpu().detach().numpy()
l = 9
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
print('layer: {}'.format(l))
p = params[l]
m1, h0_births, h1_births_9 = linear_filtration_fast2(
h1, p, l, 0, percentile=percentiles[l])
enums += m1
max1 = np.maximum.reduce([h0_births, h1_bireths])
comp_percentile = percentiles[
l - 1] if percentiles[l - 1] < percentiles[l] else percentiles[l]
enums += [([spec_hash((l, 0, i[0]))], max1[i])
for i in np.argwhere(max1 > comp_percentile)]
h1 = hiddens[l].cpu().detach().numpy()
l = 10
print('layer: {}'.format(l))
percentiles[l] = np.percentile(
np.absolute(hiddens[l].cpu().detach().numpy()), percentile)
p = params[l]
m1, h0_births, h1_births_10 = linear_filtration_fast2(
h1, p, l, 0, percentile=percentiles[l])
enums += m1
max1 = np.maximum.reduce([h0_births, h1_births_9])
comp_percentile = percentiles[
l - 1] if percentiles[l - 1] < percentiles[l] else percentiles[l]
enums += [([spec_hash((l, 0, i[0]))], max1[i])
for i in np.argwhere(max1 > comp_percentile)]
enums += [([spec_hash((l + 1, 0, i[0]))], h1_births_10[i])
for i in np.argwhere(h1_births_10 > percentiles[l])]
collect_result(enums)
# with open('quick_dump.txt', 'w') as fp:
# for k, v in nm.items():
# fp.write('{}, {}\n'.format(k,v))
print('creating filtration object...')
# f = dion.Filtration(enums)
print('filtration size', len(f))
print('Sorting filtration...')
f.sort(reverse=True)
return f, nm