def do_distribution_weight_init(weights, config, index, shape, **kwargs):
# dimension = 0, kernel level, dimension 1 channel level
# assume weights are untrained weights
# trained = cornet.cornet_s(pretrained=True, map_location=torch.device('cpu'))
# for sub in ['module'] + layers[index].split('.'):
# trained = trained._modules.get(sub)
# weights = trained.weight.data.cpu().numpy()
dim = config['dim'] if 'dim' in config else config[f'dim_{index}']
components = config[f'comp_{index}'] if f'comp_{index}' in config else 0
if dim == 0:
params = weights.reshape(weights.shape[0], weights.shape[1], -1)
params = params.reshape(params.shape[0], -1)
samples = shape[0]
else:
params = weights.reshape(-1, weights.shape[2], weights.shape[3])
params = params.reshape(params.shape[0], -1)
samples = shape[0] * shape[1]
# np.random.seed(0)
samples = mixture_gaussian(params, samples, components, f'weight_dim{dim}_{index}')
idx = 0
new_weights = np.zeros(shape)
if dim is 0:
new_weights = samples.reshape(shape[0], shape[1], shape[2] * shape[3])
new_weights = new_weights.reshape(shape[0], shape[1], shape[2], shape[3])
else:
for i in range(shape[0]):
for j in range(shape[1]):
new_weights[i, j] = samples[idx].reshape(shape[2], shape[3])
idx += 1
# if weights.shape[1] == 3:
# show_kernels(weights, 'distribution_init_channel_color')
# else:
# plot_conv_weights(weights, 'distribution_init_channel')
return new_weights
def do_distribution_gabor_init(weights, config, index, shape, **kwargs):
if index != 0:
rel = config[f'file_{index}']
file = path.join(path.dirname(__file__), f'..{rel}')
params = np.load(file)
else:
rel = config["file"]
file = path.join(path.dirname(__file__), f'..{rel}')
params = np.load(file)
param, tuples = prepare_gabor_params(params)
# np.random.seed(0)
components = config[f'comp_{index}'] if f'comp_{index}' in config else 0
samples = mixture_gaussian(param, shape[0], components, f'gabor_{index}')
new_weights = np.zeros(shape)
for i in range(shape[0]):
for s, e in tuples:
beta = samples[i, s:e]
filter = gabor_kernel_3(beta[0], theta=np.arctan2(beta[1], beta[2]) / 2,
sigma_x=beta[3], sigma_y=beta[4], offset=np.arctan2(beta[5], beta[6]), x_c=beta[7],
y_c=beta[8],
scale=beta[9], ks=shape[-1])
new_weights[i, int(s / 10)] = filter
# if weights.shape[1] == 3:
# show_kernels(new_weights, 'distribution_init')
# else:
# plot_conv_weights(weights, 'distribution_init_kernel')
return new_weights
def do_distribution_gabor_init_channel(weights, config, index, **kwargs):
if index != 0:
params = np.load(config[f'file_{index}'])
else:
params = np.load(f'{config["file"]}')
param, tuples = prepare_gabor_params_channel(params)
# np.random.seed(0)
components = config[f'comp_{index}'] if f'comp_{index}' in config else 0
if components != 0:
return components + components * param.shape[1], components * param.shape[1] * param.shape[1]
best_gmm = mixture_gaussian(param, weights.shape[0], components, f'gabor_{index}', analyze=True)
return len(best_gmm.weights_.flatten()) + len(best_gmm.means_.flatten()) + len(best_gmm.covariances_.flatten())
def do_distribution_gabor_init(weights, config, index, **kwargs):
if index != 0:
rel = config[f'file_{index}']
file = path.join(path.dirname(__file__), f'..{rel}')
params = np.load(file)
else:
rel = config[f'file']
file = path.join(path.dirname(__file__), f'..{rel}')
params = np.load(file)
param, tuples = prepare_gabor_params(params)
# np.random.seed(0)
components = config[f'comp_{index}'] if f'comp_{index}' in config else 0
if components != 0:
return components + components * param.shape[1] + components * param.shape[1] * param.shape[1]
best_gmm = mixture_gaussian(param, weights.shape[0], components, f'gabor_{index}', analyze=True)
return (best_gmm.weights_.size + best_gmm.means_.size + best_gmm.covariances_.size)
def do_distribution_weight_init(weights, config, index, **kwargs):
# dimension = 0, kernel level, dimension 1 channel level
# assume weights are untrained weights
trained = cornet.cornet_s(pretrained=True, map_location=torch.device('cpu'))
for sub in ['module'] + layers[index].split('.'):
trained = trained._modules.get(sub)
weights = trained.weight.data.cpu().numpy()
dim = config['dim'] if 'dim' in config else config[f'dim_{index}']
components = config[f'comp_{index}'] if f'comp_{index}' in config else 0
if dim == 0:
params = weights.reshape(weights.shape[0], weights.shape[1], -1)
params = params.reshape(params.shape[0], -1)
else:
params = weights.reshape(-1, weights.shape[2], weights.shape[3])
params = params.reshape(params.shape[0], -1)
if components != 0:
return components + components * params.shape[1] + components * params.shape[1] * params.shape[1]
best_gmm = mixture_gaussian(params, params.shape[0], components, f'weight_dim{dim}_{index}', analyze=True)
return len(best_gmm.weights_.flatten()) + len(best_gmm.means_.flatten()) + len(best_gmm.covariances_.flatten())
def do_distribution_gabor_init_channel(weights, config, index, shape, **kwargs):
if index != 0:
params = np.load(config[f'file_{index}'])
else:
params = np.load(f'{config["file"]}')
param, tuples = prepare_gabor_params_channel(params)
# np.random.seed(0)
components = config[f'comp_{index}'] if f'comp_{index}' in config else 0
samples = mixture_gaussian(param, shape[0], components)
for i in range(shape[0]):
beta = samples[i]
filter = gabor_kernel_3(beta[0], theta=np.arctan2(beta[1], beta[2]) / 2,
sigma_x=beta[3], sigma_y=beta[4], offset=np.arctan2(beta[5], beta[6]), x_c=beta[7],
y_c=beta[8],
scale=beta[9], ks=shape[-1])
weights[int(i / shape[0]), int(i % shape[0])] = filter
# if weights.shape[1] == 3:
# show_kernels(weights, 'distribution_init_channel_color')
# else:
# plot_conv_weights(weights, 'distribution_init_channel')
return weights
def mixture_base(param, tuples, shape, size=3):
new_param = np.zeros((shape[0], 10 * shape[1]))
for i in range(shape[0]):
for s, e in tuples:
p = param[i, int(s * 8 / 10):int(e * 8 / 10)]
new_param[i, s:e] = (p[0], np.sin(2 * p[1]),
np.cos(2 * p[1]), p[2], p[3], np.sin(p[4]),
np.cos(p[4]), p[5], p[6], p[7])
# plot_bic(best_gmm, param)
best_gmm = mixture_gaussian(new_param)
samples = best_gmm.sample(new_param.shape[0])[0]
idx = 1
plt.figure(figsize=(10, 20))
gs = gridspec.GridSpec(22,
3,
width_ratios=[1] * 3,
wspace=0.5,
hspace=0.5,
top=0.95,
bottom=0.05,
left=0.1,
right=0.95)
for i in range(shape[0]):
for s, e in tuples:
beta = samples[i, s:e]
kernel2 = gabor_kernel_3(beta[0],
theta=np.arctan2(beta[1], beta[2]),
sigma_x=beta[3],
sigma_y=beta[4],
offset=np.arctan2(beta[5], beta[6]),
x_c=beta[7],
y_c=beta[8],
scale=beta[9],
ks=size)
ax = plt.subplot(gs[i, int(s / 10)])
ax.set_xticks([])
ax.set_yticks([])
plt.imshow(kernel2, cmap='gray')
idx += 1
plt.figure(figsize=(15, 15))
length = 64 * 3
matrix = np.empty([length, 0])
weights = samples.reshape(64, 64, 10)
for i in range(0, 64):
row = np.empty([0, 3])
for j in range(0, 64):
beta = weights[i, j]
channel = gabor_kernel_3(beta[0],
theta=np.arctan2(beta[1], beta[2]),
sigma_x=beta[3],
sigma_y=beta[4],
offset=np.arctan2(beta[5], beta[6]),
x_c=beta[7],
y_c=beta[8],
scale=beta[9],
ks=size)
row = np.concatenate((row, channel), axis=0)
f_min, f_max = np.min(row), np.max(row)
row = (row - f_min) / (f_max - f_min)
matrix = np.concatenate((matrix, row), axis=1)
plot_matrixImage(matrix, 'Gabor_conv2')
plt.tight_layout()
plt.show()