def evaluate_learning(SOM, data_type, neurons_nbr):
inputs = Parameters({"alpha": Variable(start=0.6, end=0.05, nb_steps=nb_epochs),
"sigma": Variable(start=0.5, end=0.001, nb_steps=nb_epochs),
"data": data_type,
"neurons_nbr": (neurons_nbr, neurons_nbr),
"epochs_nbr": nb_epochs})
som = SOM(inputs)
som.run()
nb_comp = np.mean(som.nbr_quad_dist)
return {"nbr_comparisons": nb_comp, "percentage_calculated": nb_comp/(neurons_nbr**2)*100}
def runSOM(self):
if self.data is None:
self.load_dataset()
nb_epochs = self.model["nb_epochs"]
if "alpha_start" not in self.model: self.model["alpha_start"] = 0.2
if "alpha_end" not in self.model: self.model["alpha_end"] = 0.05
if "sigma_start" not in self.model: self.model["sigma_start"] = 0.7
if "sigma_end" not in self.model: self.model["sigma_end"] = 0.015
if "nb_images_evals" not in self.dataset:
self.dataset["nb_images_evals"] = 75
parameters = Parameters({
"alpha":
Variable(start=self.model["alpha_start"],
end=self.model["alpha_end"],
nb_steps=nb_epochs),
"sigma":
Variable(start=self.model["sigma_start"],
end=self.model["sigma_end"],
nb_steps=nb_epochs),
"data":
self.data.get_data(),
"neurons_nbr": (self.model["width"], self.model["height"]),
"epochs_nbr":
nb_epochs
})
if self.model["model"] == "standard":
self.map = SOM(parameters)
elif self.model["model"] == "fast":
self.map = FastSOM(parameters)
elif self.model["model"] == "recursive":
self.map = RecursiveSOM(parameters)
else:
print("Error : Unknown model !")
# if "initialisation" not in self.codebooks:
# self.codebooks["initialisation"] = self.som.neurons.tolist()
if "final" in self.codebooks:
self.map.neurons = np.asarray(self.codebooks["final"])
else:
self.map.run()
#for i in range(nb_epochs):
# self.map.run_epoch()
#self.codebooks["final"] = copy.deepcopy(self.map.neurons.tolist())
# for i in range(nb_epochs):
# print("Epoch "+str(i+1))
# if "Epoch "+str(i + 1) not in self.codebooks:
# if self.training_data is not None:
# self.som.data = self.training_data.get_data(self.som.data.shape[0])
# self.som.run_epoch()
# # self.codebooks["Epoch " + str(i + 1)] = copy.deepcopy(self.som.neurons.tolist())
# self.som.run_epoch()
self.map.data = self.data.get_data()
def evaluate_reconstruction(SOM, data_type):
inputs = Parameters({"alpha": Variable(start=0.6, end=0.05, nb_steps=nb_epochs),
"sigma": Variable(start=0.5, end=0.001, nb_steps=nb_epochs),
"data": data_type,
"neurons_nbr": n_nbr,
"epochs_nbr": nb_epochs})
st_som = StandardSOM(inputs)
st_som.run()
som = SOM(inputs)
som.neurons = st_som.neurons
return {"MSQE_R": som.mean_square_quantization_error()}
def learning(self, bkg_image):
# PARAMETERS
self.image_parameters = Parameters({"pictures_dim": self.pictures_dim})
data = MosaicImage(bkg_image, self.image_parameters)
inputs_SOM = Parameters({"alpha": Variable(start=self.alpha_start, end=self.alpha_end, nb_steps=self.nb_epochs),
"sigma": Variable(start=self.sigma_start, end=self.sigma_end, nb_steps=self.nb_epochs),
"data": data.get_data(),
"neurons_nbr": self.neurons_nb,
"epochs_nbr": self.nb_epochs})
self.som = SOM(inputs_SOM)
# RUN
for i in range(self.nb_epochs):
# print('Epoch', i)
self.som.run_epoch()
self.initial_map = self.som.get_all_winners()
def evaluate_learning(SOM, data_type):
inputs = Parameters({
"alpha":
Variable(start=0.6, end=0.05, nb_steps=nb_epochs),
"sigma":
Variable(start=0.5, end=0.001, nb_steps=nb_epochs),
"data":
data_type,
"neurons_nbr":
n_nbr,
"epochs_nbr":
nb_epochs
})
som = SOM(inputs)
som.run()
msqe_r, nb_errors = som.mean_square_quantization_error_secondary()
return {
"MSQE_L": som.mean_square_quantization_error(),
"MSDtN": som.mean_square_distance_to_neighbour(),
"MSQE_R": msqe_r,
"Error Nbr": nb_errors,
"Error %:": nb_errors / data_type.shape[0] * 100
}
for j in np.ndindex(self.neurons_nbr):
if hexagonal_distance(np.asarray(i), np.asarray(j)) <= 1:
error[i] += np.mean((self.neurons[i] - self.neurons[j])**2)
nb_neighbours += 1
error[i] /= nb_neighbours
return np.mean(error)
if __name__ == '__main__':
for n in range(10, 61, 2):
start = time.time()
nb_epochs = 10
inputs = Parameters({
"alpha":
Variable(start=0.6, end=0.05, nb_steps=nb_epochs),
"sigma":
Variable(start=0.5, end=0.2, nb_steps=nb_epochs),
"data":
MosaicImage(
Image.open(
"/users/yabernar/workspace/watSOM/Code/fast_som/Elijah.png"
), Parameters({"pictures_dim": [10, 10]})).get_data(),
"neurons_nbr": (n, n),
"epochs_nbr":
nb_epochs
})
som = FastSOM(inputs)
som.run()
temporal_ROI = (1, 200)
plot = None
bkg = Image.open(chosen_path + "/input/" + 'bkg.jpg')
# bkg = Image.open(path2 + video + '{0:05d}.png'.format(1))
# bkg = Image.open(path3 + "example_base.png")
############
# LEARNING #
############
pictures_dim = [10, 10]
parameters = Parameters({"pictures_dim": pictures_dim})
data = MosaicImage(bkg, parameters)
nb_epochs = 50
inputs_SOM = Parameters({
"alpha":
Variable(start=0.5, end=0.25, nb_steps=nb_epochs),
"sigma":
Variable(start=0.1, end=0.03, nb_steps=nb_epochs),
"data":
data.get_data(),
"neurons_nbr": (10, 10),
"epochs_nbr":
nb_epochs
})
som = SOM(inputs_SOM)
for i in range(nb_epochs):
print('Epoch ', i)
som.run_epoch()
original = data.image
reconstructed = Image.fromarray(
data.reconstruct(som.get_reconstructed_data()))
error[i] = np.mean(np.abs(self.data[i] - self.neurons[winners[i]]))
return np.mean(error)
def square_error(self, winners=None):
if winners is None:
winners = self.get_all_winners()
error = np.zeros(winners.shape)
for i in np.ndindex(winners.shape):
error[i] = np.mean((self.data[i] - self.neurons[winners[i]])**2)
return np.mean(error)
if __name__ == '__main__':
start = time.time()
nb_epochs = 50
inputs = Parameters({"alpha": Variable(start=0.6, end=0.05, nb_steps=nb_epochs),
"sigma": Variable(start=0.5, end=0.001, nb_steps=nb_epochs),
"data": sierpinski_carpet(200),
"neurons_nbr": (10, 10),
"epochs_nbr": nb_epochs})
som = SOM(inputs)
som.run()
end = time.time()
print("Executed in " + str(end - start) + " seconds.")
print(som.mean_error(som.get_all_winners()))
print(som.square_error(som.get_all_winners()))