visualize_rgb(map1.weights)
# +
classification
# +
# +
tens_try = map1.weights.view(length, width, 3)
plt.imshow(tens_try)
classification = map1.classify_all(map1.convert_data_tensor(data))
for i in range(len(classification)):
loc_tuple = map1.get_location(classification[i])
plt.text(loc_tuple[1], loc_tuple[0], color_names[i], ha='center', va='center',
bbox=dict(facecolor='white', alpha=0.5, lw=0))
z
# plt.text(0, 1, color_names[1], ha='center', va='center',
# bbox=dict(facecolor='white', alpha=0.5, lw=0))
plt.show()
# -
visualize_rgb(map1)
shuffle=True)
return trainloader, dim, number_rows_data
# -
def large_cycle(map_, training_data):
basic_visualization(map_display(map_.map))
print(map_display(map_.map))
for i in range(number_iterations):
cycle(map_, training_data)
basic_visualization(map_display(map_.map))
print(map_display(map_.map))
training, dim, number_rows_data = load_data(data)
map1 = MapClass(length, width, dim, move_closer_coef, number_iterations)
map1.weights_to_map()
map1.step(training, verbose=True)
map1.cycle(training, verbose=True)
map1.classify_all(map1.convert_data_tensor(data))
map1.convert_data_tensor(data)
