Ejemplos de input_rates_sparse en Python

Ejemplo n.º 1

Archivo: main_batch.py Proyecto: erensezener/grid-cell-simulation

print 'reading data'
rat_data = rat_simulator.rat_txt_to_matrix(FILENAME)
print 'data read'
# rat_data = rat_data[:1e4,:]
print 'number of data points: ' + str(np.shape(rat_data))
number_of_data_points = np.size(rat_data, 0)

output_layer = fast_output_layer_batch.FastOutputLayerBatch(number_of_data_points, NUMBER_OF_BATCHES)

batch_size = int(number_of_data_points / NUMBER_OF_BATCHES)

for i in range(NUMBER_OF_BATCHES):
    print 'batch: ' + str(i)
    a = datetime.datetime.now().replace(microsecond=0)
    input_layer_outputs = input_neuron.input_rates_sparse(rat_data[i*batch_size:((i+1)*batch_size), :])
    b = datetime.datetime.now().replace(microsecond=0)
    # io.mmwrite(INPUT_LAYER_OUTPUTS, input_layer_outputs) #write sparse matrix to a file in COO format
    print 'number of nnz from input layer ' + str(input_layer_outputs.nnz)
    print 'input processed in ' + str(b-a)

    a = datetime.datetime.now().replace(microsecond=0)
    output_layer.process_all_inputs(input_layer_outputs)
    b = datetime.datetime.now().replace(microsecond=0)
    print 'output processed in ' + str(b-a)

output_layer.save_data_to_disk()


for i in range(100):
    weights = input_neuron.reshape_vec_to_grid(output_layer.weights[i, :])

Ejemplo n.º 2

Archivo: main.py Proyecto: satpreetsingh/grid-cell-simulation

SUB_DIR = '9M'
FILENAME = 'data/Rat_Data_9M.txt'
INPUT_LAYER_OUTPUTS = 'results/' + SUB_DIR + '/input_layer.mtx'
# FILENAME = 'data/Rat_Data.txt'

# if not os.path.isdir(SUB_DIR):
#     os.makedirs(SUB_DIR)

print 'reading data'
rat_data = rat_simulator.rat_txt_to_matrix(FILENAME)
print 'data read'
# rat_data = rat_data[:1e6,:]
print 'number of data points: ' + str(np.shape(rat_data))

a = datetime.datetime.now().replace(microsecond=0)
input_layer_outputs = input_neuron.input_rates_sparse(rat_data)
b = datetime.datetime.now().replace(microsecond=0)
io.mmwrite(INPUT_LAYER_OUTPUTS,
           input_layer_outputs)  #write sparse matrix to a file in COO format
print 'number of nnz from input layer ' + str(input_layer_outputs.nnz)
print 'input processed in ' + str(b - a)

a = datetime.datetime.now().replace(microsecond=0)
output_layer = fast_output_layer.FastOutputLayer(input_layer_outputs)
output_layer.process_all_inputs()
b = datetime.datetime.now().replace(microsecond=0)
print 'output processed in ' + str(b - a)

for i in range(100):
    weights = input_neuron.reshape_vec_to_grid(output_layer.weights[i, :])
    plt.matshow(weights)

Ejemplo n.º 3

Archivo: main.py Proyecto: erensezener/grid-cell-simulation

FILENAME = 'data/Rat_Data_9M.txt'
INPUT_LAYER_OUTPUTS = 'results/' + SUB_DIR + '/input_layer.mtx'
# FILENAME = 'data/Rat_Data.txt'

# if not os.path.isdir(SUB_DIR):
#     os.makedirs(SUB_DIR)


print 'reading data'
rat_data = rat_simulator.rat_txt_to_matrix(FILENAME)
print 'data read'
# rat_data = rat_data[:1e6,:]
print 'number of data points: ' + str(np.shape(rat_data))

a = datetime.datetime.now().replace(microsecond=0)
input_layer_outputs = input_neuron.input_rates_sparse(rat_data)
b = datetime.datetime.now().replace(microsecond=0)
io.mmwrite(INPUT_LAYER_OUTPUTS, input_layer_outputs) #write sparse matrix to a file in COO format
print 'number of nnz from input layer ' + str(input_layer_outputs.nnz)
print 'input processed in ' + str(b-a)

a = datetime.datetime.now().replace(microsecond=0)
output_layer = fast_output_layer.FastOutputLayer(input_layer_outputs)
output_layer.process_all_inputs()
b = datetime.datetime.now().replace(microsecond=0)
print 'output processed in ' + str(b-a)

for i in range(100):
    weights = input_neuron.reshape_vec_to_grid(output_layer.weights[i, :])
    plt.matshow(weights)
    plt.colorbar()

Ejemplo n.º 4

Archivo: main_batch.py Proyecto: satpreetsingh/grid-cell-simulation

print 'reading data'
rat_data = rat_simulator.rat_txt_to_matrix(FILENAME)
print 'data read'
# rat_data = rat_data[:1e4,:]
print 'number of data points: ' + str(np.shape(rat_data))
number_of_data_points = np.size(rat_data, 0)

output_layer = fast_output_layer_batch.FastOutputLayerBatch(
    number_of_data_points, NUMBER_OF_BATCHES)

batch_size = int(number_of_data_points / NUMBER_OF_BATCHES)

for i in range(NUMBER_OF_BATCHES):
    print 'batch: ' + str(i)
    a = datetime.datetime.now().replace(microsecond=0)
    input_layer_outputs = input_neuron.input_rates_sparse(
        rat_data[i * batch_size:((i + 1) * batch_size), :])
    b = datetime.datetime.now().replace(microsecond=0)
    # io.mmwrite(INPUT_LAYER_OUTPUTS, input_layer_outputs) #write sparse matrix to a file in COO format
    print 'number of nnz from input layer ' + str(input_layer_outputs.nnz)
    print 'input processed in ' + str(b - a)

    a = datetime.datetime.now().replace(microsecond=0)
    output_layer.process_all_inputs(input_layer_outputs)
    b = datetime.datetime.now().replace(microsecond=0)
    print 'output processed in ' + str(b - a)

output_layer.save_data_to_disk()

for i in range(100):
    weights = input_neuron.reshape_vec_to_grid(output_layer.weights[i, :])
    plt.matshow(weights)