def gamma_ramp_test(dut):
Period = 10
clk = dut.clk
cocotb.fork(gen_clk(clk, Period))
yield Timer(20 * Period)
out_data_fp = data_gen()
# Random test
for i in range(0, 2**12):
reset = 0
dv_in = 1
gamma_in = 0
data_in = i
dut.reset = reset
dut.dv_in = dv_in
dut.gamma_in = gamma_in
dut.data_in = data_in
yield Timer(20 * Period)
if abs(int(dut.data_out) -
out_data_fp[data_in]) > 1 and reset == 0 and dv_in == 1:
raise TestFailure("result is incorrect: %s != %s data_in = %s" %
(str(int(dut.data_out)), str(
out_data_fp[data_in]), str(data_in)))
elif reset == 1 and int(dut.data_out) != 0:
raise TestFailure("result is incorrect. Reset = %s dv = %s" %
(str(reset), str(dut.dv_out)))
elif dv_in == 1 and reset == 0 and int(dut.dv_out) == 1:
dut._log.info("Ok!")
#!/usr/bin/env python
import tifffile
from functions import unet_model_3d, data_gen
if __name__ == "__main__":
image = tifffile.imread('traindata/training_input.tif')
label = tifffile.imread('traindata/training_groundtruth.tif')
res = 48 # 8*n
window_size = (res, res, res)
input_data = data_gen(image, window_size)
label_data = data_gen(label, window_size)
print('image size:', image.shape)
print('data size:', input_data.shape)
model = unet_model_3d((1,) + window_size)
model.summary()
batch_size = 8
no_epochs = 10
model.fit(input_data, label_data, batch_size=batch_size, epochs=no_epochs, verbose=1)
model.save_weights('./3d_unet.h5')