filepath = os.path.join(data_output, "checkpoints",
"weights-improvement-{epoch:02d}-{PSNR:.2f}.hdf5")
checkpoint = ModelCheckpoint(filepath, monitor=PSNR, verbose=1, mode='max')
callbacks_list = [checkpoint]
model.fit(X, y, epochs=EPOCHS,
validation_split=0.20,
batch_size=BATCH_SIZE, callbacks=callbacks_list, shuffle="batch")
print("Done training!!!")
print("Saving the final model ...")
model.save(os.path.join(data_output,"fsrcnn_Sat-6_Epoch{}_VIS2NIR.h5".format(EPOCHS))) # creates a HDF5 file
y_pred = model.predict(x_true)
n = y_true.shape[0]
mses = 0
rmses = 0
psnrs = 0
ssims = 0
for i in range(0,n):
print("Testing {}/{}...".format(i,n))
y = y_true[i,:,:,0]
y_prime = y_pred[i,:,:,0]
mses = mses + mse(y, y_prime)
rmses = rmses + rmse(y, y_prime)
psnrs = psnrs + psnr(y, y_prime, data_range=y_prime.max() - y_prime.min())
ssims = ssims + ssim(y, y_prime, data_range=y_prime.max() - y_prime.min())
mses = mses / n
rmses = rmses / n
batch_psnr = []
for row in range(0, rows):
for col in range(0, cols):
x = col * stride
y = row * stride
# Getting patches...
patch = raw[x:x + stride, y:y + stride]
scale = Image.fromarray(patch, 'L')
scale = scale.resize((ratio, ratio), Image.BICUBIC)
scale = np.array(scale)
x_true = scale / 255.
y_true = patch / 255.
x_prime = np.expand_dims(x_true, axis=2)
x_prime = np.expand_dims(x_prime, axis=0)
y_pred = model.predict(x_prime)
y_pred = y_pred[0, :, :, 0]
mse = np.mean((y_true - y_pred)**2)
batch_mse.append(mse)
psnr = 20 * np.log10(1 / np.sqrt(mse))
batch_psnr.append(psnr)
ssim = SSIM(y_true, y_pred)
batch_ssim.append(ssim)
#print("Count={} Image={} MSE={} SSIM={} PSNR={}".format(count, filename, mse, ssim, psnr))
out[x:x + stride, y:y + stride] = (y_pred * 255).astype(np.uint8)
plt.subplot(131)
plt.imshow(x_true, cmap='Greys')
plt.subplot(132)
plt.imshow(y_true, cmap='Greys')
plt.subplot(133)
