moving_mean = [
v for v in tf.global_variables() if v.name == mean_name
][0]
saver_dict.update({"l" + str(l) + "/BN/gamma": gamma})
saver_dict.update({"l" + str(l) + "/BN/beta": beta})
saver_dict.update(
{"l" + str(l) + "/BN/moving_variance": moving_variance})
saver_dict.update(
{"l" + str(l) + "/BN/moving_mean": moving_mean})
saver_initvars = tf.train.Saver(saver_dict)
saver_initvars.restore(sess, save_name)
else:
#save_name = LDAMP.GenLDAMPFilename(alg, tie_weights, LayerbyLayer) + ".ckpt"
save_name = LDAMP.GenLDAMPFilename(
alg,
tie_weights,
LayerbyLayer,
sampling_rate_override=sampling_rate_train,
loss_func=TrainLoss) + ".ckpt"
saver.restore(sess, save_name)
print("Reconstructing Signal")
start_time = time.time()
Final_PSNRs = []
for offset in range(
0, n_Test_Images - BATCH_SIZE + 1, BATCH_SIZE
): # Subtract batch size-1 to avoid eerrors when len(train_images) is not a multiple of the batch size
end = offset + BATCH_SIZE
# batch_y_test = y_test[:, offset:end] #To be used when using precomputed measurements
# Generate a new measurement matrix
optimizer = optimizer0.minimize(cost, var_list=vars_to_train)
saver_best = tf.train.Saver() # defaults to saving all variables
saver_dict={}
with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess:
sess.run(tf.global_variables_initializer())#Seems to be necessary for the batch normalization layers for some reason.
if FLAGS.debug:
sess = tf_debug.LocalCLIDebugWrapperSession(sess)
sess.add_tensor_filter("has_inf_or_nan", tf_debug.has_inf_or_nan)
start_time = time.time()
print("Load Initial Weights ...")
if ResumeTraining or learning_rate!=learning_rates[0]:
##Load previous values for the weights
saver_initvars_name_chckpt = LDAMP.GenLDAMPFilename(alg, tie_weights, LayerbyLayer,loss_func=loss_func) + ".ckpt"
for iter in range(n_layers_trained):#Create a dictionary with all the variables except those associated with the optimizer.
for l in range(0, n_DnCNN_layers):
saver_dict.update({"Iter" + str(iter) + "/l" + str(l) + "/w": theta[iter][0][l]})#,
#"Iter" + str(iter) + "/l" + str(l) + "/b": theta[iter][1][l]})
for l in range(1, n_DnCNN_layers - 1): # Associate variance, means, and beta
gamma_name = "Iter" + str(iter) + "/l" + str(l) + "/BN/gamma:0"
beta_name = "Iter" + str(iter) + "/l" + str(l) + "/BN/beta:0"
var_name = "Iter" + str(iter) + "/l" + str(l) + "/BN/moving_variance:0"
mean_name = "Iter" + str(iter) + "/l" + str(l) + "/BN/moving_mean:0"
gamma = [v for v in tf.global_variables() if v.name == gamma_name][0]
beta = [v for v in tf.global_variables() if v.name == beta_name][0]
moving_variance = [v for v in tf.global_variables() if v.name == var_name][0]
moving_mean = [v for v in tf.global_variables() if v.name == mean_name][0]
saver_dict.update({"Iter" + str(iter) + "/l" + str(l) + "/BN/gamma": gamma})
saver_dict.update({"Iter" + str(iter) + "/l" + str(l) + "/BN/beta": beta})