I am trying to create a simple 3D U-net for image segmentation, just to learn how to use the layers. Therefore I do a 3D convolution with stride 2 and then a transpose deconvolution to get back the same image size. I am also overfitting to a small set (test set) just to see if my network is learning.
I created the same net in Keras and it works just fine. Now I want to create in tensorflow but I been having trouble with it.
The cost changes slightly but no matter what I do (reduce learning rate, add more epochs, add more layers, change batch size...) the output is always the same. I believe the net is not updating the weights. I am sure I am doing something wrong but I can find what it is. Any help would be greatly appreciate it.
Here is my code:
def forward_propagation(X):
if ( mode == 'train'): print(" --------- Net --------- ")
# Convolutional Layer 1
with tf.variable_scope('CONV1'):
Z1 = tf.layers.conv3d(X, filters = 16, kernel =[3,3,3], strides = [ 2, 2, 2], padding='SAME', name = 'S2/conv3d')
A1 = tf.nn.relu(Z1, name = 'S2/ReLU')
if ( mode == 'train'): print("Convolutional Layer 1 S2 " + str(A1.get_shape()))
# DEConvolutional Layer 1
with tf.variable_scope('DeCONV1'):
output_deconv1 = tf.stack([X.get_shape()[0] , X.get_shape()[1], X.get_shape()[2], X.get_shape()[3], 1])
dZ1 = tf.nn.conv3d_transpose(A1, filters = 1, kernel =[3,3,3], strides = [2, 2, 2], padding='SAME', name = 'S2/conv3d_transpose')
dA1 = tf.nn.relu(dZ1, name = 'S2/ReLU')
if ( mode == 'train'): print("Deconvolutional Layer 1 S1 " + str(dA1.get_shape()))
return dA1
def compute_cost(output, target, method = 'dice_hard_coe'):
with tf.variable_scope('COST'):
if (method == 'sigmoid_cross_entropy') :
# Make them vectors
output = tf.reshape( output, [-1, output.get_shape().as_list()[0]] )
target = tf.reshape( target, [-1, target.get_shape().as_list()[0]] )
loss = tf.nn.sigmoid_cross_entropy_with_logits(logits = output, labels = target)
cost = tf.reduce_mean(loss)
return cost
and the main function for the model:
def model(X_h5, Y_h5, learning_rate = 0.009,
num_epochs = 100, minibatch_size = 64, print_cost = True):
ops.reset_default_graph() # to be able to rerun the model without overwriting tf variables
#tf.set_random_seed(1) # to keep results consistent (tensorflow seed)
#seed = 3 # to keep results consistent (numpy seed)
(m, n_D, n_H, n_W, num_channels) = X_h5["test_data"].shape #TTT
num_labels = Y_h5["test_mask"].shape[4] #TTT
img_size = Y_h5["test_mask"].shape[1] #TTT
costs = [] # To keep track of the cost
accuracies = [] # To keep track of the accuracy
# Create Placeholders of the correct shape
X, Y = create_placeholders(n_H, n_W, n_D, minibatch_size)
# Forward propagation: Build the forward propagation in the tensorflow graph
nn_output = forward_propagation(X)
prediction = tf.nn.sigmoid(nn_output)
# Cost function: Add cost function to tensorflow graph
cost_method = 'sigmoid_cross_entropy'
cost = compute_cost(nn_output, Y, cost_method)
# Backpropagation: Define the tensorflow optimizer. Use an AdamOptimizer that minimizes the cost.
optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate).minimize(cost)
# Initialize all the variables globally
init = tf.global_variables_initializer()
# Start the session to compute the tensorflow graph
with tf.Session() as sess:
print('------ Training ------')
# Run the initialization
tf.local_variables_initializer().run(session=sess)
sess.run(init)
# Do the training loop
for i in range(num_epochs*m):
# ----- TRAIN -------
current_epoch = i//m
patient_start = i-(current_epoch * m)
patient_end = patient_start + minibatch_size
current_X_train = np.zeros((minibatch_size, n_D, n_H, n_W,num_channels))
current_X_train[:,:,:,:,:] = np.array(X_h5["test_data"][patient_start:patient_end,:,:,:,:]) #TTT
current_X_train = np.nan_to_num(current_X_train) # make nan zero
current_Y_train = np.zeros((minibatch_size, n_D, n_H, n_W, num_labels))
current_Y_train[:,:,:,:,:] = np.array(Y_h5["test_mask"][patient_start:patient_end,:,:,:,:]) #TTT
current_Y_train = np.nan_to_num(current_Y_train) # make nan zero
feed_dict = {X: current_X_train, Y: current_Y_train}
_ , temp_cost = sess.run([optimizer, cost], feed_dict=feed_dict)
# ----- TEST -------
# Print the cost every 1/5 epoch
if ((i % (num_epochs*m/5) )== 0):
# Calculate the predictions
test_predictions = np.zeros(Y_h5["test_mask"].shape)
for j in range(0, X_h5["test_data"].shape[0], minibatch_size):
patient_start = j
patient_end = patient_start + minibatch_size
current_X_test = np.zeros((minibatch_size, n_D, n_H, n_W, num_channels))
current_X_test[:,:,:,:,:] = np.array(X_h5["test_data"][patient_start:patient_end,:,:,:,:])
current_X_test = np.nan_to_num(current_X_test) # make nan zero
current_Y_test = np.zeros((minibatch_size, n_D, n_H, n_W, num_labels))
current_Y_test[:,:,:,:,:] = np.array(Y_h5["test_mask"][patient_start:patient_end,:,:,:,:])
current_Y_test = np.nan_to_num(current_Y_test) # make nan zero
feed_dict = {X: current_X_test, Y: current_Y_test}
_, current_prediction = sess.run([cost, prediction], feed_dict=feed_dict)
test_predictions[j:j + minibatch_size,:,:,:,:] = current_prediction
costs.append(temp_cost)
print ("[" + str(current_epoch) + "|" + str(num_epochs) + "] " + "Cost : " + str(costs[-1]))
display_progress(X_h5["test_data"], Y_h5["test_mask"], test_predictions, 5, n_H, n_W)
# plot the cost
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('epochs')
plt.show()
return
I call the model with:
model(hdf5_data_file, hdf5_mask_file, num_epochs = 500, minibatch_size = 1, learning_rate = 1e-3)
These are the results that I am currently getting:
Edit: I have tried reducing the learning rate and it doesn't help. I also tried using tensorboard debug and the weights are not being updated:
I am not sure why this is happening. I Created the same simple model in keras and it works fine. I am not sure what I am doing wrong in tensorflow.
