Merge pull request #30 from jakeret/tf100

Tf100

AUTHORS.rst

@@ -5,12 +5,13 @@ Credits
 Development Lead
 ----------------
 
-* Joel Akeret <[email protected]>
+* Joel Akeret <[email protected]>
 
 Contributors
 ------------
 
 * `@FelixGruen <https://github.com/FelixGruen>`_ 
+* `@ameya005 <https://github.com/ameya005>`_ 
 
 Citations
 ---------

requirements.txt

@@ -1,3 +1,4 @@
 click
 numpy
-Pillow
+Pillow
+tensorflow>=1.0.0

tf_unet/layers.py

@@ -38,7 +38,7 @@ def conv2d(x, W,keep_prob_):
 
 def deconv2d(x, W,stride):
     x_shape = tf.shape(x)
-    output_shape = tf.pack([x_shape[0], x_shape[1]*2, x_shape[2]*2, x_shape[3]//2])
+    output_shape = tf.stack([x_shape[0], x_shape[1]*2, x_shape[2]*2, x_shape[3]//2])
     return tf.nn.conv2d_transpose(x, W, output_shape, strides=[1, stride, stride, 1], padding='VALID')
 
 def max_pool(x,n):
@@ -51,7 +51,7 @@ def crop_and_concat(x1,x2):
     offsets = [0, (x1_shape[1] - x2_shape[1]) // 2, (x1_shape[2] - x2_shape[2]) // 2, 0]
     size = [-1, x2_shape[1], x2_shape[2], -1]
     x1_crop = tf.slice(x1, offsets, size)
-    return tf.concat(3, [x1_crop, x2])
+    return tf.concat([x1_crop, x2], 3)   
 
 def pixel_wise_softmax(output_map):
     exponential_map = tf.exp(output_map)
@@ -61,7 +61,7 @@ def pixel_wise_softmax(output_map):
 def pixel_wise_softmax_2(output_map):
     exponential_map = tf.exp(output_map)
     sum_exp = tf.reduce_sum(exponential_map, 3, keep_dims=True)
-    tensor_sum_exp = tf.tile(sum_exp, tf.pack([1, 1, 1, tf.shape(output_map)[3]]))
+    tensor_sum_exp = tf.tile(sum_exp, tf.stack([1, 1, 1, tf.shape(output_map)[3]]))
     return tf.div(exponential_map,tensor_sum_exp)
 
 

tf_unet/unet.py

@@ -56,7 +56,7 @@ def create_conv_net(x, keep_prob, channels, n_class, layers=3, features_root=16,
     # Placeholder for the input image
     nx = tf.shape(x)[1]
     ny = tf.shape(x)[2]
-    x_image = tf.reshape(x, tf.pack([-1,nx,ny,channels]))
+    x_image = tf.reshape(x, tf.stack([-1,nx,ny,channels]))
     in_node = x_image
     batch_size = tf.shape(x_image)[0]
 
@@ -215,17 +215,17 @@ def _get_cost(self, logits, cost_name, cost_kwargs):
             if class_weights is not None:
                 class_weights = tf.constant(np.array(class_weights, dtype=np.float32))
 
-                weight_map = tf.mul(flat_labels, class_weights)
+                weight_map = tf.multiply(flat_labels, class_weights)
                 weight_map = tf.reduce_sum(weight_map, axis=1)
 
                 loss_map = tf.nn.softmax_cross_entropy_with_logits(flat_logits, flat_labels)
-                weighted_loss = tf.mul(loss_map, weight_map)
+                weighted_loss = tf.multiply(loss_map, weight_map)
 
                 loss = tf.reduce_mean(weighted_loss)
 
             else:
-                loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(flat_logits, 
-                                                                              flat_labels))
+                loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=flat_logits, 
+                                                                              labels=flat_labels))
         elif cost_name == "dice_coefficient":
             eps = 1e-5
             prediction = pixel_wise_softmax_2(logits)
@@ -498,7 +498,7 @@ def get_image_summary(img, idx=0):
 
     img_w = tf.shape(img)[1]
     img_h = tf.shape(img)[2]
-    V = tf.reshape(V, tf.pack((img_w, img_h, 1)))
+    V = tf.reshape(V, tf.stack((img_w, img_h, 1)))
     V = tf.transpose(V, (2, 0, 1))
-    V = tf.reshape(V, tf.pack((-1, img_w, img_h, 1)))
+    V = tf.reshape(V, tf.stack((-1, img_w, img_h, 1)))
     return V