Homework part

Author: Ji Zhou

.DS_Store

@@ -86,19 +86,8 @@ def bbox_ohem(bbox_pred,bbox_target,label):
     return tf.reduce_mean(square_error)
 
 def landmark_ohem(landmark_pred,landmark_target,label):
-    #keep label =-2  then do landmark detection
-    ones = tf.ones_like(label,dtype=tf.float32)
-    zeros = tf.zeros_like(label,dtype=tf.float32)
-    valid_inds = tf.where(tf.equal(label,-2),ones,zeros)
-    square_error = tf.square(landmark_pred-landmark_target)
-    square_error = tf.reduce_sum(square_error,axis=1)
-    num_valid = tf.reduce_sum(valid_inds)
-    #keep_num = tf.cast(num_valid*num_keep_radio,dtype=tf.int32)
-    keep_num = tf.cast(num_valid, dtype=tf.int32)
-    square_error = square_error*valid_inds
-    _, k_index = tf.nn.top_k(square_error, k=keep_num)
-    square_error = tf.gather(square_error, k_index)
-    return tf.reduce_mean(square_error)
+    # Implement here!!!!!!!
+    pass
 
 def cal_accuracy(cls_prob,label):
     pred = tf.argmax(cls_prob,axis=1)
@@ -206,51 +195,8 @@ def R_Net(inputs,label=None,bbox_target=None,landmark_target=None,training=True)
             return cls_prob,bbox_pred,landmark_pred
 
 def O_Net(inputs,label=None,bbox_target=None,landmark_target=None,training=True):
-    with slim.arg_scope([slim.conv2d],
-                        activation_fn = prelu,
-                        weights_initializer=slim.xavier_initializer(),
-                        biases_initializer=tf.zeros_initializer(),
-                        weights_regularizer=slim.l2_regularizer(0.0005),                        
-                        padding='valid'):
-        print inputs.get_shape()
-        net = slim.conv2d(inputs, num_outputs=32, kernel_size=[3,3], stride=1, scope="conv1")
-        print net.get_shape()
-        net = slim.max_pool2d(net, kernel_size=[3, 3], stride=2, scope="pool1", padding='SAME')
-        print net.get_shape()
-        net = slim.conv2d(net,num_outputs=64,kernel_size=[3,3],stride=1,scope="conv2")
-        print net.get_shape()
-        net = slim.max_pool2d(net, kernel_size=[3, 3], stride=2, scope="pool2")
-        print net.get_shape()
-        net = slim.conv2d(net,num_outputs=64,kernel_size=[3,3],stride=1,scope="conv3")
-        print net.get_shape()
-        net = slim.max_pool2d(net, kernel_size=[2, 2], stride=2, scope="pool3", padding='SAME')
-        print net.get_shape()
-        net = slim.conv2d(net,num_outputs=128,kernel_size=[2,2],stride=1,scope="conv4")
-        print net.get_shape()               
-        fc_flatten = slim.flatten(net)
-        print fc_flatten.get_shape()
-        fc1 = slim.fully_connected(fc_flatten, num_outputs=256,scope="fc1", activation_fn=prelu)
-        print fc1.get_shape()
-        #batch*2
-        cls_prob = slim.fully_connected(fc1,num_outputs=2,scope="cls_fc",activation_fn=tf.nn.softmax)
-        print cls_prob.get_shape()
-        #batch*4
-        bbox_pred = slim.fully_connected(fc1,num_outputs=4,scope="bbox_fc",activation_fn=None)
-        print bbox_pred.get_shape()
-        #batch*10
-        landmark_pred = slim.fully_connected(fc1,num_outputs=10,scope="landmark_fc",activation_fn=None)
-        print landmark_pred.get_shape()        
-        #train
-        if training:
-            cls_loss = cls_ohem(cls_prob,label)
-            bbox_loss = bbox_ohem(bbox_pred,bbox_target,label)
-            accuracy = cal_accuracy(cls_prob,label)
-            landmark_loss = landmark_ohem(landmark_pred, landmark_target,label)
-            L2_loss = tf.add_n(slim.losses.get_regularization_losses())
-            return cls_loss,bbox_loss,landmark_loss,L2_loss,accuracy
-        else:
-            return cls_prob,bbox_pred,landmark_pred
-            
+    # Implement here!!!!!
+    pass