Updates

• config file from train.py accepts tensors as input
• TFRecord, add keyword argument to flag the shuffling mechanism
• Added InceptionResnetV1 in our basket of networks
• Added an option to sum the regularization losses in the CrossEntropy loss
• Implemented validation with embeddings (officially appending to the tensorboard)
• Created method Trainer.load_variables_from_external_model that load variables from another model in the current graph
• Implemented MeanSoftMaxLossCenterLoss (http://ydwen.github.io/papers/WenECCV16.pdf)
• Patched InceptionV2 (Added the flag trainable for each variable in the model)
• Implemented TFRecordImage (read, data augmentation, scaling and casting to float32)
• Added data type as input in the TFRecord datashufflers

bob/learn/tensorflow/test/test_cnn_trainable_variables_select.py

@@ -171,6 +171,16 @@ def test_trainable_variables():
 
     trainer.train()
     
+    conv1_after_train = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='conv1')[0].eval(session=trainer.session)[0]
+    
+    print(conv1_trained - conv1_before_load)
+    print(conv1_trained - conv1_restored)
+    print(conv1_trained - conv1_after_train)    
+    
+    import ipdb; ipdb.set_trace();
+    
+    x = 0
+    
     
 
     #var_list = tf.get_collection(tf.GraphKeys.VARIABLES, scope='fc1') + tf.get_collection(tf.GraphKeys.VARIABLES, scope='logits')