Cross validation

This MR adds the following

• Adds cross-validation using a validation set; the best model based on the lowest validation loss is saved automatically now
• Adds trainer, extractor, training script and unit tests for FASNet architecture
• Small change in MCCNN architecture; added a flag for selecting whether to use sigmoid in eval phase.

bob/learn/pytorch/config/mccnn/wmca_mccnn_cv.py

@@ -7,7 +7,7 @@ from bob.learn.pytorch.datasets import DataFolder
 
 from bob.pad.face.database import BatlPadDatabase
 
-from bob.learn.pytorch.datasets import ChannelSelect
+from bob.learn.pytorch.datasets import ChannelSelect, RandomHorizontalFlipImage
 
 
 #==============================================================================
@@ -36,17 +36,38 @@ from bob.learn.pytorch.datasets import ChannelSelect
 
 data_folder_train='/idiap/temp/ageorge/WMCA/preprocessed/'
 
+output_base_path='/idiap/temp/ageorge/Pytorch_WMCA/MCCNNv1_new_2/' 
+
+unseen_protocols=['','-LOO_fakehead','-LOO_flexiblemask','-LOO_glasses','-LOO_papermask','-LOO_prints','-LOO_replay','-LOO_rigidmask']
+
+PROTOCOL_INDEX=0 
+####################################################################
+
 frames=50
 
 extension='.h5'
 
 train_groups=['train'] # only 'train' group is used for training the network
 
-protocols="grandtest-color*depth*infrared*thermal-{}".format(frames) # makeup is excluded anyway here
+val_groups=['dev']
+
+do_crossvalidation=True
+#=======================
+
+if do_crossvalidation:
+	phases=['train','val']
+else:
+	phases=['train']
+
+groups={"train":['train'],"val":['dev']}
+
+
+
+protocols="grandtest-color-50"+unseen_protocols[PROTOCOL_INDEX] # makeup is excluded anyway here
 
 exlude_attacks_list=["makeup"]
 
-bob_hldi_instance_train = BatlPadDatabase(
+bob_hldi_instance = BatlPadDatabase(
     protocol=protocols,
     original_directory=data_folder_train,
     original_extension=extension,
@@ -58,50 +79,71 @@ bob_hldi_instance_train = BatlPadDatabase(
 #==============================================================================
 # Initialize the torch dataset, subselect channels from the pretrained files if needed.
 
-SELECTED_CHANNELS = [0,1,2,3] # selects  color, depth, infrared and thermal
+SELECTED_CHANNELS = [0,1,2,3] 
+####################################################################
 
-img_transform_train = transforms.Compose([ChannelSelect(selected_channels = SELECTED_CHANNELS),transforms.ToPILImage(),transforms.RandomHorizontalFlip(),transforms.ToTensor()])# Add p=0.5 later
 
-dataset = DataFolder(data_folder=data_folder_train,
-					 transform=img_transform_train,
-					 extension='.hdf5',
-					 bob_hldi_instance=bob_hldi_instance_train,
-					 groups=train_groups,
-					 protocol=protocols,
-					 purposes=['real', 'attack'],
-					 allow_missing_files=True)
+img_transform={}
 
-#==============================================================================
-# Load the architecture
+img_transform['train'] = transforms.Compose([ChannelSelect(selected_channels = SELECTED_CHANNELS),RandomHorizontalFlipImage(p=0.5),transforms.ToTensor()])
 
-NUM_CHANNELS = 4
+img_transform['val'] = transforms.Compose([ChannelSelect(selected_channels = SELECTED_CHANNELS),transforms.ToTensor()])
+
+dataset={}
+
+for phase in phases:
+
+	dataset[phase] = DataFolder(data_folder=data_folder_train,
+						 transform=img_transform[phase],
+						 extension='.hdf5',
+						 bob_hldi_instance=bob_hldi_instance,
+						 groups=groups[phase],
+						 protocol=protocols,
+						 purposes=['real', 'attack'],
+						 allow_missing_files=True)
 
-assert(len(SELECTED_CHANNELS)==NUM_CHANNELS)
 
-network=MCCNN(num_channels = NUM_CHANNELS)
 
 #==============================================================================
 # Specify other training parameters
 
-batch_size = 64
-num_workers = 4
+NUM_CHANNELS = len(SELECTED_CHANNELS)
+
+ADAPTED_LAYERS = 'conv1-block1-group1-ffc'
+####################################################################
+ADAPT_REF_CHANNEL = False
+####################################################################
+
+
+
+batch_size = 32
+num_workers = 0
 epochs=25
 learning_rate=0.0001
 seed = 3
-output_dir = 'training_mccn'
 use_gpu = False
-adapted_layers = 'conv1-group1-block1-ffc'
-adapt_reference_channel = False
+adapted_layers = ADAPTED_LAYERS
+adapt_reference_channel = ADAPT_REF_CHANNEL
 verbose = 2
+UID = "_".join([str(i) for i in SELECTED_CHANNELS])+"_"+str(ADAPT_REF_CHANNEL)+"_"+ADAPTED_LAYERS+"_"+str(NUM_CHANNELS)+"_"+protocols
+training_logs= output_base_path+UID+'/train_log_dir/'
+output_dir = output_base_path+UID
 
 
+#==============================================================================
+# Load the architecture
+
+
+assert(len(SELECTED_CHANNELS)==NUM_CHANNELS)
+
+network=MCCNN(num_channels = NUM_CHANNELS)
 #==============================================================================
 """
 Note: Running in GPU
 
 jman submit --queue gpu \
---name mccnn \
---log-dir /idiap/user/ageorge/WORK/COMMON_ENV_PAD_BATL_DB/training_mccn/logs/ \
+--name mccnnv2 \
+--log-dir /idiap/temp/ageorge/Pytorch_WMCA/MCCNNv2/logs/ \
 --environment="PYTHONUNBUFFERED=1" -- \
 ./bin/train_mccnn.py \
 /idiap/user/ageorge/WORK/COMMON_ENV_PAD_BATL_DB/src/bob.learn.pytorch/bob/learn/pytorch/config/mccnn/wmca_mccnn.py --use-gpu -vvv