Merge cc89611 into 650e66a

configs/default/components/tasks/image_to_class/simple_molecules.yml

@@ -0,0 +1,60 @@
+# This file defines the default values for the MNIST task.
+
+####################################################################
+# 1. CONFIGURATION PARAMETERS that will be LOADED by the component.
+####################################################################
+
+# Folder where task will store data (LOADED)
+data_folder: '~/data/simple-molecules'
+
+# Defines the split that will be used used (LOADED)
+# Options: training | validation | test
+split: training
+
+# Optional parameter (LOADED)
+# When present, resizes the MNIST images from [28,28] to [width, height]
+#resize_image: [height, width]
+
+streams:
+  ####################################################################
+  # 2. Keymappings associated with INPUT and OUTPUT streams.
+  ####################################################################
+
+  # Stream containing batch of indices (OUTPUT)
+  # Every task MUST return that stream.
+  indices: indices
+
+  # Stream containing batch of images (OUTPUT)
+  images: images
+
+  # Stream containing targets (label ids) (OUTPUT)
+  targets: targets
+
+  # Stream containing labels (words) (OUTPUT)
+  labels: labels
+
+globals:
+  ####################################################################
+  # 3. Keymappings of variables that will be RETRIEVED from GLOBALS.
+  ####################################################################
+
+  ####################################################################
+  # 4. Keymappings associated with GLOBAL variables that will be SET.
+  ####################################################################
+
+  # Width of the image (SET)
+  input_width: image_width
+  # Height of the image (SET)
+  input_height: image_height
+  # Depth of the image (SET)
+  input_depth: image_depth
+
+  # Number of output classes: 10 (SET)
+  num_classes: num_classes
+  # Label (word-idx) mappings (SET)
+  label_word_mappings: label_word_mappings
+
+  ####################################################################
+  # 5. Keymappings associated with statistics that will be ADDED.
+  ####################################################################
+

configs/molecule_classification/mnist_classification_convnet_softmax.yml

@@ -0,0 +1,120 @@
+# Training parameters:
+training:
+  task: 
+    type: SimpleMolecules
+    batch_size: &b 64
+    split: training
+    # TODO: change!
+    resize_image: [87, 87]
+  # TODO: change!
+  # Use sampler that operates on a subset.
+  sampler:
+    type: SubsetRandomSampler
+    indices: [0, 50000]
+  # optimizer parameters:
+  optimizer:
+    type: Adam
+    lr: 0.0001
+  # settings parameters
+  terminal_conditions:
+    loss_stop_threshold: 0.15
+    early_stop_validations: -1
+    episode_limit: 10000
+    epoch_limit: 10
+
+# Validation parameters:
+validation:
+  task:
+    type: SimpleMolecules
+    batch_size: *b
+    # TODO: change!
+    split: training
+    # TODO: change!
+    resize_image: [87, 87]
+  # TODO: change!
+  # Use sampler that operates on a subset.
+  sampler:
+    type: SubsetRandomSampler
+    indices: [50000, 50400]
+
+# Testing parameters:
+test:
+  task:
+    type: SimpleMolecules
+    batch_size: *b
+    # TODO: change!
+    split: training
+    # TODO: change!
+    resize_image: [87, 87]
+
+pipeline:
+  # Model 1: 3 CNN layers.
+  image_encoder:
+    type: ConvNetEncoder
+    priority: 1
+    # Using default stream names, so the following could be removed (leaving it just for the clarity though).
+    streams:
+      inputs: images
+      feature_maps: feature_maps
+
+  # Reshape inputs
+  reshaper:
+    type: ReshapeTensor
+    # TODO: change!
+    #input_dims: [-1, 16, 107, 107]
+    #output_dims: [-1, 183184]
+    input_dims: [-1, 16, 9, 9]
+    output_dims: [-1, 1296]
+    priority: 2
+    streams:
+      inputs: feature_maps
+      outputs: reshaped_maps
+    globals:
+      output_size: reshaped_maps_size
+
+  # Model 2: 1 Fully connected layer with softmax acitvation.
+  classifier:
+    type: FeedForwardNetwork 
+    priority: 3
+    streams:
+      inputs: reshaped_maps
+      # Using default stream name, so the following could be removed (leaving it just for the clarity though).
+      predictions: predictions
+    globals:
+      input_size: reshaped_maps_size
+      prediction_size: num_classes
+
+  # Loss
+  nllloss:
+    type: NLLLoss
+    priority: 4
+    # Using default stream names, so the following could be removed (leaving it just for the clarity though).
+    streams:
+      targets: targets
+      predictions: predictions
+
+  accuracy:
+    priority: 5
+    type: AccuracyStatistics
+    # Using default stream names, so the following could be removed (leaving it just for the clarity though).
+    streams:
+      targets: targets
+      predictions: predictions
+
+  answer_decoder:
+    priority: 6
+    type: WordDecoder
+    import_word_mappings_from_globals: True
+    globals:
+      word_mappings: label_word_mappings
+    streams:
+      inputs: predictions
+      outputs: predicted_answers
+
+  stream_viewer:
+    priority: 7
+    type: StreamViewer
+    input_streams: labels, targets, predictions, predicted_answers
+
+
+#: pipeline

ptp/components/tasks/image_to_class/__init__.py

@@ -1,8 +1,10 @@
 #from .cifar10 import CIFAR10
 from .cifar_100 import CIFAR100
 from .mnist import MNIST
+from .simple_molecules import SimpleMolecules
 
 __all__ = [
     'CIFAR100',
-    'MNIST'
+    'MNIST',
+    'SimpleMolecules',
     ]