fix hp optimizer

pinky/src/model.py

 
 from .data import *
 from .tf_util import *
+from .util import delete_if_exists
 from .optimize import Optimizer
 
 import tensorflow as tf
@@ -13,18 +14,6 @@ import shutil
 logger = logging.getLogger('pinky.model')
 
 
-def delete_if_exists(dirname):
-    if os.path.exists(dirname):
-        logger.info('deleting directory: %s' % dirname)
-        shutil.rmtree(dirname)
-
-
-def unlist_dict(d):
-    '''horrible hack to make the strange scikit-optimize list-of-list shit work
-    '''
-    for k, v in d.items():
-        if isinstance(v, list) and len(v) == 1:
-            d[k] = v[0]
 
 class Model(Object):
 
@@ -32,6 +21,7 @@ class Model(Object):
     data_generator = DataGeneratorBase.T()
     dropout_rate = Float.T(optional=True)
     batch_size = Int.T(default=10)
+    n_epochs = Int.T(default=1)
     outdir = String.T(default='/tmp/dnn-seis')
     auto_clear = Bool.T(default=True)
     summary_outdir= String.T(default='summary')
@@ -39,8 +29,7 @@ class Model(Object):
     shuffle_size = Int.T(
         optional=True, help='if set, shuffle examples at given buffer size.')
 
-    def __init__(self, tf_config=None, debug=False, **kwargs):
-        print(kwargs)
+    def __init__(self, tf_config=None, **kwargs):
         super().__init__(**kwargs)
 
         if self.auto_clear:
@@ -48,7 +37,7 @@ class Model(Object):
             delete_if_exists(self.outdir)
 
         self.tf_config = tf_config
-        self.debug = debug
+        self.debug = logger.getEffectiveLevel() == logging.DEBUG
         self.sess = tf.Session(config=tf_config)
 
         # initializer = tf.truncated_normal_initializer(
@@ -57,11 +46,14 @@ class Model(Object):
             mean=0.0, stddev=0.1)
 
     def generate_input(self):
+        '''
+        Generates data and labels
+        '''
         dataset = self.data_generator.get_dataset()
         dataset = dataset.batch(self.batch_size)
         if self.shuffle_size:
             dataset = dataset.shuffle(buffer_size=self.shuffle_size)
-        # dataset = dataset.repeat()
+        dataset = dataset.repeat(count=self.n_epochs)
         dataset = dataset.prefetch(buffer_size=self.batch_size)
 
         return dataset.make_one_shot_iterator().get_next()
@@ -71,8 +63,9 @@ class Model(Object):
         '''
         CNN along horizontal axis
 
+        :param n_filters: number of filters
         :param cross_channel_kernel: convolution kernel size accross channels
-        :param n_filters: 
+        :param kernel_width: convolution kernel size accross time axis
 
         (Needs some debugging and checking)
         '''
@@ -82,34 +75,33 @@ class Model(Object):
             cross_channel_kernel = n_channels
 
         with tf.variable_scope('conv_layer%s' %name):
-
             input = tf.layers.conv2d(
                 inputs=input,
                 filters=n_filters,
                 kernel_size=(cross_channel_kernel, kernel_width),    # use identity (1) along channels
                 activation=tf.nn.relu,
                 bias_initializer=self.initializer,
-                name=name)
+                name=name+'conv2d')
 
             input = tf.layers.batch_normalization(input, training=training)
             input = tf.layers.max_pooling2d(
                 input,
-                pool_size=(2, 2),       # (height, width)
-                strides=(1, 1),
+                pool_size=(cross_channel_kernel, kernel_width),       # (height, width)
+                strides=(1, 2),
+                name=name+'max_pooling2d',
             )
 
             if self.debug:
                 # super expensive!!
+                logging.warn('Debug mode enables super expensive summaries.')
                 tf.summary.image(
                     'post-%s' % name, tf.split(
                         input, num_or_size_splits=n_filters, axis=-1)[0])
                 variable_summaries(input, name)
-
         return input
 
     def model(self, features, labels, mode, params):
 
-        unlist_dict(params)
         training = bool(mode == tf.estimator.ModeKeys.TRAIN)
 
         n_filters = 32
@@ -118,9 +110,10 @@ class Model(Object):
 
         # tf.summary.image('input', features)
         # conv = self.time_axis_cnn(features, n_filters, None, kernel_width=3, name='conv1',
+        #         training=training)
         conv = self.time_axis_cnn(features, n_filters, 1, kernel_width=1, name='conv1',
                 training=training)
-        conv = self.time_axis_cnn(conv, n_filters*2, 1, kernel_width=1, name='conv2',
+        conv = self.time_axis_cnn(conv, n_filters*2, 1, kernel_width=2, name='conv2',
                 training=training)
         conv = self.time_axis_cnn(conv, n_filters*4, 2, kernel_width=1, name='conv3',
                 training=training)
@@ -177,7 +170,6 @@ class Model(Object):
         )
 
     def train(self, params=None):
-        print(params)
         params = params or {}
 
         with self.sess as default:

pinky/src/optimize.py

+from .util import delete_if_exists
 from skopt import gp_minimize
 from skopt.space import Real, Categorical, Integer
 from pyrocko.guts import Object, Int, Float, List, Tuple, String
 
 
-
 def to_skopt_real(x, name, prior):
     return Real(low=x[0], high=x[1], prior=prior, name=name)
 
@@ -11,7 +11,8 @@ def to_skopt_real(x, name, prior):
 class Optimizer(Object):
 
     learning_rate = Tuple.T(3, Float.T(), default=(1e-3, 1e-5, 1e-4))  # low, high, default
-    n_calls = Int.T(default=50)
+    n_calls = Int.T(default=50, help='number of test sets')
+    log_path = String.T(default='./logs/')
     path_best = String.T(default='winner')
 
     def __init__(self, **kwargs):
@@ -26,15 +27,19 @@ class Optimizer(Object):
 
         print(self.dimensions)
 
-    def evaluate(self, *args):
+    def evaluate(self, args):
         ''' wrapper to parse gp_minimize args to model.train'''
-        print(args)
         args = dict(zip(['learning_rate',], args))
+        self.model.outdir = self.log_dir_name(args)
         print(args)
         return self.model.train(args)['loss']
 
     def optimize(self, model):
+
         self.model = model
+        if self.model.auto_clear:
+            delete_if_exists(self.log_path)
+
         default_parameters = [self.learning_rate[-1]]
 
         gp_minimize(
@@ -45,13 +50,17 @@ class Optimizer(Object):
                 x0=default_parameters,
                 )
 
-    def log_dir_name(self, learning_rate):
+    def log_dir_name(self, params):
 
 	# The dir-name for the TensorBoard log-dir.
-        s = "./logs/lr_{0:.0e}_layers"
-
-	# Insert all the hyper-parameters in the dir-name.
-        log_dir = s.format(learning_rate)
+        placeholders = '{}_{}_' * len(params)
+        identifiers = []
+        for k, v in params.items():
+            identifiers.append(k[0:3])
+            identifiers.append(v)
+
+        placeholders = placeholders.format(*identifiers)
+        log_dir = self.log_path + placeholders
 
         return log_dir
 

pinky/src/util.py

+import os
+import shutil
+import logging
+
+logger = logging.getLogger()
+
+
+def delete_if_exists(dirname):
+    if os.path.exists(dirname):
+        logger.info('deleting directory: %s' % dirname)
+        shutil.rmtree(dirname)
+
+
 def nsl(tr):
     return tr.nslc_id[:3]