Box and stuff

.gitignore

@@ -3,9 +3,6 @@
 
 
 ### Local Datasets ###
-code/raw_runs
-code/processed_runs
-experiments/
 
 
 ### Data ###

code/bar_plot.py

@@ -60,52 +60,6 @@ def plot_histogram(bars_dict_list: List[dict], filename='histogram_plot'):
     pass
 
 
-def line_plot(line_dict_list, filename='lineplot'):
-    # lines with standard deviation
-    # Transform data accordingly and plot it
-    data = []
-    rdylgn = cl.scales['10']['div']['RdYlGn']
-    rdylgn_background = [scale + (0.4,) for scale in cl.to_numeric(rdylgn)]
-    for line_id, line_dict in enumerate(line_dict_list):
-        name = line_dict.get('name', 'gimme a name')
-
-        upper_bound = go.Scatter(
-            name='Upper Bound',
-            x=line_dict['x'],
-            y=line_dict['upper_y'],
-            mode='lines',
-            marker=dict(color="#444"),
-            line=dict(width=0),
-            fillcolor=rdylgn_background[line_id],
-        )
-
-        trace = go.Scatter(
-            x=line_dict['x'],
-            y=line_dict['main_y'],
-            mode='lines',
-            name=name,
-            line=dict(color=line_id),
-            fillcolor=rdylgn_background[line_id],
-            fill='tonexty')
-
-        lower_bound = go.Scatter(
-            name='Lower Bound',
-            x=line_dict['x'],
-            y=line_dict['lower_y'],
-            marker=dict(color="#444"),
-            line=dict(width=0),
-            mode='lines')
-
-        data.extend([upper_bound, trace, lower_bound])
-
-    layout=dict(title='{} Line Plot'.format('Experiment Name Penis'),
-                height=800, width=800, margin=dict(l=0, r=0, t=0, b=0))
-
-    fig = go.Figure(data=data, layout=layout)
-    pl.offline.plot(fig, auto_open=True, filename=filename)
-    pass
-
-
 def search_and_apply(absolut_file_or_folder, plotting_function, files_to_look_for=[]):
     if os.path.isdir(absolut_file_or_folder):
         for sub_file_or_folder in os.scandir(absolut_file_or_folder):

code/box_plots.py

@@ -0,0 +1,114 @@
+import os
+
+from experiment import Experiment
+# noinspection PyUnresolvedReferences
+from soup import Soup
+from typing import List
+
+from collections import defaultdict
+
+from argparse import ArgumentParser
+import numpy as np
+
+import plotly as pl
+import plotly.graph_objs as go
+
+import colorlover as cl
+
+import dill
+
+
+def build_args():
+    arg_parser = ArgumentParser()
+    arg_parser.add_argument('-i', '--in_file', nargs=1, type=str)
+    arg_parser.add_argument('-o', '--out_file', nargs='?', default='out', type=str)
+    return arg_parser.parse_args()
+
+
+def plot_box(exp: Experiment, filename='histogram_plot'):
+    # catagorical
+    ryb = cl.scales['10']['div']['RdYlBu']
+
+    data = []
+
+    for d in range(exp.depth):
+        names = ['D 10e-{}'.format(d)] * exp.trials
+        data.extend(names)
+
+    trace_list = []
+
+    vergence_box = go.Box(
+        y=exp.ys,
+        x=data,
+        name='Time to Vergence',
+        boxpoints=False,
+        showlegend=True,
+        marker=dict(
+            color=ryb[3]
+        ),
+    )
+    fixpoint_box = go.Box(
+        y=exp.zs,
+        x=data,
+        name='Time as Fixpoint',
+        boxpoints=False,
+        showlegend=True,
+        marker=dict(
+            color=ryb[-1]
+        ),
+    )
+
+    trace_list.extend([vergence_box, fixpoint_box])
+
+    layout = dict(title='{} Histogram Plot'.format('Experiment Name Penis'),
+                  boxmode='group',
+                  boxgap=0,
+                  # barmode='group',
+                  bargap=0,
+                  xaxis=dict(showgrid=False,
+                             zeroline=True,
+                             tickangle=0,
+                             showticklabels=True),
+                  yaxis=dict(
+                      title='Occurences',
+                      zeroline=False)
+                  # height=400, width=400,
+                  # margin=dict(l=20, r=20, t=20, b=20)
+                  )
+
+    fig = go.Figure(data=trace_list, layout=layout)
+    pl.offline.plot(fig, auto_open=True, filename=filename)
+    pass
+
+
+def search_and_apply(absolut_file_or_folder, plotting_function, files_to_look_for=[]):
+    if os.path.isdir(absolut_file_or_folder):
+        for sub_file_or_folder in os.scandir(absolut_file_or_folder):
+            search_and_apply(sub_file_or_folder.path, plotting_function, files_to_look_for=files_to_look_for)
+    elif absolut_file_or_folder.endswith('.dill'):
+        file_or_folder = os.path.split(absolut_file_or_folder)[-1]
+        if file_or_folder in files_to_look_for and not os.path.exists('{}.html'.format(file_or_folder[:-5])):
+            print('Apply Plotting function "{func}" on file "{file}"'.format(func=plotting_function.__name__,
+                                                                             file=absolut_file_or_folder)
+                  )
+
+            with open(absolut_file_or_folder, 'rb') as in_f:
+                exp = dill.load(in_f)
+
+            plotting_function(exp, filename='{}.html'.format(absolut_file_or_folder[:-5]))
+
+        else:
+            pass
+            # This was not a file i should look for.
+    else:
+        # This was either another FilyType or Plot.html alerady exists.
+        pass
+
+
+if __name__ == '__main__':
+    args = build_args()
+    in_file = args.in_file[0]
+    out_file = args.out_file
+
+    search_and_apply(in_file, plot_box, files_to_look_for=['experiment.dill'])
+    # , 'all_names.dill', 'all_notable_nets.dill'])

code/experiments/exp-FixpointExperiment-_6511565650566781-0/log.txt

@@ -0,0 +1 @@
+{'divergent': 38, 'fix_zero': 62, 'fix_other': 0, 'fix_sec': 0, 'other': 0}

code/experiments/exp-FixpointExperiment-_6511565800569721-0/log.txt

@@ -0,0 +1 @@
+{'divergent': 0, 'fix_zero': 100, 'fix_other': 0, 'fix_sec': 0, 'other': 0}

code/experiments/exp-FixpointExperiment-_813945717034465-0/log.txt

@@ -0,0 +1 @@
+{'divergent': 3, 'fix_zero': 97, 'fix_other': 0, 'fix_sec': 0, 'other': 0}

code/network.py

@@ -180,7 +180,7 @@ class ParticleDecorator:
 
     def make_state(self, **kwargs):
         weights = self.net.get_weights_flat()
-        if any(np.isinf(weights)):
+        if any(np.isinf(weights)) or any(np.isnan(weights)):
             return None
         state = {'class': self.net.__class__.__name__, 'weights': weights}
         state.update(kwargs)
@@ -609,8 +609,8 @@ class TrainingNeuralNetworkDecorator():
     def train(self, batchsize=1, store_states=True, epoch=0):
         self.compiled()
         x, y = self.net.compute_samples()
-        savestatecallback = SaveStateCallback(net=self, epoch=epoch) if store_states else None
-        history = self.net.model.fit(x=x, y=y, verbose=0, batch_size=batchsize, callbacks=[savestatecallback] if store_states else None, initial_epoch=epoch)
+        savestatecallback = [SaveStateCallback(net=self, epoch=epoch)] if store_states else None
+        history = self.net.model.fit(x=x, y=y, epochs=epoch+1, verbose=0, batch_size=batchsize, callbacks=savestatecallback, initial_epoch=epoch)
         return history.history['loss'][-1]
 
     def learn_from(self, other_network, batchsize=1):
@@ -628,36 +628,37 @@ if __name__ == '__main__':
         exp.run_net(net, 100, run_id=run_id + 1)
         exp.historical_particles[run_id] = net
         if prints:
-            # print(net.apply_to_network(net))
             print("Fixpoint? " + str(net.is_fixpoint()))
             print("Loss " + str(loss))
-        K.clear_session()
 
-    if False:
+    if True:
         # WeightWise Neural Network
         with FixpointExperiment() as exp:
             for run_id in tqdm(range(100)):
                 net = ParticleDecorator(WeightwiseNeuralNetwork(width=2, depth=2) \
                                         .with_keras_params(activation='linear'))
                 run_exp(net)
+                K.clear_session()
             exp.log(exp.counters)
 
-    if False:
+    if True:
         # Aggregating Neural Network
         with FixpointExperiment() as exp:
             for run_id in tqdm(range(100)):
                 net = ParticleDecorator(AggregatingNeuralNetwork(aggregates=4, width=2, depth=2) \
                                         .with_keras_params())
                 run_exp(net)
+                K.clear_session()
             exp.log(exp.counters)
 
-    if False:
+    if True:
         #FFT Neural Network
         with FixpointExperiment() as exp:
             for run_id in tqdm(range(100)):
                 net = ParticleDecorator(FFTNeuralNetwork(aggregates=4, width=2, depth=2) \
                                         .with_keras_params(activation='linear'))
                 run_exp(net)
+                K.clear_session()
             exp.log(exp.counters)
 
     if True:
@@ -665,13 +666,14 @@ if __name__ == '__main__':
         with FixpointExperiment() as exp:
             for i in range(1):
                 run_count = 1000
-                net = ParticleDecorator(TrainingNeuralNetworkDecorator(WeightwiseNeuralNetwork(width=2, depth=2)))
+                net = TrainingNeuralNetworkDecorator(ParticleDecorator(WeightwiseNeuralNetwork(width=2, depth=2)))
                 net.with_params(epsilon=0.0001).with_keras_params(optimizer='sgd')
                 for run_id in tqdm(range(run_count+1)):
                     net.compiled()
                     loss = net.train(epoch=run_id)
                     if run_id % 100 == 0:
                         run_exp(net)
+                K.clear_session()
 
     if False:
         with FixpointExperiment() as exp:
@@ -689,6 +691,7 @@ if __name__ == '__main__':
                     print("Fixpoint after Agg? " + str(fp))
                     print("Loss " + str(loss))
                     print()
+
     if False:
         # this explodes in our faces completely... NAN everywhere
         # TODO: Wtf is happening here?

code/setups/experiments/exp-fixpoint-density-_6511547300443771-0/log.txt

@@ -0,0 +1,36 @@
+ParticleDecorator activiation='linear' use_bias='False'
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 100}
+
+
+ParticleDecorator activiation='linear' use_bias='False'
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 100}
+
+
+ParticleDecorator activiation='linear' use_bias='False'
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 100}
+
+
+ParticleDecorator activiation='sigmoid' use_bias='False'
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 100}
+
+
+ParticleDecorator activiation='sigmoid' use_bias='False'
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 100}
+
+
+ParticleDecorator activiation='sigmoid' use_bias='False'
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 100}
+
+
+ParticleDecorator activiation='relu' use_bias='False'
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 100}
+
+
+ParticleDecorator activiation='relu' use_bias='False'
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 100}
+
+
+ParticleDecorator activiation='relu' use_bias='False'
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 100}
+
+

code/setups/experiments/exp-known-fixpoint-variation-_813943796847257-0/log.txt

@@ -0,0 +1,30 @@
+variation 10e-0
+avg time to vergence 3.72
+avg time as fixpoint 0
+variation 10e-1
+avg time to vergence 5.13
+avg time as fixpoint 0
+variation 10e-2
+avg time to vergence 6.53
+avg time as fixpoint 0
+variation 10e-3
+avg time to vergence 8.09
+avg time as fixpoint 0
+variation 10e-4
+avg time to vergence 9.81
+avg time as fixpoint 0.06
+variation 10e-5
+avg time to vergence 11.43
+avg time as fixpoint 1.51
+variation 10e-6
+avg time to vergence 13.15
+avg time as fixpoint 3.34
+variation 10e-7
+avg time to vergence 14.57
+avg time as fixpoint 4.79
+variation 10e-8
+avg time to vergence 22.41
+avg time as fixpoint 12.37
+variation 10e-9
+avg time to vergence 26.17
+avg time as fixpoint 16.11

code/setups/experiments/exp-training_fixpoint-_813946210831437-0/log.txt

@@ -0,0 +1,8 @@
+ParticleDecorator activiation='linear' use_bias=False
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 19, 'fix_sec': 0, 'other': 1}
+
+
+ParticleDecorator activiation='linear' use_bias=False
+{'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 20}
+
+

code/setups/fixpoint-density.py

@@ -28,34 +28,38 @@ def count(counters, net, notable_nets=[]):
         counters['other'] += 1
     return counters, notable_nets
 
-with Experiment('fixpoint-density') as exp:
-    exp.trials = 100
-    exp.epsilon = 1e-4
-    net_generators = []
-    for activation in ['linear', 'sigmoid', 'relu']:
-        net_generators += [lambda activation=activation: WeightwiseNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=False)]
-        net_generators += [lambda activation=activation: AggregatingNeuralNetwork(aggregates=4, width=2, depth=2).with_keras_params(activation=activation, use_bias=False)]
-        net_generators += [lambda activation=activation: RecurrentNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=False)]
-    all_counters = []
-    all_notable_nets = []
-    all_names = []
-    for net_generator_id, net_generator in enumerate(net_generators):
-        counters = generate_counters()
-        notable_nets = []
-        for _ in tqdm(range(exp.trials)):
-            net = net_generator().with_params(epsilon=exp.epsilon)
-            name = str(net.__class__.__name__) + " activiation='" + str(net.get_keras_params().get('activation')) + "' use_bias='" + str(net.get_keras_params().get('use_bias')) + "'"
-            count(counters, net, notable_nets)
-            keras.backend.clear_session()
-        all_counters += [counters]
-        all_notable_nets += [notable_nets]
-        all_names += [name]
-    exp.save(all_counters=all_counters)
-    exp.save(all_notable_nets=all_notable_nets)
-    exp.save(all_names=all_names)
-    for exp_id, counter in enumerate(all_counters):
-        exp.log(all_names[exp_id])
-        exp.log(all_counters[exp_id])
-        exp.log('\n')
 
-print('Done')
+if __name__ == '__main__':
+    with Experiment('fixpoint-density') as exp:
+        exp.trials = 100
+        exp.epsilon = 1e-4
+        net_generators = []
+        for activation in ['linear', 'sigmoid', 'relu']:
+            net_generators += [lambda activation=activation: WeightwiseNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=False)]
+            net_generators += [lambda activation=activation: AggregatingNeuralNetwork(aggregates=4, width=2, depth=2).with_keras_params(activation=activation, use_bias=False)]
+            net_generators += [lambda activation=activation: FFTNeuralNetwork(aggregates=4, width=2, depth=2).with_keras_params(activation=activation, use_bias=False)]
+            # net_generators += [lambda activation=activation: RecurrentNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=False)]
+        all_counters = []
+        all_notable_nets = []
+        all_names = []
+        for net_generator_id, net_generator in enumerate(net_generators):
+            counters = generate_counters()
+            notable_nets = []
+            for _ in tqdm(range(exp.trials)):
+                net = net_generator().with_params(epsilon=exp.epsilon)
+                net = ParticleDecorator(net)
+                name = str(net.__class__.__name__) + " activiation='" + str(net.get_keras_params().get('activation')) + "' use_bias='" + str(net.get_keras_params().get('use_bias')) + "'"
+                count(counters, net, notable_nets)
+                keras.backend.clear_session()
+            all_counters += [counters]
+            all_notable_nets += [notable_nets]
+            all_names += [name]
+        exp.save(all_counters=all_counters)
+        exp.save(all_notable_nets=all_notable_nets)
+        exp.save(all_names=all_names)
+        for exp_id, counter in enumerate(all_counters):
+            exp.log(all_names[exp_id])
+            exp.log(all_counters[exp_id])
+            exp.log('\n')
+
+    print('Done')

code/setups/known-fixpoint-variation.py

@@ -5,7 +5,6 @@ import os
 # Concat top Level dir to system environmental variables
 sys.path += os.path.join('..', '.')
 
-
 from util import *
 from experiment import *
 from network import *
@@ -16,19 +15,22 @@ import keras.backend
 
 from statistics import mean
 avg = mean
-    
+
+
 def generate_fixpoint_weights():
     return [
         np.array([[1.0, 0.0], [0.0, 0.0], [0.0, 0.0], [0.0, 0.0]], dtype=np.float32),
         np.array([[1.0, 0.0], [0.0, 0.0]], dtype=np.float32),
         np.array([[1.0], [0.0]], dtype=np.float32)
     ]
-    
+
+
 def generate_fixpoint_net():
     net = WeightwiseNeuralNetwork(width=2, depth=2).with_keras_params(activation='sigmoid')
     net.set_weights(generate_fixpoint_weights())
     return net
 
+
 def vary(old_weights, e=1.0):
     new_weights = copy.deepcopy(old_weights)
     for layer_id, layer in enumerate(new_weights):
@@ -40,45 +42,49 @@ def vary(old_weights, e=1.0):
                     new_weights[layer_id][cell_id][weight_id] = weight - prng() * e
     return new_weights
 
-with Experiment('known-fixpoint-variation') as exp:
-    exp.depth = 10
-    exp.trials = 100
-    exp.max_steps = 100
-    exp.epsilon = 1e-4
-    exp.xs = []
-    exp.ys = []
-    exp.zs = []
-    exp.notable_nets = []
-    current_scale = 1.0
-    for _ in range(exp.depth):
-        print('variation scale ' + str(current_scale))
-        for _ in tqdm(range(exp.trials)):
-            net = generate_fixpoint_net().with_params(epsilon=exp.epsilon)
-            net.set_weights(vary(net.get_weights(), current_scale))
-            time_to_something = 0
-            time_as_fixpoint = 0
-            still_fixpoint = True
-            for _ in range(exp.max_steps):
-                net.self_attack()
-                if net.is_zero() or net.is_diverged():
-                    break
-                if net.is_fixpoint():
-                    if still_fixpoint:
-                        time_as_fixpoint += 1
+
+if __name__ == '__main__':
+    with Experiment('known-fixpoint-variation') as exp:
+        exp.depth = 10
+        exp.trials = 100
+        exp.max_steps = 100
+        exp.epsilon = 1e-4
+        exp.xs = []
+        exp.ys = []
+        exp.zs = []
+        exp.notable_nets = []
+        current_scale = 1.0
+        for _ in range(exp.depth):
+            print('variation scale ' + str(current_scale))
+            for _ in tqdm(range(exp.trials)):
+                net = generate_fixpoint_net().with_params(epsilon=exp.epsilon)
+                net = ParticleDecorator(net)
+                net.set_weights(vary(net.get_weights(), current_scale))
+                time_to_something = 0
+                time_as_fixpoint = 0
+                still_fixpoint = True
+                for _ in range(exp.max_steps):
+                    net.self_attack()
+                    if net.is_zero() or net.is_diverged():
+                        break
+                    if net.is_fixpoint():
+                        if still_fixpoint:
+                            time_as_fixpoint += 1
+                        else:
+                            print('remarkable')
+                            exp.notable_nets += [net.get_weights()]
+                            still_fixpoint = True
                     else:
-                        print('remarkable')
-                        exp.notable_nets += [net.get_weights()]
-                        still_fixpoint = True
-                else:
-                    still_fixpoint = False
-                time_to_something += 1
-            exp.xs += [current_scale]
-            exp.ys += [time_to_something] #time steps taken to reach divergence or zero (reaching another fix-point is basically never happening)
-            exp.zs += [time_as_fixpoint] #time steps still regarded as sthe initial fix-point
-            keras.backend.clear_session()
-        current_scale /= 10.0
-    for d in range(exp.depth):
-        exp.log('variation 10e-' + str(d))
-        exp.log('avg time to vergence ' + str(avg(exp.ys[d*exp.trials:(d+1)*exp.trials])))
-        exp.log('avg time as fixpoint ' + str(avg(exp.zs[d*exp.trials:(d+1)*exp.trials])))
-        
+                        still_fixpoint = False
+                    time_to_something += 1
+                exp.xs += [current_scale]
+                # time steps taken to reach divergence or zero (reaching another fix-point is basically never happening)
+                exp.ys += [time_to_something]
+                # time steps still regarded as sthe initial fix-point
+                exp.zs += [time_as_fixpoint]
+                keras.backend.clear_session()
+            current_scale /= 10.0
+        for d in range(exp.depth):
+            exp.log('variation 10e-' + str(d))
+            exp.log('avg time to vergence ' + str(avg(exp.ys[d*exp.trials:(d+1) * exp.trials])))
+            exp.log('avg time as fixpoint ' + str(avg(exp.zs[d*exp.trials:(d+1) * exp.trials])))

code/setups/mixed-self-fixpoints.py

@@ -3,6 +3,9 @@ import os
 
 from typing import Tuple
 
+# Concat top Level dir to system environmental variables
+sys.path += os.path.join('..', '.')
+
 from util import *
 from experiment import *
 from network import *
@@ -10,10 +13,6 @@ from network import *
 import keras.backend
 
 
-# Concat top Level dir to system environmental variables
-sys.path += os.path.join('..', '.')
-
-
 def generate_counters():
     """
     Initial build of the counter dict, to store counts.
@@ -51,46 +50,52 @@ def count(counters, net, notable_nets=[]):
         counters['other'] += 1
     return counters, notable_nets
 
+if __name__ == '__main__':
 
-with Experiment('mixed-self-fixpoints') as exp:
-    exp.trials = 20
-    exp.selfattacks = 4
-    exp.trains_per_selfattack_values = [100 * i for i in range(11)]
-    exp.epsilon = 1e-4
-    net_generators = []
-    for activation in ['linear', 'sigmoid', 'relu']:
-        for use_bias in [False]:
-            net_generators += [lambda activation=activation, use_bias=use_bias: WeightwiseNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
-            # net_generators += [lambda activation=activation, use_bias=use_bias: AggregatingNeuralNetwork(aggregates=4, width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
-            # net_generators += [lambda activation=activation, use_bias=use_bias: RecurrentNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+    with Experiment('mixed-self-fixpoints') as exp:
+        exp.trials = 20
+        exp.selfattacks = 4
+        exp.trains_per_selfattack_values = [100 * i for i in range(11)]
+        exp.epsilon = 1e-4
+        net_generators = []
+        for activation in ['linear']:  # , 'sigmoid', 'relu']:
+            for use_bias in [False]:
+                net_generators += [lambda activation=activation, use_bias=use_bias: WeightwiseNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+                net_generators += [lambda activation=activation, use_bias=use_bias: AggregatingNeuralNetwork(aggregates=4, width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+                # net_generators += [lambda activation=activation, use_bias=use_bias: FFTNeuralNetwork(aggregates=4, width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+                # net_generators += [lambda activation=activation, use_bias=use_bias: RecurrentNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
 
-    all_names = []
-    all_data = []
-    for net_generator_id, net_generator in enumerate(net_generators):
-        xs = []
-        ys = []
-        for trains_per_selfattack in exp.trains_per_selfattack_values:
-            counters = generate_counters()
-            notable_nets = []
-            for _ in tqdm(range(exp.trials)):
-                net = TrainingNeuralNetworkDecorator(net_generator()).with_params(epsilon=exp.epsilon)
-                name = str(net.net.__class__.__name__) + " activiation='" + str(net.get_keras_params().get('activation')) + "' use_bias=" + str(net.get_keras_params().get('use_bias'))
-                for selfattack_id in range(exp.selfattacks):
-                    net.self_attack()
-                    for train_id in range(trains_per_selfattack):
-                        loss = net.compiled().train(epoch=selfattack_id*trains_per_selfattack+train_id)
-                    if net.is_diverged() or net.is_fixpoint():
-                        break
-                count(counters, net, notable_nets)
-                keras.backend.clear_session()
-            xs += [trains_per_selfattack]
-            ys += [float(counters['fix_zero'] + counters['fix_other']) / float(exp.trials)]
-        all_names += [name]
-        all_data += [{'xs':xs, 'ys':ys}] #xs: how many trains per self-attack from exp.trains_per_selfattack_values, ys: average amount of fixpoints found
+        all_names = []
+        all_data = []
 
-    exp.save(all_names=all_names)
-    exp.save(all_data=all_data)
-    for exp_id, name in enumerate(all_names):
-        exp.log(all_names[exp_id])
-        exp.log(all_data[exp_id])
-        exp.log('\n')
+        for net_generator_id, net_generator in enumerate(net_generators):
+            xs = []
+            ys = []
+            for trains_per_selfattack in exp.trains_per_selfattack_values:
+                counters = generate_counters()
+                notable_nets = []
+                for _ in tqdm(range(exp.trials)):
+                    net = ParticleDecorator(net_generator())
+                    net = TrainingNeuralNetworkDecorator(net).with_params(epsilon=exp.epsilon)
+                    name = str(net.net.__class__.__name__) + " activiation='" + str(net.get_keras_params().get('activation')) + "' use_bias=" + str(net.get_keras_params().get('use_bias'))
+                    for selfattack_id in range(exp.selfattacks):
+                        net.self_attack()
+                        for train_id in range(trains_per_selfattack):
+                            loss = net.compiled().train(epoch=selfattack_id*trains_per_selfattack+train_id)
+                        if net.is_diverged() or net.is_fixpoint():
+                            break
+                    count(counters, net, notable_nets)
+                    keras.backend.clear_session()
+                xs += [trains_per_selfattack]
+                ys += [float(counters['fix_zero'] + counters['fix_other']) / float(exp.trials)]
+            all_names += [name]
+            # xs: how many trains per self-attack from exp.trains_per_selfattack_values
+            # ys: average amount of fixpoints found
+            all_data += [{'xs': xs, 'ys': ys}]
+
+        exp.save(all_names=all_names)
+        exp.save(all_data=all_data)
+        for exp_id, name in enumerate(all_names):
+            exp.log(all_names[exp_id])
+            exp.log(all_data[exp_id])
+            exp.log('\n')

code/setups/training-fixpoints.py

@@ -8,7 +8,7 @@ from util import *
 from experiment import *
 from network import *
 
-import keras.backend
+import keras.backend as K
 
 def generate_counters():
     return {'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 0}
@@ -29,36 +29,40 @@ def count(counters, net, notable_nets=[]):
         counters['other'] += 1
     return counters, notable_nets
 
-with Experiment('training_fixpoint') as exp:
-    exp.trials = 5
-    exp.run_count = 500
-    exp.epsilon = 1e-4
-    net_generators = []
-    for activation in ['linear', 'sigmoid', 'relu']:
-        for use_bias in [False]:
-            net_generators += [lambda activation=activation, use_bias=use_bias: WeightwiseNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
-            net_generators += [lambda activation=activation, use_bias=use_bias: AggregatingNeuralNetwork(aggregates=4, width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
-            net_generators += [lambda activation=activation, use_bias=use_bias: RecurrentNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
-    all_counters = []
-    all_notable_nets = []
-    all_names = []
-    for net_generator_id, net_generator in enumerate(net_generators):
-        counters = generate_counters()
-        notable_nets = []
-        for _ in tqdm(range(exp.trials)):
-            net = TrainingNeuralNetworkDecorator(net_generator()).with_params(epsilon=exp.epsilon)
-            name = str(net.net.__class__.__name__) + " activiation='" + str(net.get_keras_params().get('activation')) + "' use_bias=" + str(net.get_keras_params().get('use_bias'))
-            for run_id in range(exp.run_count):
-                loss = net.compiled().train(epoch=run_id+1)
-            count(counters, net, notable_nets)
-            keras.backend.clear_session()
-        all_counters += [counters]
-        all_notable_nets += [notable_nets]
-        all_names += [name]
-    exp.save(all_counters=all_counters) #net types reached in the end
-    exp.save(all_notable_nets=all_notable_nets)
-    exp.save(all_names=all_names) #experiment setups
-    for exp_id, counter in enumerate(all_counters):
-        exp.log(all_names[exp_id])
-        exp.log(all_counters[exp_id])
-        exp.log('\n')
+
+if __name__ == '__main__':
+
+    with Experiment('training_fixpoint') as exp:
+        exp.trials = 20
+        exp.run_count = 500
+        exp.epsilon = 1e-4
+        net_generators = []
+        for activation in ['linear']:  # , 'sigmoid', 'relu']:
+            for use_bias in [False]:
+                net_generators += [lambda activation=activation, use_bias=use_bias: WeightwiseNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+                net_generators += [lambda activation=activation, use_bias=use_bias: AggregatingNeuralNetwork(aggregates=4, width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+                # net_generators += [lambda activation=activation, use_bias=use_bias: RecurrentNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+        all_counters = []
+        all_notable_nets = []
+        all_names = []
+        for net_generator_id, net_generator in enumerate(net_generators):
+            counters = generate_counters()
+            notable_nets = []
+            for _ in tqdm(range(exp.trials)):
+                net = ParticleDecorator(net_generator())
+                net = TrainingNeuralNetworkDecorator(net).with_params(epsilon=exp.epsilon)
+                name = str(net.net.__class__.__name__) + " activiation='" + str(net.get_keras_params().get('activation')) + "' use_bias=" + str(net.get_keras_params().get('use_bias'))
+                for run_id in range(exp.run_count):
+                    loss = net.compiled().train(epoch=run_id+1)
+                count(counters, net, notable_nets)
+            all_counters += [counters]
+            all_notable_nets += [notable_nets]
+            all_names += [name]
+            K.clear_session()
+        exp.save(all_counters=all_counters) #net types reached in the end
+        # exp.save(all_notable_nets=all_notable_nets)
+        exp.save(all_names=all_names) #experiment setups
+        for exp_id, counter in enumerate(all_counters):
+            exp.log(all_names[exp_id])
+            exp.log(all_counters[exp_id])
+            exp.log('\n')

code/soup.py

@@ -68,7 +68,8 @@ class Soup(object):
                     description['counterpart'] = other_particle.get_uid()
                 for _ in range(self.params.get('train', 0)):
                     particle.compiled()
-                    loss = particle.train(store_states=False) #callbacks on save_state are broken for TrainingNeuralNetwork
+                    # callbacks on save_state are broken for TrainingNeuralNetwork
+                    loss = particle.train(store_states=False)
                     description['fitted'] = self.params.get('train', 0)
                     description['loss'] = loss
                     description['action'] = 'train_self'

code/visualization.py

@@ -34,6 +34,8 @@ def build_from_soup_or_exp(soup):
             action=[event.get('action', None) for event in particle],
             counterpart=[event.get('counterpart', None) for event in particle]
         )
+        if any([x is not None for x in particle_dict['counterpart']]):
+            print('counterpart')
         particle_list.append(particle_dict)
     return particle_list