Add all results

output_files/data/cnn_custom_loss/run8/precision.txt

@@ -0,0 +1,10 @@
+9.406301382037950409e-01 9.390636803981691205e-01 9.350382911908047268e-01
+9.401635337510554358e-01 9.395969426298715899e-01 9.372305914766932977e-01
+9.488957027951828715e-01 9.420410611918410559e-01 9.366084522063734541e-01
+9.576945296182731715e-01 9.536061858418877213e-01 9.482365314254428412e-01
+9.501177620761676046e-01 9.462849397858063005e-01 9.423780532966015144e-01
+9.325201084299871157e-01 9.328089588054926384e-01 9.313350812484270103e-01
+9.330978091809980501e-01 9.324978891703328276e-01 9.317794664415114392e-01
+9.638714838021597009e-01 9.590832333466648985e-01 9.539616939963548869e-01
+9.240767897613652027e-01 9.240545705017109146e-01 9.219437408345565466e-01
+9.415411278496200742e-01 9.409078789494733641e-01 9.394747367017737272e-01

output_files/data/cnn_custom_loss/run8/train_loss.txt

@@ -0,0 +1,10 @@
+3.447442017954560622e+00
+3.032605540426612567e+00
+2.742131795889509061e+00
+2.478343357978917805e+00
+2.257342595348090786e+00
+2.067952862366100764e+00
+1.932888886735730560e+00
+1.779144155432146546e+00
+1.686574836139052680e+00
+1.585422100327479544e+00

output_files/data/cnn_custom_loss/run8/usage_weights.txt

@@ -0,0 +1,10 @@
+3.936345393657711522e+00 3.956220864457514974e+00 3.925039751856840731e+00
+3.925179001525750611e+00 3.994469675893861815e+00 3.971853111862147401e+00
+4.015317196089235097e+00 4.104230873728798024e+00 4.070394991595565060e+00
+3.910744708596085140e+00 3.954146783531009124e+00 3.947170004865719228e+00
+3.927876564276199023e+00 4.011052305745963942e+00 4.007251774704665870e+00
+3.896312018336436811e+00 3.946214901863008606e+00 3.926146430822128774e+00
+3.844265969379780934e+00 3.926398434653870950e+00 3.895556759874028607e+00
+3.814130870635099146e+00 3.906702958799252556e+00 3.915924946027232068e+00
+3.789132584777637369e+00 3.854966671877742002e+00 3.841349306370368311e+00
+3.666232820131840153e+00 3.794197632862366554e+00 3.807031315773607982e+00

output_files/data/cnn_custom_loss/run8/validation_loss.txt

@@ -0,0 +1,10 @@
+3.855386945146317412e+00
+3.124217235089435718e+00
+2.544980639367000919e+00
+2.212079491026095912e+00
+2.122859110816682993e+00
+1.983663900657135493e+00
+1.802326244486429863e+00
+2.012231487156037169e+00
+1.655694580661460691e+00
+1.587806274781172311e+00

output_files/data/rnn/run3/precision.txt

@@ -0,0 +1,10 @@
+9.723148024707817250e-01 9.630604808247789084e-01 9.620717237701688074e-01
+9.742256588010487217e-01 9.644491845531706353e-01 9.625679539024464271e-01
+9.793583077811847115e-01 9.722703639514731488e-01 9.674561910263813624e-01
+9.750255521486024257e-01 9.669932897835844532e-01 9.641825534373248408e-01
+9.751588677065280431e-01 9.676043194240767642e-01 9.647380349286813761e-01
+9.734924232324578819e-01 9.645713904812691641e-01 9.637603875038948109e-01
+9.744256321379372032e-01 9.648380215971203988e-01 9.636641040453924889e-01
+9.744478513975913803e-01 9.663711505132649426e-01 9.636048526863129071e-01
+9.800471048304670862e-01 9.689263653735057380e-01 9.638122324430861143e-01
+9.772252588543749452e-01 9.686708438874817029e-01 9.638714838021653630e-01

output_files/data/rnn/run3/train_loss.txt

@@ -0,0 +1,10 @@
+4.802699544467869779e-04
+4.273360533625727726e-04
+4.039634591400698442e-04
+3.593671435125180350e-04
+3.555946465726244721e-04
+3.332630187252748951e-04
+3.187152041339375778e-04
+3.042372855247271334e-04
+2.968075000402442976e-04
+2.859094250268788616e-04

output_files/data/rnn/run3/usage_weights.txt

@@ -0,0 +1,10 @@
+2.639223463407977199e+00 3.162304827395501672e+00 3.002933578572025031e+00
+2.640435049423367708e+00 3.178556340135207048e+00 2.980619358110639716e+00
+2.682672318055179694e+00 3.198413707240802317e+00 3.040913682115776506e+00
+2.636460751649627454e+00 3.173390977783855593e+00 3.000292057078069341e+00
+2.643382580919789948e+00 3.132824303494126994e+00 2.979020830576209367e+00
+2.645108158370484297e+00 3.172562938889210926e+00 3.011074741901686558e+00
+2.603392238543586590e+00 3.059977187417030731e+00 2.948180655529843541e+00
+2.455593373966231674e+00 2.989562178601280706e+00 2.916373133052857280e+00
+2.450515659634514343e+00 2.978212519748875575e+00 2.900591683249116759e+00
+2.494280683908981722e+00 3.031274722598638505e+00 2.931875422053293434e+00

output_files/data/rnn/run3/validation_loss.txt

@@ -0,0 +1,10 @@
+3.200215093165471175e-03
+2.832872110851423694e-03
+3.414532355753112369e-03
+2.974444527831834797e-03
+2.785137674981451837e-03
+3.116628717649228865e-03
+3.693625316708692118e-03
+3.440773388241248881e-03
+3.555314441048499762e-03
+3.532970938563382689e-03

output_files/data/rnn/run8/precision.txt

@@ -0,0 +1,10 @@
+9.896680442607652672e-01 9.809692041061192080e-01 9.764031462471712830e-01
+9.899346753766165019e-01 9.810914100342176258e-01 9.765068361255581086e-01
+9.903124027907390658e-01 9.813247122605874839e-01 9.767364351419849378e-01
+9.899568946362706789e-01 9.812025063324889551e-01 9.766994030425619755e-01
+9.900902101941962963e-01 9.812247255921432432e-01 9.767290287221011003e-01
+9.901568679731591605e-01 9.814135892992045251e-01 9.768697506999112212e-01
+9.903346220503932429e-01 9.813580411500688605e-01 9.768919699595658424e-01
+9.902679642714304897e-01 9.814246989290317247e-01 9.768993763794507901e-01
+9.903568413100475309e-01 9.814246989290317247e-01 9.769364084788736413e-01
+9.903790605697018190e-01 9.814691374483401898e-01 9.769067827993350717e-01

output_files/data/rnn/run8/train_loss.txt

@@ -0,0 +1,10 @@
+5.864146855659916171e-04
+5.633366759281050471e-04
+6.545921258797564443e-04
+5.475326251216883428e-04
+5.672426932793488879e-04
+1.258756600341643132e-03
+6.017132126703749395e-04
+6.092219044824460396e-04
+1.321081984164688538e-03
+5.829874503500343712e-04

output_files/data/rnn/run8/usage_weights.txt

@@ -0,0 +1,10 @@
+4.378735079483125681e+00 3.968104365814237866e+00 3.843236071828839862e+00
+4.381539278064927601e+00 3.903176569754001513e+00 3.903759890740498228e+00
+4.386123251224291586e+00 3.968987887433257367e+00 3.823754638521313254e+00
+4.391737366630641404e+00 4.113654657850194241e+00 3.840281456530012072e+00
+4.403949362040771476e+00 4.197625586743011006e+00 3.966169187623515224e+00
+4.397725108537621885e+00 4.012280744140413802e+00 3.739170578580423232e+00
+4.381264523133343580e+00 3.945400544386926001e+00 3.861414646466194256e+00
+4.406938428516977702e+00 3.905414775520493098e+00 3.841673246885459747e+00
+4.397726666076190227e+00 4.348804265355178167e+00 4.206314850830318086e+00
+4.402439583579986326e+00 4.399751702229505845e+00 4.176577369189176991e+00

output_files/data/rnn/run8/validation_loss.txt

@@ -0,0 +1,10 @@
+3.804541184578469522e-04
+3.670656945136249651e-04
+3.880013795301148153e-04
+3.904127285129954552e-04
+3.701605151980723210e-04
+3.722056163683904275e-04
+9.814247817029374613e-04
+3.945000151901545209e-04
+4.165869904311884377e-04
+4.400969773753974756e-04

output_files/paper_plots_dense_cnn_rnn.py

@@ -179,7 +179,6 @@ def assemble_usage():
         usage_top1 = list()
         usage_top2 = list()
         usage_top3 = list()
-        print(approach)
         for i in range(1, runs+1):
             path = base_path + approach + 'run' + str(i) + '/'
             usage_path = path + 'usage_weights.txt'
@@ -188,7 +187,6 @@ def assemble_usage():
                 usage_top1.append(top1_p)
                 usage_top2.append(top2_p)
                 usage_top3.append(top3_p)
-                print(i)
             except Exception:
                 continue
         mean_top1_usage = np.mean(usage_top1, axis=0)
@@ -221,7 +219,7 @@ def plot_accuracy(ax, x_val1, y1_top1, y2_top1, x_val2, y1_top2, y2_top2, x_val3
 
 def assemble_accuracy():
     fig = plt.figure(figsize=fig_size)
-    fig.suptitle('Precision@k for multiple neural network architectures', size=size_title + 2)
+    fig.suptitle('Mean precision@k for multiple neural network architectures', size=size_title + 2)
     for idx, approach in enumerate(all_approaches_path):
         if idx == 0:
             ax = plt.subplot(gs[0,0])