Added the inceptionTime results with no shuffling for ETRA

config.py

@@ -42,8 +42,7 @@ Cluster can be set to clustering(), clustering2() or clustering3(), where differ
 """
 
 # Choosing model
-config['model'] = 'eegnet'
-config['model'] = 'cnn'
+config['model'] = 'inception'
 config['downsampled'] = False
 config['split'] = False
 config['cluster'] = clustering()

main.py

@@ -18,7 +18,7 @@ def main():
     logging.info('Started the Logging')
     start_time = time.time()
     # try:
-    # trainX, trainY = IOHelper.get_mat_data(config['data_dir'], verbose=True)
+    trainX, trainY = IOHelper.get_mat_data(config['data_dir'], verbose=True)
 
     # if config['model'] == 'eegnet' or config['model'] == 'eegnet_cluster':
     #    trainX = np.transpose(trainX, (0, 2, 1))
@@ -26,9 +26,9 @@ def main():
 
     # tune(trainX,trainY)
 
-    # run(trainX,trainY)
+    run(trainX,trainY)
     # select_best_model()
-    comparison_plot_loss()
+    # comparison_plot_loss()
 
     logging.info("--- Runtime: %s seconds ---" % (time.time() - start_time))
     logging.info('Finished Logging')

results/ETRA/inception_ensemble/inception_ensemble_df_best_model.csv

+best_model_train_loss,best_model_val_loss,best_model_train_acc,best_model_val_acc
+0.01928609237074852,0.15049758553504944,0.993760347366333,0.9424809424809425

results/ETRA/inception_ensemble/inception_ensemble_history.csv

+loss,accuracy,val_loss,val_accuracy
+0.6722853183746338,0.5859417915344238,0.6028470396995544,0.6611226611226612
+0.5265356302261353,0.7339699268341064,0.41125452518463135,0.8224532224532225
+0.3922158479690552,0.82166987657547,0.33120256662368774,0.865973665973666
+0.29196494817733765,0.8725868463516235,0.24931132793426514,0.9111573111573111
+0.21338815987110138,0.9094387888908386,0.23614224791526794,0.8999306999307
+0.1751759648323059,0.9267443418502808,0.24837961792945862,0.9075537075537076
+0.15001289546489716,0.9373965859413147,0.19534331560134888,0.9205821205821206
+0.13244186341762543,0.9461182951927185,0.17744697630405426,0.9325017325017325
+0.12098821997642517,0.9516340494155884,0.1869119107723236,0.9266805266805267
+0.1055828258395195,0.9584252834320068,0.1862993985414505,0.9304227304227304
+0.10049077123403549,0.9584252834320068,0.15370672941207886,0.9374913374913375
+0.08910729736089706,0.9653543829917908,0.1731726974248886,0.9287595287595287
+0.08551010489463806,0.9655267596244812,0.17658497393131256,0.9337491337491337
+0.08070551604032516,0.9698359370231628,0.15600478649139404,0.9391545391545392
+0.0676453486084938,0.973869264125824,0.1869611293077469,0.9334719334719335
+0.06528659164905548,0.9753171801567078,0.15727461874485016,0.9354123354123354
+0.05435468629002571,0.9783852696418762,0.17434537410736084,0.9331947331947332
+0.057876382023096085,0.977592408657074,0.24514557421207428,0.9180873180873181
+0.04892421513795853,0.9816946983337402,0.15651626884937286,0.9394317394317394
+0.04561583697795868,0.9828668236732483,0.1678732931613922,0.9381843381843382
+0.047174591571092606,0.9824186563491821,0.15873776376247406,0.9383229383229383
+0.042516980320215225,0.9836596846580505,0.15351776778697968,0.93998613998614
+0.043724723160266876,0.9834528565406799,0.1653166115283966,0.9354123354123354
+0.04096753150224686,0.9843836426734924,0.1594633162021637,0.934996534996535
+0.03846059367060661,0.9858659505844116,0.16427364945411682,0.9347193347193348
+0.03433896228671074,0.9879343509674072,0.2022698074579239,0.9343035343035343
+0.031095879152417183,0.9883135557174683,0.16637396812438965,0.9388773388773389
+0.03374674171209335,0.9877964854240417,0.1590413600206375,0.9358281358281358
+0.030995260924100876,0.9891409277915955,0.15908408164978027,0.9344421344421344
+0.03253192454576492,0.9881067276000977,0.15217256546020508,0.9388773388773389
+0.025174863636493683,0.9911059141159058,0.16574282944202423,0.9380457380457381
+0.025740234181284904,0.9910025000572205,0.23283922672271729,0.9094941094941095
+0.03183327615261078,0.9883480668067932,0.1536131054162979,0.9377685377685377
+0.022048894315958023,0.9922090172767639,0.1788920760154724,0.923908523908524
+0.023586412891745567,0.9916919469833374,0.15580466389656067,0.9386001386001386
+0.028705136850476265,0.9900027513504028,0.14732694625854492,0.9416493416493417
+0.022552447393536568,0.991898775100708,0.17103932797908783,0.9381843381843382
+0.01856909692287445,0.993760347366333,0.152370885014534,0.9377685377685377
+0.020421523600816727,0.9933466911315918,0.16610780358314514,0.9384615384615385
+0.02842124179005623,0.9902440905570984,0.17342473566532135,0.9340263340263341
+0.022968309000134468,0.991933286190033,0.1650119572877884,0.9369369369369369
+0.01836862601339817,0.9941051006317139,0.16068759560585022,0.9381843381843382
+0.022933362051844597,0.9917953610420227,0.16337242722511292,0.9367983367983368
+0.022229192778468132,0.9920021891593933,0.1692405790090561,0.9334719334719335
+0.019939107820391655,0.9932432174682617,0.17722535133361816,0.9352737352737353
+0.019692491739988327,0.9931398034095764,0.1535763293504715,0.9416493416493417
+0.01373304147273302,0.9953116178512573,0.1870376318693161,0.9330561330561331
+0.02113223262131214,0.9921401143074036,0.15716007351875305,0.9376299376299376
+0.01928609237074852,0.993760347366333,0.15049758553504944,0.9424809424809425
+0.01314290426671505,0.995621919631958,0.16562756896018982,0.9351351351351351

results/ETRA/inception_ensemble/info.log

+INFO:root:Started the Logging
+INFO:root:X training loaded.
+INFO:root:(129, 500, 36223)
+INFO:root:y training loaded.
+INFO:root:(1, 36223)
+INFO:root:Setting the shapes
+INFO:root:(36223, 500, 129)
+INFO:root:(36223, 1)
+INFO:root:Started running inception. If you want to run other methods please choose another model in the config.py file.
+INFO:root:Parameters: 
+INFO:root:--------------- use residual : True
+INFO:root:--------------- depth        : 12
+INFO:root:--------------- batch size   : 64
+INFO:root:--------------- kernel size  : 64
+INFO:root:--------------- nb filters   : 16
+INFO:root:--------------- preprocessing: False
+INFO:root:--------------- bottleneck_size : 16
+INFO:root:Parameters: 
+INFO:root:--------------- use residual : True
+INFO:root:--------------- depth        : 12
+INFO:root:--------------- batch size   : 64
+INFO:root:--------------- kernel size  : 64
+INFO:root:--------------- nb filters   : 16
+INFO:root:--------------- preprocessing: False
+INFO:root:--------------- bottleneck_size : 16
+INFO:root:Parameters: 
+INFO:root:--------------- use residual : True
+INFO:root:--------------- depth        : 12
+INFO:root:--------------- batch size   : 64
+INFO:root:--------------- kernel size  : 64
+INFO:root:--------------- nb filters   : 16
+INFO:root:--------------- preprocessing: False
+INFO:root:--------------- bottleneck_size : 16
+INFO:root:Parameters: 
+INFO:root:--------------- use residual : True
+INFO:root:--------------- depth        : 12
+INFO:root:--------------- batch size   : 64
+INFO:root:--------------- kernel size  : 64
+INFO:root:--------------- nb filters   : 16
+INFO:root:--------------- preprocessing: False
+INFO:root:--------------- bottleneck_size : 16
+INFO:root:Parameters: 
+INFO:root:--------------- use residual : True
+INFO:root:--------------- depth        : 12
+INFO:root:--------------- batch size   : 64
+INFO:root:--------------- kernel size  : 64
+INFO:root:--------------- nb filters   : 16
+INFO:root:--------------- preprocessing: False
+INFO:root:--------------- bottleneck_size : 16
+INFO:root:**********
+
+INFO:root:--- Runtime: 10901.414864778519 seconds ---
+INFO:root:Finished Logging