# model_path = 'thibault_model2/' # model_name = 'cnn_gpu.model' # size = 50 # model = nn.CNN_thibault() # model_path = 'thibault_model3/' # model_name = 'cnn_gpu.model' # size = 50 # model = nn.CNN_thibault() model_path = 'thibault_model5/' model_name = 'cnn_gpu.model' size = 50 model = nn.CNN_thibault2() # model_path = 'thibault_model6/' # model_name = 'cnn_gpu.model' # size = 50 # model = nn.CNN_thibault() serializers.load_npz(model_path + model_name, model) optimizer = chainer.optimizers.Adam() optimizer.setup(model) Xts, Yts = ld.load_test_dataset(test_N) Ye = validation(size, model, Xts, Yts) v.loss_visualizer(model_path) plt.show()
trainer.extend(extensions.LogReport()) # Print selected entries of the log to stdout # Here "main" refers to the target link of the "main" optimizer again, and # "validation" refers to the default name of the Evaluator extension. # Entries other than 'epoch' are reported by the Classifier link, called by # either the updater or the evaluator. trainer.extend( extensions.PrintReport([ 'epoch', 'main/loss', 'validation/main/loss', 'main/accuracy', 'validation/main/accuracy' ])) # Print a progress bar to stdout trainer.extend(extensions.ProgressBar()) start_time = time.time() #start time measurement # Run the training trainer.run() execution_time = time.time() - start_time print "execution time : " + str(execution_time) print('saved the model') serializers.save_npz('cnn.model', model) print('saved the optimizer') serializers.save_npz('cnn.state', optimizer) v.loss_visualizer()