diff --git a/model_binary.tflite b/Demonstration Files/model_binary.tflite
similarity index 100%
rename from model_binary.tflite
rename to Demonstration Files/model_binary.tflite
diff --git a/model_fp.tflite b/Demonstration Files/model_fp.tflite
similarity index 100%
rename from model_fp.tflite
rename to Demonstration Files/model_fp.tflite
diff --git a/Archive/Model_CH_01.py b/Model Archive/Model_CH_01.py
similarity index 100%
rename from Archive/Model_CH_01.py
rename to Model Archive/Model_CH_01.py
diff --git a/Archive/Model_CH_02.py b/Model Archive/Model_CH_02.py
similarity index 100%
rename from Archive/Model_CH_02.py
rename to Model Archive/Model_CH_02.py
diff --git a/Archive/Model_CH_03.py b/Model Archive/Model_CH_03.py
similarity index 100%
rename from Archive/Model_CH_03.py
rename to Model Archive/Model_CH_03.py
diff --git a/Archive/Model_CH_04.py b/Model Archive/Model_CH_04.py
similarity index 100%
rename from Archive/Model_CH_04.py
rename to Model Archive/Model_CH_04.py
diff --git a/Archive/Model_CH_05.py b/Model Archive/Model_CH_05.py
similarity index 100%
rename from Archive/Model_CH_05.py
rename to Model Archive/Model_CH_05.py
diff --git a/Archive/Model_CH_06.py b/Model Archive/Model_CH_06.py
similarity index 100%
rename from Archive/Model_CH_06.py
rename to Model Archive/Model_CH_06.py
diff --git a/Model_CH_07.py b/Model Archive/Model_CH_07.py
similarity index 100%
rename from Model_CH_07.py
rename to Model Archive/Model_CH_07.py
diff --git a/Model_CH_08.py b/Model Archive/Model_CH_08.py
similarity index 100%
rename from Model_CH_08.py
rename to Model Archive/Model_CH_08.py
diff --git a/Model_CH_09.py b/Model Archive/Model_CH_09.py
similarity index 100%
rename from Model_CH_09.py
rename to Model Archive/Model_CH_09.py
diff --git a/Model_CH_10.py b/Model Archive/Model_CH_10.py
similarity index 100%
rename from Model_CH_10.py
rename to Model Archive/Model_CH_10.py
diff --git a/Model_CH_11.py b/Model Archive/Model_CH_11.py
similarity index 100%
rename from Model_CH_11.py
rename to Model Archive/Model_CH_11.py
diff --git a/Model_CH_12.py b/Model Archive/Model_CH_12.py
similarity index 100%
rename from Model_CH_12.py
rename to Model Archive/Model_CH_12.py
diff --git a/Model_CH_13.py b/Model Archive/Model_CH_13.py
similarity index 100%
rename from Model_CH_13.py
rename to Model Archive/Model_CH_13.py
diff --git a/Archive/Model_KS_02.py b/Model Archive/Model_KS_02.py
similarity index 100%
rename from Archive/Model_KS_02.py
rename to Model Archive/Model_KS_02.py
diff --git a/Archive/Model_KS_03.py b/Model Archive/Model_KS_03.py
similarity index 100%
rename from Archive/Model_KS_03.py
rename to Model Archive/Model_KS_03.py
diff --git a/Model_Final_Binary.py b/Model_Final_Binary.py
new file mode 100644
index 0000000000000000000000000000000000000000..a03c7f7236a4edd207238adaa423cb20c83e166c
--- /dev/null
+++ b/Model_Final_Binary.py
@@ -0,0 +1,242 @@
+###################Dependency Imports#################
+import tensorflow as tf
+import larq as lq
+import numpy as np
+import os
+import matplotlib
+matplotlib.use('Agg')
+import matplotlib.pyplot as plot
+from sklearn.metrics import confusion_matrix
+import time
+from pathlib import Path
+import datetime
+
+#################OUR IMPORTS##################
+import PreProcessing
+import ModelFunctions
+
+##Sharath's Imports
+import metrics
+import utils
+
+class_dict_classToNum = {
+ 'brakes squeaking': 0,
+ 'car': 1,
+ 'children': 2,
+ 'large vehicle': 3,
+ 'people speaking': 4,
+ 'people walking': 5
+ }
+class_dict_numToClass = dict(map(reversed, class_dict_classToNum.items()))
+
+class model:
+ def __init__(self):
+ self.model = tf.keras.models.Sequential()
+ return
+
+ def Create_FP_Model(self, X_train, Y_train):
+ # CNN model definition
+ cnn_nb_filt = 128 # CNN filter size
+ cnn_pool_size = [2, 2] # Maxpooling across frequency. Length of cnn_pool_size = number of CNN layers
+ fp_cnn_pool_size = 5
+ fc_nb = [32] # Number of FC nodes. Length of fc_nb = number of FC layers
+ dropout_rate = 0.2 # Dropout after each layer
+
+ kwargs = dict(
+ input_quantizer="ste_sign",
+ kernel_quantizer="ste_sign",
+ kernel_constraint="weight_clip")
+
+ self.model.add(tf.keras.layers.Conv2D(cnn_nb_filt, (3, 3), input_shape=(X_train.shape[1], X_train.shape[2], 1), padding="same"))
+ self.model.add(tf.keras.layers.Activation("relu")) # change the order of activation and batch normalization according to "https://docs.larq.dev/compute-engine/end_to_end/"
+ self.model.add(tf.keras.layers.BatchNormalization())
+ self.model.add(tf.keras.layers.MaxPooling2D((1, fp_cnn_pool_size)))
+
+ for _i, _cnt in enumerate(cnn_pool_size):
+ self.model.add(lq.layers.QuantConv2D(cnn_nb_filt, (3, 3), padding="same", **kwargs))
+ self.model.add(tf.keras.layers.Activation("relu")) # change the order of activation and batch normalization according to "https://docs.larq.dev/compute-engine/end_to_end/"
+ self.model.add(tf.keras.layers.BatchNormalization())
+ self.model.add(tf.keras.layers.MaxPooling2D((1, cnn_pool_size[_i])))
+ self.model.add(tf.keras.layers.Reshape(
+ (X_train.shape[-2], int(cnn_nb_filt * (X_train.shape[-1] / (fp_cnn_pool_size * np.prod(cnn_pool_size)))))))
+
+ for _f in fc_nb:
+ self.model.add(tf.keras.layers.TimeDistributed(lq.layers.QuantDense(_f, **kwargs)))
+ self.model.add(tf.keras.layers.Activation("relu")) # added relu activation function
+ self.model.add(tf.keras.layers.BatchNormalization())
+ self.model.add(tf.keras.layers.Dropout(dropout_rate))
+
+ self.model.add(tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(Y_train.shape[2])))
+ self.model.add(tf.keras.layers.Activation("sigmoid", name="strong_out"))
+ case_optimizer = lq.optimizers.CaseOptimizer(
+ (
+ lq.optimizers.Bop.is_binary_variable, # predicate
+ lq.optimizers.Bop(threshold=1e-5, gamma=1e-6), # optimizer
+ ),
+ default_optimizer=tf.keras.optimizers.Adam(learning_rate=0.001, decay=0.001, name='Adam'),
+ ) # Case Bop optimizer
+ self.model.compile(optimizer=case_optimizer, loss='binary_crossentropy')
+
+ def Summary(self):
+ lq.models.summary(self.model)
+
+def plot_functions(_nb_epoch, _tr_loss, _val_loss, _f1, _er, extension=''):
+ plot.figure()
+
+ plot.subplot(211)
+ plot.plot(range(_nb_epoch), _tr_loss, label='train loss')
+ plot.plot(range(_nb_epoch), _val_loss, label='val loss')
+ plot.legend()
+ plot.grid(True)
+
+ plot.subplot(212)
+ plot.plot(range(_nb_epoch), _f1, label='f')
+ plot.plot(range(_nb_epoch), _er, label='er')
+ plot.legend()
+ plot.grid(True)
+
+ plot.savefig(__models_dir + __fig_name + extension)
+ plot.close()
+ print('figure name : {}'.format(__fig_name))
+
+if __name__ == '__main__':
+ #set up some classes
+ preprocess = PreProcessing.npz_preprocessing()
+ our_model = model()
+ model_filepath = ""
+
+ avg_er = list()
+ avg_f1 = list()
+ for fold in [1, 2, 3, 4]:
+ # COMMENT AND UNCOMMENT TO RUN LOCALLY:
+ # IRIDIS
+ #train_data_path = "/mainfs/cdt/TUT-sound-events-2017-modified/processed/train_fold_{}_data.npz".format(fold)
+ #test_data_path = "/mainfs/cdt/TUT-sound-events-2017-modified/processed/test_fold_{}_data.npz".format(fold)
+ #file_name = os.path.splitext(__file__)[0]
+ #__models_dir = '/mainfs/cdt/models/' + file_name + "/"
+
+ #LOCAL - For MAC
+ #train_data_path = "/Users/charles/Documents/MINDS/Year1/6003_Project/datasets_processed/TUT-2016/train_fold_{}_data.npz".format(fold)
+ #test_data_path = "/Users/charles/Documents/MINDS/Year1/6003_Project/datasets_processed/TUT-2016/test_fold_{}_data.npz".format(fold)
+ #file_name = os.path.splitext(os.path.basename(__file__))[0]
+ #__models_dir = '/Users/charles/Documents/MINDS/Year1/6003_Project/local_testing/models/' + file_name + "/"
+
+ # LOCAL - For Linux
+ train_data_path = "/home/charles/Documents/MINDS/Year1/Interdisciplinary_Project_6003/datasets/TUT-sound-events-2017-modified/processed/train_fold_{}_data.npz".format(fold)
+ test_data_path = "/home/charles/Documents/MINDS/Year1/Interdisciplinary_Project_6003/datasets/TUT-sound-events-2017-modified/processed/test_fold_{}_data.npz".format(fold)
+ file_name = os.path.splitext(os.path.basename(__file__))[0]
+ __models_dir = '/home/charles/Documents/MINDS/Year1/Interdisciplinary_Project_6003/PyProjects/localtesting/models/' + file_name + "/"
+
+ print("########FOLD: {}".format(fold))
+
+ batch_size = 128 # Decrease this if you want to run on smaller GPU's
+ seq_len = 256 # Frame sequence length. Input to the CRNN.
+ nb_epoch = 500 # Training epochs
+ patience = int(0.25 * nb_epoch) # Patience for early stopping
+ Path(__models_dir).mkdir(parents=True, exist_ok=True)
+
+ X_train_orig, Y_train = preprocess.load_from_npz(train_data_path)
+ X_train_orig, Y_train = preprocess.split_into_batches(X_train_orig, Y_train, seq_len)
+
+ X_test_orig, Y_test = preprocess.load_from_npz(test_data_path)
+ X_test_orig, Y_test = preprocess.split_into_batches(X_test_orig, Y_test, seq_len)
+
+ print("Creating New Model...")
+ our_model = model()
+ our_model.Create_FP_Model(X_train_orig, Y_train)
+ our_model.Summary()
+
+ #get the data ready for the network by adding another dimension for the feature maps
+ X_train = X_train_orig.reshape((X_train_orig.shape[0], X_train_orig.shape[1], X_train_orig.shape[2], 1))
+ X_test = X_test_orig.reshape((X_test_orig.shape[0], X_test_orig.shape[1], X_test_orig.shape[2], 1))
+
+ #------------------------------------
+ #the next bit is just copy and paste from Sharath SED
+ #------------------------------------
+ # Number of frames in 1 second, required to calculate F and ER for 1 sec segments.
+ # Make sure the nfft and sr are the same as in feature.py
+ sr = 44100
+ nfft = 2048
+ frames_1_sec = int(sr / (nfft / 2.0))
+
+ __fig_name = time.strftime("%m_%d_%H_%M_%S")
+ file_name = os.path.splitext(__file__)[0]
+ # file_name = os.path.splitext(os.path.basename(__file__))[0]
+
+ # TensorBoard Vars
+ log_dir = __models_dir + "TensorLogs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
+ file_writer = tf.summary.create_file_writer(log_dir + "/metrics")
+ file_writer.set_as_default()
+ tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir,
+ histogram_freq=0,
+ write_graph=True,
+ write_images=True,
+ update_freq='epoch',
+ profile_batch=2,
+ embeddings_freq=1)
+
+ # Training
+ best_epoch, pat_cnt, best_er, f1_for_best_er, best_conf_mat = 0, 0, 99999, None, None
+ tr_loss, val_loss, f1_overall_1sec_list, er_overall_1sec_list = [0] * nb_epoch, [0] * nb_epoch, [0] * nb_epoch, [0] * nb_epoch
+ posterior_thresh = 0.5
+ for i in range(nb_epoch):
+ print('Epoch : {} '.format(i), end='')
+ hist = our_model.model.fit(
+ X_train, Y_train,
+ batch_size=batch_size,
+ validation_data=(X_test, Y_test),
+ epochs=1,
+ verbose=2,
+ callbacks=[tensorboard_callback]
+ )
+
+ val_loss[i] = hist.history.get('val_loss')[-1]
+ tr_loss[i] = hist.history.get('loss')[-1]
+
+ # Calculate the predictions on test data, in order to calculate ER and F scores
+ pred = our_model.model.predict(X_test)
+ pred_thresh = pred > posterior_thresh
+ score_list = metrics.compute_scores(pred_thresh, Y_test, frames_in_1_sec=frames_1_sec)
+
+ f1_overall_1sec_list[i] = score_list['f1_overall_1sec']
+ er_overall_1sec_list[i] = score_list['er_overall_1sec']
+ pat_cnt = pat_cnt + 1
+
+ # Calculate confusion matrix
+ test_pred_cnt = np.sum(pred_thresh, 2)
+ Y_test_cnt = np.sum(Y_test, 2)
+ conf_mat = confusion_matrix(Y_test_cnt.reshape(-1), test_pred_cnt.reshape(-1))
+ conf_mat = conf_mat / (utils.eps + np.sum(conf_mat, 1)[:, None].astype('float'))
+
+ if er_overall_1sec_list[i] < best_er:
+ best_conf_mat = conf_mat
+ best_er = er_overall_1sec_list[i]
+ f1_for_best_er = f1_overall_1sec_list[i]
+ our_model.model.save(os.path.join(__models_dir, '{}__{}.tf'.format(file_name, __fig_name)), save_format='tf')
+ model_filepath = __models_dir + '{}__{}.tf'.format(file_name, __fig_name)
+ best_epoch = i
+ pat_cnt = 0
+
+ print('tr Er : {}, val Er : {}, F1_overall : {}, ER_overall : {} Best ER : {}, best_epoch: {}'.format(
+ tr_loss[i], val_loss[i], f1_overall_1sec_list[i], er_overall_1sec_list[i], best_er, best_epoch))
+ plot_functions(nb_epoch, tr_loss, val_loss, f1_overall_1sec_list, er_overall_1sec_list)
+ with file_writer.as_default():
+ tf.summary.scalar('f1', f1_overall_1sec_list[i], step=i)
+ tf.summary.scalar('er', er_overall_1sec_list[i], step=i)
+ tf.summary.scalar('validation_loss', val_loss[i], step=i)
+ tf.summary.scalar('test_loss', tr_loss[i], step=i)
+ avg_er.append(best_er)
+ avg_f1.append(f1_for_best_er)
+ print('saved model for the best_epoch: {} with best_f1: {} f1_for_best_er: {}'.format(
+ best_epoch, best_er, f1_for_best_er))
+ print('best_conf_mat: {}'.format(best_conf_mat))
+ print('best_conf_mat_diag: {}'.format(np.diag(best_conf_mat)))
+
+ #lets make some graphs
+ fold_label_dir = __models_dir + "/{}/".format(fold)
+ Path(fold_label_dir).mkdir(parents=True, exist_ok=True)
+ ModelFunctions.Generate_Model_Graphs(X_test, model_filepath, fold_label_dir)
+ ModelFunctions.Generate_Ground_Truth_Graphs(Y_test, fold_label_dir)
+
+ print('\n\nMETRICS FOR ALL FOUR FOLDS: avg_er: {}, avg_f1: {}'.format(avg_er, avg_f1))
+ print('MODEL AVERAGE OVER FOUR FOLDS: avg_er: {}, avg_f1: {}'.format(np.mean(avg_er), np.mean(avg_f1)))
\ No newline at end of file
diff --git a/Model_Final_FullPrecision.py b/Model_Final_FullPrecision.py
new file mode 100644
index 0000000000000000000000000000000000000000..551a123cb161d64da2c0d014cef90d749597b27a
--- /dev/null
+++ b/Model_Final_FullPrecision.py
@@ -0,0 +1,230 @@
+###################Dependency Imports#################
+import tensorflow as tf
+import larq as lq
+import numpy as np
+import os
+import matplotlib
+matplotlib.use('Agg')
+import matplotlib.pyplot as plot
+from sklearn.metrics import confusion_matrix
+import time
+from pathlib import Path
+import datetime
+
+#################OUR IMPORTS##################
+import PreProcessing
+import ModelFunctions
+
+##Sharath's Imports
+import metrics
+import utils
+
+class_dict_classToNum = {
+ 'brakes squeaking': 0,
+ 'car': 1,
+ 'children': 2,
+ 'large vehicle': 3,
+ 'people speaking': 4,
+ 'people walking': 5
+ }
+class_dict_numToClass = dict(map(reversed, class_dict_classToNum.items()))
+
+class model:
+ def __init__(self):
+ self.model = tf.keras.models.Sequential()
+ return
+
+ def Create_FP_Model(self, X_train, Y_train):
+ # CRNN model definition
+ cnn_nb_filt = 128 # CNN filter size
+ cnn_pool_size = [5, 2, 2] # Maxpooling across frequency. Length of cnn_pool_size = number of CNN layers
+ cnn_kernel_size = [5, 3, 3]
+ fc_nb = [32] # Number of FC nodes. Length of fc_nb = number of FC layers
+ dropout_rate = 0.5 # Dropout after each layer
+
+ #decreased the dropout rate to 0.2 from 0.5
+ for _i, _cnt in enumerate(cnn_pool_size):
+ self.model.add(tf.keras.layers.Conv2D(cnn_nb_filt, cnn_kernel_size[_i], input_shape=(X_train.shape[1], X_train.shape[2], 1), padding="same")) #tried this with "valid" and it came up with an error :(, also changed the kernel size for the first layer
+ self.model.add(tf.keras.layers.BatchNormalization())
+ self.model.add(tf.keras.layers.Activation("relu"))
+ self.model.add(tf.keras.layers.MaxPooling2D((1, cnn_pool_size[_i])))
+ self.model.add(tf.keras.layers.Reshape((X_train.shape[-2], int(cnn_nb_filt * (X_train.shape[-1] / np.prod(cnn_pool_size))))))
+
+ for _f in fc_nb:
+ self.model.add(tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(_f)))
+ self.model.add(tf.keras.layers.BatchNormalization())
+ self.model.add(tf.keras.layers.Activation("relu")) #added relu activation function
+ self.model.add(tf.keras.layers.Dropout(dropout_rate))
+
+ # Custom Adam Optimiser
+ opt = tf.keras.optimizers.Adam(learning_rate=0.001, decay=0.001, name='Adam')
+
+ self.model.add(tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(Y_train.shape[2])))
+ self.model.add(tf.keras.layers.Activation("sigmoid", name="strong_out"))
+ self.model.compile(optimizer=opt, loss='binary_crossentropy')
+
+ def Summary(self):
+ lq.models.summary(self.model)
+
+def plot_functions(_nb_epoch, _tr_loss, _val_loss, _f1, _er, extension=''):
+ plot.figure()
+
+ plot.subplot(211)
+ plot.plot(range(_nb_epoch), _tr_loss, label='train loss')
+ plot.plot(range(_nb_epoch), _val_loss, label='val loss')
+ plot.legend()
+ plot.grid(True)
+
+ plot.subplot(212)
+ plot.plot(range(_nb_epoch), _f1, label='f')
+ plot.plot(range(_nb_epoch), _er, label='er')
+ plot.legend()
+ plot.grid(True)
+
+ plot.savefig(__models_dir + __fig_name + extension)
+ plot.close()
+ print('figure name : {}'.format(__fig_name))
+
+if __name__ == '__main__':
+ #set up some classes
+ preprocess = PreProcessing.npz_preprocessing()
+ our_model = model()
+ model_filepath = ""
+
+ avg_er = list()
+ avg_f1 = list()
+ for fold in [1, 2, 3, 4]:
+ # COMMENT AND UNCOMMENT TO RUN LOCALLY:
+ # IRIDIS
+ #train_data_path = "/mainfs/cdt/TUT-sound-events-2017-modified/processed/train_fold_{}_data.npz".format(fold)
+ #test_data_path = "/mainfs/cdt/TUT-sound-events-2017-modified/processed/test_fold_{}_data.npz".format(fold)
+ #file_name = os.path.splitext(__file__)[0]
+ #__models_dir = '/mainfs/cdt/models/' + file_name + "/"
+
+ #LOCAL - For MAC
+ #train_data_path = "/Users/charles/Documents/MINDS/Year1/6003_Project/datasets_processed/TUT-2016/train_fold_{}_data.npz".format(fold)
+ #test_data_path = "/Users/charles/Documents/MINDS/Year1/6003_Project/datasets_processed/TUT-2016/test_fold_{}_data.npz".format(fold)
+ #file_name = os.path.splitext(os.path.basename(__file__))[0]
+ #__models_dir = '/Users/charles/Documents/MINDS/Year1/6003_Project/local_testing/models/' + file_name + "/"
+
+ # LOCAL - For Linux
+ train_data_path = "/home/charles/Documents/MINDS/Year1/Interdisciplinary_Project_6003/datasets/TUT-sound-events-2017-modified/processed/train_fold_{}_data.npz".format(fold)
+ test_data_path = "/home/charles/Documents/MINDS/Year1/Interdisciplinary_Project_6003/datasets/TUT-sound-events-2017-modified/processed/test_fold_{}_data.npz".format(fold)
+ file_name = os.path.splitext(os.path.basename(__file__))[0]
+ __models_dir = '/home/charles/Documents/MINDS/Year1/Interdisciplinary_Project_6003/PyProjects/localtesting/models/' + file_name + "/"
+
+ print("########FOLD: {}".format(fold))
+
+ batch_size = 128 # Decrease this if you want to run on smaller GPU's
+ seq_len = 256 # Frame sequence length. Input to the CRNN.
+ nb_epoch = 500 # Training epochs
+ patience = int(0.25 * nb_epoch) # Patience for early stopping
+ Path(__models_dir).mkdir(parents=True, exist_ok=True)
+
+ X_train_orig, Y_train = preprocess.load_from_npz(train_data_path)
+ X_train_orig, Y_train = preprocess.split_into_batches(X_train_orig, Y_train, seq_len)
+
+ X_test_orig, Y_test = preprocess.load_from_npz(test_data_path)
+ X_test_orig, Y_test = preprocess.split_into_batches(X_test_orig, Y_test, seq_len)
+
+ print("Creating New Model...")
+ our_model = model()
+ our_model.Create_FP_Model(X_train_orig, Y_train)
+ our_model.Summary()
+
+ #get the data ready for the network by adding another dimension for the feature maps
+ X_train = X_train_orig.reshape((X_train_orig.shape[0], X_train_orig.shape[1], X_train_orig.shape[2], 1))
+ X_test = X_test_orig.reshape((X_test_orig.shape[0], X_test_orig.shape[1], X_test_orig.shape[2], 1))
+
+ #------------------------------------
+ #the next bit is just copy and paste from Sharath SED
+ #------------------------------------
+ # Number of frames in 1 second, required to calculate F and ER for 1 sec segments.
+ # Make sure the nfft and sr are the same as in feature.py
+ sr = 44100
+ nfft = 2048
+ frames_1_sec = int(sr / (nfft / 2.0))
+
+ __fig_name = time.strftime("%m_%d_%H_%M_%S")
+ file_name = os.path.splitext(__file__)[0]
+ # file_name = os.path.splitext(os.path.basename(__file__))[0]
+
+ # TensorBoard Vars
+ log_dir = __models_dir + "TensorLogs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
+ file_writer = tf.summary.create_file_writer(log_dir + "/metrics")
+ file_writer.set_as_default()
+ tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir,
+ histogram_freq=0,
+ write_graph=True,
+ write_images=True,
+ update_freq='epoch',
+ profile_batch=2,
+ embeddings_freq=1)
+
+ # Training
+ best_epoch, pat_cnt, best_er, f1_for_best_er, best_conf_mat = 0, 0, 99999, None, None
+ tr_loss, val_loss, f1_overall_1sec_list, er_overall_1sec_list = [0] * nb_epoch, [0] * nb_epoch, [0] * nb_epoch, [0] * nb_epoch
+ posterior_thresh = 0.5
+ for i in range(nb_epoch):
+ print('Epoch : {} '.format(i), end='')
+ hist = our_model.model.fit(
+ X_train, Y_train,
+ batch_size=batch_size,
+ validation_data=(X_test, Y_test),
+ epochs=1,
+ verbose=2,
+ callbacks=[tensorboard_callback]
+ )
+
+ val_loss[i] = hist.history.get('val_loss')[-1]
+ tr_loss[i] = hist.history.get('loss')[-1]
+
+ # Calculate the predictions on test data, in order to calculate ER and F scores
+ pred = our_model.model.predict(X_test)
+ pred_thresh = pred > posterior_thresh
+ score_list = metrics.compute_scores(pred_thresh, Y_test, frames_in_1_sec=frames_1_sec)
+
+ f1_overall_1sec_list[i] = score_list['f1_overall_1sec']
+ er_overall_1sec_list[i] = score_list['er_overall_1sec']
+ pat_cnt = pat_cnt + 1
+
+ # Calculate confusion matrix
+ test_pred_cnt = np.sum(pred_thresh, 2)
+ Y_test_cnt = np.sum(Y_test, 2)
+ conf_mat = confusion_matrix(Y_test_cnt.reshape(-1), test_pred_cnt.reshape(-1))
+ conf_mat = conf_mat / (utils.eps + np.sum(conf_mat, 1)[:, None].astype('float'))
+
+ if er_overall_1sec_list[i] < best_er:
+ best_conf_mat = conf_mat
+ best_er = er_overall_1sec_list[i]
+ f1_for_best_er = f1_overall_1sec_list[i]
+ our_model.model.save(os.path.join(__models_dir, '{}__{}.tf'.format(file_name, __fig_name)), save_format='tf')
+ model_filepath = __models_dir + '{}__{}.tf'.format(file_name, __fig_name)
+ best_epoch = i
+ pat_cnt = 0
+
+ print('tr Er : {}, val Er : {}, F1_overall : {}, ER_overall : {} Best ER : {}, best_epoch: {}'.format(
+ tr_loss[i], val_loss[i], f1_overall_1sec_list[i], er_overall_1sec_list[i], best_er, best_epoch))
+ plot_functions(nb_epoch, tr_loss, val_loss, f1_overall_1sec_list, er_overall_1sec_list)
+ with file_writer.as_default():
+ tf.summary.scalar('f1', f1_overall_1sec_list[i], step=i)
+ tf.summary.scalar('er', er_overall_1sec_list[i], step=i)
+ tf.summary.scalar('validation_loss', val_loss[i], step=i)
+ tf.summary.scalar('test_loss', tr_loss[i], step=i)
+ if pat_cnt > patience:
+ break
+ avg_er.append(best_er)
+ avg_f1.append(f1_for_best_er)
+ print('saved model for the best_epoch: {} with best_f1: {} f1_for_best_er: {}'.format(
+ best_epoch, best_er, f1_for_best_er))
+ print('best_conf_mat: {}'.format(best_conf_mat))
+ print('best_conf_mat_diag: {}'.format(np.diag(best_conf_mat)))
+
+ #lets make some graphs
+ fold_label_dir = __models_dir + "/{}/".format(fold)
+ Path(fold_label_dir).mkdir(parents=True, exist_ok=True)
+ ModelFunctions.Generate_Model_Graphs(X_test, model_filepath, fold_label_dir)
+ ModelFunctions.Generate_Ground_Truth_Graphs(Y_test, fold_label_dir)
+
+ print('\n\nMETRICS FOR ALL FOUR FOLDS: avg_er: {}, avg_f1: {}'.format(avg_er, avg_f1))
+ print('MODEL AVERAGE OVER FOUR FOLDS: avg_er: {}, avg_f1: {}'.format(np.mean(avg_er), np.mean(avg_f1)))
\ No newline at end of file
diff --git a/run_on_iridis.sh b/Scripts/run_on_iridis.sh
similarity index 100%
rename from run_on_iridis.sh
rename to Scripts/run_on_iridis.sh
diff --git a/run_on_iridis_gpu.sh b/Scripts/run_on_iridis_gpu.sh
similarity index 100%
rename from run_on_iridis_gpu.sh
rename to Scripts/run_on_iridis_gpu.sh