diff --git a/Model_KS_02.py b/Model_KS_02.py
deleted file mode 100644
index 307a132da97748a1bb16d557bfe840d6b61fd5cc..0000000000000000000000000000000000000000
--- a/Model_KS_02.py
+++ /dev/null
@@ -1,203 +0,0 @@
-###################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
-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 = 256 # CNN filter size
- cnn_pool_size = [2, 2, 2] # Maxpooling across frequency. Length of cnn_pool_size = number of CNN layers
- fc_nb = [1024, 32] # Number of FC nodes. Length of fc_nb = number of FC layers
- dropout_rate = 0.5 # Dropout after each layer
-
- for _i, _cnt in enumerate(cnn_pool_size):
- 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.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.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"))
- self.model.compile(optimizer='Adam', 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__':
- 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
-
- preprocess = PreProcessing.npz_preprocessing()
- X_train, Y_train = preprocess.load_from_npz(
- "/mainfs/cdt/TUT-sound-events-2017-modified/processed/train_fold_1_data.npz")
- # X_train, Y_train = preprocess.load_from_npz("/Users/charles/Documents/MINDS/Year1/6003_Project/datasets_processed/train_fold_1_data.npz")
- X_train, Y_train = preprocess.split_into_batches(X_train, Y_train, seq_len)
-
- X_test, Y_test = preprocess.load_from_npz(
- "/mainfs/cdt/TUT-sound-events-2017-modified/processed/test_fold_1_data.npz")
- # X_test, Y_test = preprocess.load_from_npz("/Users/charles/Documents/MINDS/Year1/6003_Project/datasets_processed/test_fold_1_data.npz")
- X_test, Y_test = preprocess.split_into_batches(X_test, Y_test, seq_len)
-
- our_model = model()
- our_model.Create_FP_Model(X_train, Y_train)
- our_model.Summary()
-
- # get the data ready for the network by adding another dimension for the feature maps
- X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], X_train.shape[2], 1))
- X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], X_test.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]
-
- # Folder for saving model and training curves
- __models_dir = '/mainfs/cdt/models/' + file_name + "/"
- # __models_dir = '/Users/charles/Documents/MINDS/Year1/6003_Project/local_testing/models/' + file_name + "/"
- from pathlib import Path
-
- Path(__models_dir).mkdir(parents=True, exist_ok=True)
-
- # TensorBoard Vars
- log_dir = __models_dir + "TensorLogs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
- 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
- avg_er = list()
- avg_f1 = list()
- figname_best_model = ''
- 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, '{}__{}.h5'.format(file_name, __fig_name)))
- figname_best_model = __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)
- 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
- model_filepath = __models_dir + '{}__{}.h5'.format(file_name, figname_best_model)
- ModelFunctions.Generate_Model_Graphs(X_test, model_filepath, __models_dir)
- ModelFunctions.Generate_Ground_Truth_Graphs(Y_test, __models_dir)
diff --git a/Model_KS_03.py b/Model_KS_03.py
deleted file mode 100644
index 2f059012d0eeccce4e672d405b48db90e8051081..0000000000000000000000000000000000000000
--- a/Model_KS_03.py
+++ /dev/null
@@ -1,216 +0,0 @@
-###################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
-from tensorflow.keras.regularizers import l1
-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
- rnn_nb = [32, 32] # Number of RNN nodes. Length of rnn_nb = number of RNN layers
- fc_nb = [32] # Number of FC nodes. Length of fc_nb = number of FC layers
- dropout_rate = 0.5 # Dropout after each layer
-
- for _i, _cnt in enumerate(cnn_pool_size):
- 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", kernel_regularizer=l1(0.0001)))
- 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 _r in rnn_nb:
- self.model.add(tf.keras.layers.Bidirectional(tf.keras.layers.GRU(_r, activation="tanh", dropout=dropout_rate, recurrent_dropout=dropout_rate, return_sequences=True), merge_mode="mul"))
-
- for _f in fc_nb:
- self.model.add(tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(_f)))
- 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"))
- self.model.compile(optimizer='Adam', 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 = ""
-
- 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
- #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 + "/"
-
- 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 = 10 # Training epochs
- patience = int(0.25 * nb_epoch) # Patience for early stopping
- Path(__models_dir).mkdir(parents=True, exist_ok=True)
-
- X_train, Y_train = preprocess.load_from_npz(train_data_path)
- X_train, Y_train = preprocess.split_into_batches(X_train, Y_train, seq_len)
-
- X_test, Y_test = preprocess.load_from_npz(test_data_path)
- X_test, Y_test = preprocess.split_into_batches(X_test, Y_test, seq_len)
-
- if fold == 1:
- print("Creating New Model...")
- our_model.Create_FP_Model(X_train, Y_train)
- else:
- print("Loading: {}...".format(model_filepath))
- our_model.model = tf.keras.models.load_model(model_filepath)
- our_model.Summary()
-
- #get the data ready for the network by adding another dimension for the feature maps
- X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], X_train.shape[2], 1))
- X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], X_test.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")
- 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
- avg_er = list()
- avg_f1 = list()
- 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)
- 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)
\ No newline at end of file