diff --git a/modules/deeplearning/espcn.py b/modules/deeplearning/espcn.py
new file mode 100644
index 0000000000000000000000000000000000000000..69f654a35346c39a309f8b4432ed282633ea8d48
--- /dev/null
+++ b/modules/deeplearning/espcn.py
@@ -0,0 +1,829 @@
+import glob
+import tensorflow as tf
+from util.setup import logdir, modeldir, cachepath, now, ancillary_path, home_dir
+from util.util import EarlyStop, normalize, scale, make_for_full_domain_predict
+import os, datetime
+import numpy as np
+import pickle
+import h5py
+
+# L1B M/I-bands: /apollo/cloud/scratch/cwhite/VIIRS_HRES/2019/2019_01_01/
+# CLAVRx: /apollo/cloud/scratch/Satellite_Output/VIIRS_HRES/2019/2019_01_01/
+# /apollo/cloud/scratch/Satellite_Output/andi/NEW/VIIRS_HRES/2019
+
+LOG_DEVICE_PLACEMENT = False
+
+PROC_BATCH_SIZE = 10
+PROC_BATCH_BUFFER_SIZE = 50000
+
+NumClasses = 2
+if NumClasses == 2:
+ NumLogits = 1
+else:
+ NumLogits = NumClasses
+
+BATCH_SIZE = 128
+NUM_EPOCHS = 60
+
+TRACK_MOVING_AVERAGE = False
+EARLY_STOP = False
+
+NOISE_TRAINING = True
+NOISE_STDDEV = 0.10
+DO_AUGMENT = True
+
+img_width = 16
+
+# setup scaling parameters dictionary
+mean_std_dct = {}
+mean_std_file = ancillary_path+'mean_std_lo_hi_l2.pkl'
+f = open(mean_std_file, 'rb')
+mean_std_dct_l2 = pickle.load(f)
+f.close()
+
+mean_std_file = ancillary_path+'mean_std_lo_hi_l1b.pkl'
+f = open(mean_std_file, 'rb')
+mean_std_dct_l1b = pickle.load(f)
+f.close()
+
+mean_std_dct.update(mean_std_dct_l1b)
+mean_std_dct.update(mean_std_dct_l2)
+
+emis_params = ['temp_10_4um_nom', 'temp_11_0um_nom', 'temp_12_0um_nom', 'temp_13_3um_nom', 'temp_3_75um_nom',
+ 'temp_6_7um_nom', 'temp_6_2um_nom', 'temp_7_3um_nom', 'temp_8_5um_nom', 'temp_9_7um_nom']
+l2_params = ['cloud_fraction', 'cld_temp_acha', 'cld_press_acha', 'cld_opd_acha', 'cld_reff_acha']
+
+# -- Zero out params (Experimentation Only) ------------
+zero_out_params = ['cld_reff_dcomp', 'cld_opd_dcomp', 'iwc_dcomp', 'lwc_dcomp']
+DO_ZERO_OUT = False
+
+label_idx = 1
+label_param = l2_params[label_idx]
+
+
+def build_conv2d_block(conv, num_filters, activation, block_name, padding='SAME'):
+ with tf.name_scope(block_name):
+ skip = conv
+
+ conv = tf.keras.layers.Conv2D(num_filters, kernel_size=5, strides=1, padding=padding, activation=activation)(conv)
+ conv = tf.keras.layers.MaxPool2D(padding=padding)(conv)
+ conv = tf.keras.layers.BatchNormalization()(conv)
+ print(conv.shape)
+
+ skip = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, padding=padding, activation=None)(skip)
+ skip = tf.keras.layers.MaxPool2D(padding=padding)(skip)
+ skip = tf.keras.layers.BatchNormalization()(skip)
+
+ conv = conv + skip
+ conv = tf.keras.layers.LeakyReLU()(conv)
+ print(conv.shape)
+
+ return conv
+
+
+def build_residual_block_1x1(input_layer, num_filters, activation, block_name, padding='SAME', drop_rate=0.5,
+ do_drop_out=True, do_batch_norm=True):
+
+ with tf.name_scope(block_name):
+ skip = input_layer
+ if do_drop_out:
+ input_layer = tf.keras.layers.Dropout(drop_rate)(input_layer)
+ if do_batch_norm:
+ input_layer = tf.keras.layers.BatchNormalization()(input_layer)
+ conv = tf.keras.layers.Conv2D(num_filters, kernel_size=1, strides=1, padding=padding, activation=activation)(input_layer)
+ print(conv.shape)
+
+ # if do_drop_out:
+ # conv = tf.keras.layers.Dropout(drop_rate)(conv)
+ # if do_batch_norm:
+ # conv = tf.keras.layers.BatchNormalization()(conv)
+ # conv = tf.keras.layers.Conv2D(num_filters, kernel_size=1, strides=1, padding=padding, activation=activation)(conv)
+ # print(conv.shape)
+
+ if do_drop_out:
+ conv = tf.keras.layers.Dropout(drop_rate)(conv)
+ if do_batch_norm:
+ conv = tf.keras.layers.BatchNormalization()(conv)
+ conv = tf.keras.layers.Conv2D(num_filters, kernel_size=1, strides=1, padding=padding, activation=None)(conv)
+
+ conv = conv + skip
+ conv = tf.keras.layers.LeakyReLU()(conv)
+ print(conv.shape)
+
+ return conv
+
+
+class ESPCN:
+
+ def __init__(self):
+
+ self.train_data = None
+ self.train_label = None
+ self.test_data = None
+ self.test_label = None
+ self.test_data_denorm = None
+
+ self.train_dataset = None
+ self.inner_train_dataset = None
+ self.test_dataset = None
+ self.eval_dataset = None
+ self.X_img = None
+ self.X_prof = None
+ self.X_u = None
+ self.X_v = None
+ self.X_sfc = None
+ self.inputs = []
+ self.y = None
+ self.handle = None
+ self.inner_handle = None
+ self.in_mem_batch = None
+
+ self.h5f_l1b_trn = None
+ self.h5f_l1b_tst = None
+ self.h5f_l2_trn = None
+ self.h5f_l2_tst = None
+
+ self.logits = None
+
+ self.predict_data = None
+ self.predict_dataset = None
+ self.mean_list = None
+ self.std_list = None
+
+ self.training_op = None
+ self.correct = None
+ self.accuracy = None
+ self.loss = None
+ self.pred_class = None
+ self.variable_averages = None
+
+ self.global_step = None
+
+ self.writer_train = None
+ self.writer_valid = None
+ self.writer_train_valid_loss = None
+
+ self.OUT_OF_RANGE = False
+
+ self.abi = None
+ self.temp = None
+ self.wv = None
+ self.lbfp = None
+ self.sfc = None
+
+ self.in_mem_data_cache = {}
+ self.in_mem_data_cache_test = {}
+
+ self.model = None
+ self.optimizer = None
+ self.ema = None
+ self.train_loss = None
+ self.train_accuracy = None
+ self.test_loss = None
+ self.test_accuracy = None
+ self.test_auc = None
+ self.test_recall = None
+ self.test_precision = None
+ self.test_confusion_matrix = None
+ self.test_true_pos = None
+ self.test_true_neg = None
+ self.test_false_pos = None
+ self.test_false_neg = None
+
+ self.test_labels = []
+ self.test_preds = []
+ self.test_probs = None
+
+ self.learningRateSchedule = None
+ self.num_data_samples = None
+ self.initial_learning_rate = None
+
+ self.data_dct = None
+ self.train_data_files = None
+ self.train_label_files = None
+ self.test_data_files = None
+ self.test_label_files = None
+
+ self.train_data_nda = None
+ self.train_label_nda = None
+ self.test_data_nda = None
+ self.test_label_nda = None
+
+ self.n_chans = 1
+
+ self.X_img = tf.keras.Input(shape=(None, None, self.n_chans))
+ # self.X_img = tf.keras.Input(shape=(30, 30, self.n_chans))
+
+ self.inputs.append(self.X_img)
+ self.inputs.append(tf.keras.Input(shape=(None, None, self.n_chans)))
+ # self.inputs.append(tf.keras.Input(shape=(30, 30, self.n_chans)))
+
+ self.DISK_CACHE = False
+
+ tf.debugging.set_log_device_placement(LOG_DEVICE_PLACEMENT)
+
+ def get_in_mem_data_batch(self, idxs, is_training):
+ if is_training:
+ data_files = self.train_data_files
+ label_files = self.train_label_files
+ else:
+ data_files = self.test_data_files
+ label_files = self.test_label_files
+
+ data_s = []
+ label_s = []
+ for k in idxs:
+ f = data_files[k]
+ nda = np.load(f)
+ data_s.append(nda)
+
+ f = label_files[k]
+ nda = np.load(f)
+ label_s.append(nda)
+
+ data = np.concatenate(data_s)
+ label = np.concatenate(label_s)
+
+ label = label[:, label_idx, :, :]
+ label = np.expand_dims(label, axis=3)
+
+ data = data.astype(np.float32)
+ label = label.astype(np.float32)
+
+ data_norm = []
+ for k, param in enumerate(emis_params):
+ tmp = normalize(data[:, k, :, :], param, mean_std_dct)
+ data_norm.append(tmp)
+ data = np.stack(data_norm, axis=3)
+
+ if label_param != 'cloud_fraction':
+ label = scale(label, label_param, mean_std_dct)
+
+ if is_training and DO_AUGMENT:
+ data_ud = np.flip(data, axis=1)
+ label_ud = np.flip(label, axis=1)
+
+ data_lr = np.flip(data, axis=2)
+ label_lr = np.flip(label, axis=2)
+
+ data = np.concatenate([data, data_ud, data_lr])
+ label = np.concatenate([label, label_ud, label_lr])
+
+ return data, data, label
+
+ def get_in_mem_data_batch_train(self, idxs):
+ return self.get_in_mem_data_batch(idxs, True)
+
+ def get_in_mem_data_batch_test(self, idxs):
+ return self.get_in_mem_data_batch(idxs, False)
+
+ def get_in_mem_data_batch_eval(self, idxs):
+ data = []
+ for param in self.train_params:
+ nda = self.data_dct[param]
+ nda = normalize(nda, param, mean_std_dct)
+ data.append(nda)
+ data = np.stack(data)
+ data = data.astype(np.float32)
+ data = np.transpose(data, axes=(1, 2, 0))
+ data = np.expand_dims(data, axis=0)
+
+ nda = np.zeros([1])
+ nda[0] = self.flight_level
+ nda = tf.one_hot(nda, 5).numpy()
+ nda = np.expand_dims(nda, axis=0)
+ nda = np.expand_dims(nda, axis=0)
+
+ return data, nda
+
+ @tf.function(input_signature=[tf.TensorSpec(None, tf.int32)])
+ def data_function(self, indexes):
+ out = tf.numpy_function(self.get_in_mem_data_batch_train, [indexes], [tf.float32, tf.float32, tf.float32])
+ return out
+
+ @tf.function(input_signature=[tf.TensorSpec(None, tf.int32)])
+ def data_function_test(self, indexes):
+ out = tf.numpy_function(self.get_in_mem_data_batch_test, [indexes], [tf.float32, tf.float32, tf.float32])
+ return out
+
+ @tf.function(input_signature=[tf.TensorSpec(None, tf.int32)])
+ def data_function_evaluate(self, indexes):
+ # TODO: modify for user specified altitude
+ out = tf.numpy_function(self.get_in_mem_data_batch_eval, [indexes], [tf.float32, tf.float32])
+ return out
+
+ def get_train_dataset(self, indexes):
+ indexes = list(indexes)
+
+ dataset = tf.data.Dataset.from_tensor_slices(indexes)
+ dataset = dataset.batch(PROC_BATCH_SIZE)
+ dataset = dataset.map(self.data_function, num_parallel_calls=8)
+ dataset = dataset.cache()
+ if DO_AUGMENT:
+ dataset = dataset.shuffle(PROC_BATCH_BUFFER_SIZE)
+ dataset = dataset.prefetch(buffer_size=1)
+ self.train_dataset = dataset
+
+ def get_test_dataset(self, indexes):
+ indexes = list(indexes)
+
+ dataset = tf.data.Dataset.from_tensor_slices(indexes)
+ dataset = dataset.batch(PROC_BATCH_SIZE)
+ dataset = dataset.map(self.data_function_test, num_parallel_calls=8)
+ dataset = dataset.cache()
+ self.test_dataset = dataset
+
+ def get_evaluate_dataset(self, indexes):
+ indexes = list(indexes)
+
+ dataset = tf.data.Dataset.from_tensor_slices(indexes)
+ dataset = dataset.map(self.data_function_evaluate, num_parallel_calls=8)
+ self.eval_dataset = dataset
+
+ def setup_pipeline(self, train_data_files, train_label_files, test_data_files, test_label_files, num_train_samples):
+
+ self.train_data_files = train_data_files
+ self.train_label_files = train_label_files
+ self.test_data_files = test_data_files
+ self.test_label_files = test_label_files
+
+ trn_idxs = np.arange(len(train_data_files))
+ np.random.shuffle(trn_idxs)
+ tst_idxs = np.arange(len(train_data_files))
+
+ self.get_train_dataset(trn_idxs)
+ self.get_test_dataset(tst_idxs)
+
+ self.num_data_samples = num_train_samples # approximately
+
+ print('datetime: ', now)
+ print('training and test data: ')
+ print('---------------------------')
+ print('num train samples: ', self.num_data_samples)
+ print('BATCH SIZE: ', BATCH_SIZE)
+ print('num test samples: ', tst_idxs.shape[0])
+ print('setup_pipeline: Done')
+
+ def setup_test_pipeline(self, filename_l1b, filename_l2, seed=None, shuffle=False):
+
+ if filename_l1b is not None:
+ self.h5f_l1b_tst = h5py.File(filename_l1b, 'r')
+ if filename_l2 is not None:
+ self.h5f_l2_tst = h5py.File(filename_l2, 'r')
+
+ if self.h5f_l1b_tst is not None:
+ h5f = self.h5f_l1b_tst
+ else:
+ h5f = self.h5f_l2_tst
+ time = h5f['time']
+ tst_idxs = np.arange(time.shape[0])
+ self.num_data_samples = len(tst_idxs)
+ if seed is not None:
+ np.random.seed(seed)
+ if shuffle:
+ np.random.shuffle(tst_idxs)
+
+ self.get_test_dataset(tst_idxs)
+
+ print('num test samples: ', tst_idxs.shape[0])
+ print('setup_test_pipeline: Done')
+
+ def setup_eval_pipeline(self, data_dct, num_tiles=1):
+ self.data_dct = data_dct
+ idxs = np.arange(num_tiles)
+ self.num_data_samples = idxs.shape[0]
+
+ self.get_evaluate_dataset(idxs)
+
+ def build_espcn(self):
+ print('build_cnn')
+ # padding = "VALID"
+ padding = "SAME"
+
+ # activation = tf.nn.relu
+ # activation = tf.nn.elu
+ activation = tf.nn.leaky_relu
+ momentum = 0.99
+
+ # num_filters = len(self.train_params) * 4
+ num_filters = self.n_chans * 64
+
+ input_2d = self.inputs[0]
+ print('input: ', input_2d.shape)
+ conv = tf.keras.layers.Conv2D(num_filters, kernel_size=5, strides=1, padding='VALID', activation=None)(input_2d)
+ conv = conv[:, 4:20, 4:20, :]
+ print('Contracting Branch')
+ print('input: ', conv.shape)
+ skip = conv
+
+ if NOISE_TRAINING:
+ conv = tf.keras.layers.GaussianNoise(stddev=NOISE_STDDEV)(conv)
+
+ conv = tf.keras.layers.Conv2D(num_filters, kernel_size=5, strides=1, padding=padding, activation=activation)(conv)
+ conv = tf.keras.layers.BatchNormalization()(conv)
+ print(conv.shape)
+
+ conv = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, padding=padding, activation=activation)(conv)
+ conv = tf.keras.layers.BatchNormalization()(conv)
+ print(conv.shape)
+
+ conv = tf.keras.layers.Conv2D(num_filters/2, kernel_size=3, strides=1, padding=padding, activation=None)(conv)
+ conv = tf.keras.layers.BatchNormalization()(conv)
+ print(conv.shape)
+
+ conv = conv + skip
+ conv = tf.keras.layers.LeakyReLU()(conv)
+ print(conv.shape)
+
+ conv = tf.keras.layers.Conv2D(4, kernel_size=3, strides=1, padding=padding, activation=activation)(conv)
+ print(conv.shape)
+
+ conv = tf.nn.depth_to_space(conv, block_size=2)
+ print(conv.shape)
+
+ if NumClasses == 2:
+ activation = tf.nn.sigmoid # For binary
+ else:
+ activation = tf.nn.softmax # For multi-class
+
+ # Called logits, but these are actually probabilities, see activation
+ self.logits = tf.keras.layers.Conv2D(1, kernel_size=1, strides=1, padding=padding, name='probability', activation=activation)(conv)
+
+ print(self.logits.shape)
+
+ def build_training(self):
+ # if NumClasses == 2:
+ # self.loss = tf.keras.losses.BinaryCrossentropy(from_logits=False) # for two-class only
+ # else:
+ # self.loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False) # For multi-class
+ self.loss = tf.keras.losses.MeanSquaredError() # Regression
+
+ # decayed_learning_rate = learning_rate * decay_rate ^ (global_step / decay_steps)
+ initial_learning_rate = 0.002
+ decay_rate = 0.95
+ steps_per_epoch = int(self.num_data_samples/BATCH_SIZE) # one epoch
+ decay_steps = int(steps_per_epoch / 2)
+ print('initial rate, decay rate, steps/epoch, decay steps: ', initial_learning_rate, decay_rate, steps_per_epoch, decay_steps)
+
+ self.learningRateSchedule = tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate, decay_steps, decay_rate)
+
+ optimizer = tf.keras.optimizers.Adam(learning_rate=self.learningRateSchedule)
+
+ if TRACK_MOVING_AVERAGE:
+ # Not really sure this works properly (from tfa)
+ # optimizer = tfa.optimizers.MovingAverage(optimizer)
+ self.ema = tf.train.ExponentialMovingAverage(decay=0.9999)
+
+ self.optimizer = optimizer
+ self.initial_learning_rate = initial_learning_rate
+
+ def build_evaluation(self):
+ #self.train_loss = tf.keras.metrics.Mean(name='train_loss')
+ #self.test_loss = tf.keras.metrics.Mean(name='test_loss')
+ self.train_accuracy = tf.keras.metrics.MeanAbsoluteError(name='train_accuracy')
+ self.test_accuracy = tf.keras.metrics.MeanAbsoluteError(name='test_accuracy')
+ self.train_loss = tf.keras.metrics.Mean(name='train_loss')
+ self.test_loss = tf.keras.metrics.Mean(name='test_loss')
+
+ # if NumClasses == 2:
+ # self.train_accuracy = tf.keras.metrics.BinaryAccuracy(name='train_accuracy')
+ # self.test_accuracy = tf.keras.metrics.BinaryAccuracy(name='test_accuracy')
+ # self.test_auc = tf.keras.metrics.AUC(name='test_auc')
+ # self.test_recall = tf.keras.metrics.Recall(name='test_recall')
+ # self.test_precision = tf.keras.metrics.Precision(name='test_precision')
+ # self.test_true_neg = tf.keras.metrics.TrueNegatives(name='test_true_neg')
+ # self.test_true_pos = tf.keras.metrics.TruePositives(name='test_true_pos')
+ # self.test_false_neg = tf.keras.metrics.FalseNegatives(name='test_false_neg')
+ # self.test_false_pos = tf.keras.metrics.FalsePositives(name='test_false_pos')
+ # else:
+ # self.train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')
+ # self.test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')
+
+ @tf.function
+ def train_step(self, mini_batch):
+ inputs = [mini_batch[0], mini_batch[1]]
+ labels = mini_batch[2]
+ with tf.GradientTape() as tape:
+ pred = self.model(inputs, training=True)
+ loss = self.loss(labels, pred)
+ total_loss = loss
+ if len(self.model.losses) > 0:
+ reg_loss = tf.math.add_n(self.model.losses)
+ total_loss = loss + reg_loss
+ gradients = tape.gradient(total_loss, self.model.trainable_variables)
+ self.optimizer.apply_gradients(zip(gradients, self.model.trainable_variables))
+ if TRACK_MOVING_AVERAGE:
+ self.ema.apply(self.model.trainable_variables)
+
+ self.train_loss(loss)
+ self.train_accuracy(labels, pred)
+
+ return loss
+
+ @tf.function
+ def test_step(self, mini_batch):
+ inputs = [mini_batch[0], mini_batch[1]]
+ labels = mini_batch[2]
+ pred = self.model(inputs, training=False)
+ t_loss = self.loss(labels, pred)
+
+ self.test_loss(t_loss)
+ self.test_accuracy(labels, pred)
+ # if NumClasses == 2:
+ # self.test_auc(labels, pred)
+ # self.test_recall(labels, pred)
+ # self.test_precision(labels, pred)
+ # self.test_true_neg(labels, pred)
+ # self.test_true_pos(labels, pred)
+ # self.test_false_neg(labels, pred)
+ # self.test_false_pos(labels, pred)
+
+ def predict(self, mini_batch):
+ inputs = [mini_batch[0], mini_batch[1]]
+ labels = mini_batch[2]
+ pred = self.model(inputs, training=False)
+ t_loss = self.loss(labels, pred)
+
+ self.test_labels.append(labels)
+ self.test_preds.append(pred.numpy())
+
+ self.test_loss(t_loss)
+ self.test_accuracy(labels, pred)
+ # if NumClasses == 2:
+ # self.test_auc(labels, pred)
+ # self.test_recall(labels, pred)
+ # self.test_precision(labels, pred)
+ # self.test_true_neg(labels, pred)
+ # self.test_true_pos(labels, pred)
+ # self.test_false_neg(labels, pred)
+ # self.test_false_pos(labels, pred)
+
+ def reset_test_metrics(self):
+ self.test_loss.reset_states()
+ self.test_accuracy.reset_states()
+ # if NumClasses == 2:
+ # self.test_auc.reset_states()
+ # self.test_recall.reset_states()
+ # self.test_precision.reset_states()
+ # self.test_true_neg.reset_states()
+ # self.test_true_pos.reset_states()
+ # self.test_false_neg.reset_states()
+ # self.test_false_pos.reset_states()
+
+ def get_metrics(self):
+ recall = self.test_recall.result()
+ precsn = self.test_precision.result()
+ f1 = 2 * (precsn * recall) / (precsn + recall)
+
+ tn = self.test_true_neg.result()
+ tp = self.test_true_pos.result()
+ fn = self.test_false_neg.result()
+ fp = self.test_false_pos.result()
+
+ mcc = ((tp * tn) - (fp * fn)) / np.sqrt((tp + fp) * (tp + fn) * (tn + fp) * (tn + fn))
+ return f1, mcc
+
+ def do_training(self, ckpt_dir=None):
+
+ if ckpt_dir is None:
+ if not os.path.exists(modeldir):
+ os.mkdir(modeldir)
+ ckpt = tf.train.Checkpoint(step=tf.Variable(1), model=self.model)
+ ckpt_manager = tf.train.CheckpointManager(ckpt, modeldir, max_to_keep=3)
+ else:
+ ckpt = tf.train.Checkpoint(step=tf.Variable(1), model=self.model)
+ ckpt_manager = tf.train.CheckpointManager(ckpt, ckpt_dir, max_to_keep=3)
+
+ self.writer_train = tf.summary.create_file_writer(os.path.join(logdir, 'plot_train'))
+ self.writer_valid = tf.summary.create_file_writer(os.path.join(logdir, 'plot_valid'))
+ self.writer_train_valid_loss = tf.summary.create_file_writer(os.path.join(logdir, 'plot_train_valid_loss'))
+
+ step = 0
+ total_time = 0
+ best_test_loss = np.finfo(dtype=np.float).max
+ best_test_acc = 0
+ best_test_recall = 0
+ best_test_precision = 0
+ best_test_auc = 0
+ best_test_f1 = 0
+ best_test_mcc = 0
+
+ if EARLY_STOP:
+ es = EarlyStop()
+
+ for epoch in range(NUM_EPOCHS):
+ self.train_loss.reset_states()
+ self.train_accuracy.reset_states()
+
+ t0 = datetime.datetime.now().timestamp()
+
+ proc_batch_cnt = 0
+ n_samples = 0
+
+ for data0, data1, label in self.train_dataset:
+ trn_ds = tf.data.Dataset.from_tensor_slices((data0, data1, label))
+ trn_ds = trn_ds.batch(BATCH_SIZE)
+ for mini_batch in trn_ds:
+ if self.learningRateSchedule is not None:
+ loss = self.train_step(mini_batch)
+
+ if (step % 100) == 0:
+
+ with self.writer_train.as_default():
+ tf.summary.scalar('loss_trn', loss.numpy(), step=step)
+ tf.summary.scalar('learning_rate', self.optimizer._decayed_lr('float32').numpy(), step=step)
+ tf.summary.scalar('num_train_steps', step, step=step)
+ tf.summary.scalar('num_epochs', epoch, step=step)
+
+ self.reset_test_metrics()
+ for data0_tst, data1_tst, label_tst in self.test_dataset:
+ tst_ds = tf.data.Dataset.from_tensor_slices((data0_tst, data1_tst, label_tst))
+ tst_ds = tst_ds.batch(BATCH_SIZE)
+ for mini_batch_test in tst_ds:
+ self.test_step(mini_batch_test)
+
+ # if NumClasses == 2:
+ # f1, mcc = self.get_metrics()
+
+ with self.writer_valid.as_default():
+ tf.summary.scalar('loss_val', self.test_loss.result(), step=step)
+ tf.summary.scalar('acc_val', self.test_accuracy.result(), step=step)
+ # if NumClasses == 2:
+ # tf.summary.scalar('auc_val', self.test_auc.result(), step=step)
+ # tf.summary.scalar('recall_val', self.test_recall.result(), step=step)
+ # tf.summary.scalar('prec_val', self.test_precision.result(), step=step)
+ # tf.summary.scalar('f1_val', f1, step=step)
+ # tf.summary.scalar('mcc_val', mcc, step=step)
+ # tf.summary.scalar('num_train_steps', step, step=step)
+ # tf.summary.scalar('num_epochs', epoch, step=step)
+
+ with self.writer_train_valid_loss.as_default():
+ tf.summary.scalar('loss_trn', loss.numpy(), step=step)
+ tf.summary.scalar('loss_val', self.test_loss.result(), step=step)
+
+ print('****** test loss, acc, lr: ', self.test_loss.result().numpy(), self.test_accuracy.result().numpy(),
+ self.optimizer._decayed_lr('float32').numpy())
+
+ step += 1
+ print('train loss: ', loss.numpy())
+
+ proc_batch_cnt += 1
+ n_samples += data0.shape[0]
+ print('proc_batch_cnt: ', proc_batch_cnt, n_samples)
+
+ t1 = datetime.datetime.now().timestamp()
+ print('End of Epoch: ', epoch+1, 'elapsed time: ', (t1-t0))
+ total_time += (t1-t0)
+
+ self.reset_test_metrics()
+ for data0, data1, label in self.test_dataset:
+ ds = tf.data.Dataset.from_tensor_slices((data0, data1, label))
+ ds = ds.batch(BATCH_SIZE)
+ for mini_batch in ds:
+ self.test_step(mini_batch)
+
+ print('loss, acc: ', self.test_loss.result().numpy(), self.test_accuracy.result().numpy())
+ # if NumClasses == 2:
+ # f1, mcc = self.get_metrics()
+ # print('loss, acc, recall, precision, auc, f1, mcc: ', self.test_loss.result().numpy(), self.test_accuracy.result().numpy(),
+ # self.test_recall.result().numpy(), self.test_precision.result().numpy(), self.test_auc.result().numpy(), f1.numpy(), mcc.numpy())
+ # else:
+ # print('loss, acc: ', self.test_loss.result().numpy(), self.test_accuracy.result().numpy())
+ print('------------------------------------------------------')
+
+ tst_loss = self.test_loss.result().numpy()
+ if tst_loss < best_test_loss:
+ best_test_loss = tst_loss
+ # if NumClasses == 2:
+ # best_test_acc = self.test_accuracy.result().numpy()
+ # best_test_recall = self.test_recall.result().numpy()
+ # best_test_precision = self.test_precision.result().numpy()
+ # best_test_auc = self.test_auc.result().numpy()
+ # best_test_f1 = f1.numpy()
+ # best_test_mcc = mcc.numpy()
+
+ ckpt_manager.save()
+
+ if self.DISK_CACHE and epoch == 0:
+ f = open(cachepath, 'wb')
+ pickle.dump(self.in_mem_data_cache, f)
+ f.close()
+
+ if EARLY_STOP and es.check_stop(tst_loss):
+ break
+
+ print('total time: ', total_time)
+ self.writer_train.close()
+ self.writer_valid.close()
+ self.writer_train_valid_loss.close()
+
+ if self.h5f_l1b_trn is not None:
+ self.h5f_l1b_trn.close()
+ if self.h5f_l1b_tst is not None:
+ self.h5f_l1b_tst.close()
+ if self.h5f_l2_trn is not None:
+ self.h5f_l2_trn.close()
+ if self.h5f_l2_tst is not None:
+ self.h5f_l2_tst.close()
+
+ # f = open(home_dir+'/best_stats_'+now+'.pkl', 'wb')
+ # pickle.dump((best_test_loss, best_test_acc, best_test_recall, best_test_precision, best_test_auc, best_test_f1, best_test_mcc), f)
+ # f.close()
+
+ def build_model(self):
+ self.build_espcn()
+ self.model = tf.keras.Model(self.inputs, self.logits)
+
+ def restore(self, ckpt_dir):
+
+ ckpt = tf.train.Checkpoint(step=tf.Variable(1), model=self.model)
+ ckpt_manager = tf.train.CheckpointManager(ckpt, ckpt_dir, max_to_keep=3)
+
+ ckpt.restore(ckpt_manager.latest_checkpoint)
+
+ self.reset_test_metrics()
+
+ for data0, data1, label in self.test_dataset:
+ ds = tf.data.Dataset.from_tensor_slices((data0, data1, label))
+ ds = ds.batch(BATCH_SIZE)
+ for mini_batch_test in ds:
+ self.predict(mini_batch_test)
+ f1, mcc = self.get_metrics()
+ print('loss, acc: ', self.test_loss.result().numpy(), self.test_accuracy.result().numpy(), self.test_recall.result().numpy(),
+ self.test_precision.result().numpy(), self.test_auc.result().numpy(), f1.numpy(), mcc.numpy())
+
+ labels = np.concatenate(self.test_labels)
+ self.test_labels = labels
+
+ preds = np.concatenate(self.test_preds)
+ self.test_probs = preds
+
+ if NumClasses == 2:
+ preds = np.where(preds > 0.5, 1, 0)
+ else:
+ preds = np.argmax(preds, axis=1)
+
+ self.test_preds = preds
+
+ def do_evaluate(self, prob_thresh=0.5):
+
+ self.reset_test_metrics()
+
+ pred_s = []
+
+ for data in self.eval_dataset:
+ print(data[0].shape, data[1].shape)
+ pred = self.model([data])
+ print(pred.shape, np.histogram(pred.numpy()))
+
+ preds = np.concatenate(pred_s)
+ preds = preds[:,0]
+ self.test_probs = preds
+
+ if NumClasses == 2:
+ preds = np.where(preds > prob_thresh, 1, 0)
+ else:
+ preds = np.argmax(preds, axis=1)
+ self.test_preds = preds
+
+ def run(self, directory):
+ train_data_files = glob.glob(directory+'data_train*.npy')
+ valid_data_files = glob.glob(directory+'data_valid*.npy')
+ train_label_files = glob.glob(directory+'label_train*.npy')
+ valid_label_files = glob.glob(directory+'label_valid*.npy')
+
+ train_data_files.sort()
+ valid_data_files.sort()
+ train_label_files.sort()
+ valid_label_files.sort()
+
+ self.setup_pipeline(train_data_files, train_label_files, valid_data_files, valid_label_files, 200000)
+ self.build_model()
+ self.build_training()
+ self.build_evaluation()
+ self.do_training()
+
+ def run_restore(self, filename_l1b, filename_l2, ckpt_dir):
+ self.setup_test_pipeline(filename_l1b, filename_l2)
+ self.build_model()
+ self.build_training()
+ self.build_evaluation()
+ self.restore(ckpt_dir)
+
+ if self.h5f_l1b_tst is not None:
+ self.h5f_l1b_tst.close()
+ if self.h5f_l2_tst is not None:
+ self.h5f_l2_tst.close()
+
+ def run_evaluate(self, filename, ckpt_dir):
+ data_dct, ll, cc = make_for_full_domain_predict(filename, name_list=self.train_params)
+ self.setup_eval_pipeline(data_dct, len(ll))
+ self.build_model()
+ self.build_training()
+ self.build_evaluation()
+ self.do_evaluate(ckpt_dir)
+
+
+if __name__ == "__main__":
+ nn = ESPCN()
+ nn.run('matchup_filename')