From 6bbbecdf71c35479849b445fa0f989c5aaa206b8 Mon Sep 17 00:00:00 2001
From: tomrink <rink@ssec.wisc.edu>
Date: Tue, 1 Nov 2022 13:37:01 -0500
Subject: [PATCH] snapshot...
---
modules/deeplearning/cnn_cld_frac.py | 829 +++++++++++++++++++++++++++
1 file changed, 829 insertions(+)
create mode 100644 modules/deeplearning/cnn_cld_frac.py
diff --git a/modules/deeplearning/cnn_cld_frac.py b/modules/deeplearning/cnn_cld_frac.py
new file mode 100644
index 00000000..9d3f2768
--- /dev/null
+++ b/modules/deeplearning/cnn_cld_frac.py
@@ -0,0 +1,829 @@
+import glob
+import tensorflow as tf
+from util.setup import logdir, modeldir, cachepath, now, ancillary_path
+from util.util import EarlyStop, normalize, denormalize, resample, resample_2d_linear, resample_one, resample_2d_linear_one, get_grid_values_all
+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 = 2
+PROC_BATCH_BUFFER_SIZE = 50000
+
+NumClasses = 5
+if NumClasses == 2:
+ NumLogits = 1
+else:
+ NumLogits = NumClasses
+
+BATCH_SIZE = 128
+NUM_EPOCHS = 60
+
+TRACK_MOVING_AVERAGE = False
+EARLY_STOP = True
+
+NOISE_TRAINING = True
+NOISE_STDDEV = 0.01
+DO_AUGMENT = True
+
+DO_ZERO_OUT = False
+
+# 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)
+
+# label_param = 'cloud_fraction'
+# label_param = 'cld_opd_dcomp'
+label_param = 'cloud_probability'
+
+params = ['temp_11_0um_nom', 'temp_12_0um_nom', 'refl_0_65um_nom', label_param]
+data_params = ['temp_11_0um_nom']
+
+label_idx = params.index(label_param)
+
+print('data_params: ', data_params)
+print('label_param: ', label_param)
+
+x_134 = np.arange(134)
+y_134 = np.arange(134)
+x_64 = np.arange(64)
+y_64 = np.arange(64)
+x_134_2 = x_134[3:131:2]
+y_134_2 = y_134[3:131:2]
+t = np.arange(0, 64, 0.5)
+s = np.arange(0, 64, 0.5)
+
+x_128_2 = x_134[3:131:2]
+y_128_2 = y_134[3:131:2]
+x_128 = x_134[3:131]
+y_128 = y_134[3:131]
+
+#----------- New
+# x_134_2 = x_134[1:134:2]
+# t = np.arange(1, 66, 0.5)
+#--------------------------
+
+
+def build_residual_conv2d_block(conv, num_filters, block_name, activation=tf.nn.relu, padding='SAME',
+ kernel_initializer='he_uniform', scale=None,
+ do_drop_out=True, drop_rate=0.5, do_batch_norm=False):
+
+ with tf.name_scope(block_name):
+ skip = tf.keras.layers.Conv2D(num_filters, kernel_size=3, padding=padding, kernel_initializer=kernel_initializer, activation=activation)(conv)
+ skip = tf.keras.layers.Conv2D(num_filters, kernel_size=3, padding=padding, activation=None)(skip)
+
+ if scale is not None:
+ skip = tf.keras.layers.Lambda(lambda x: x * scale)(skip)
+
+ if do_drop_out:
+ skip = tf.keras.layers.Dropout(drop_rate)(skip)
+
+ if do_batch_norm:
+ skip = tf.keras.layers.BatchNormalization()(skip)
+
+ conv = conv + skip
+ print(block_name+':', conv.shape)
+
+ return conv
+
+
+class CNN:
+
+ 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 = len(data_params) + 2
+
+ self.X_img = tf.keras.Input(shape=(None, None, self.n_chans))
+ # self.X_img = tf.keras.Input(shape=(36, 36, self.n_chans))
+ # self.X_img = tf.keras.Input(shape=(34, 34, self.n_chans))
+ # self.X_img = tf.keras.Input(shape=(66, 66, self.n_chans))
+
+ self.inputs.append(self.X_img)
+
+ tf.debugging.set_log_device_placement(LOG_DEVICE_PLACEMENT)
+
+ def get_in_mem_data_batch(self, idxs, is_training):
+ if is_training:
+ files = self.train_data_files
+ else:
+ files = self.test_data_files
+
+ data_s = []
+ for k in idxs:
+ f = files[k]
+ nda = np.load(f)
+ data_s.append(nda)
+ input_data = np.concatenate(data_s)
+
+ add_noise = None
+ noise_scale = None
+ if is_training and NOISE_TRAINING:
+ add_noise = True
+ noise_scale = NOISE_STDDEV
+
+ data_norm = []
+ for param in data_params:
+ idx = params.index(param)
+ tmp = input_data[:, idx, y_128_2, x_128_2]
+ tmp = normalize(tmp, param, mean_std_dct, add_noise=add_noise, noise_scale=noise_scale)
+ tmp = resample_2d_linear(x_64, y_64, tmp, t, s)
+ data_norm.append(tmp)
+ # --------------------------
+ param = 'refl_0_65um_nom'
+ idx = params.index(param)
+ tmp = input_data[:, idx, y_128_2, x_128_2]
+ tmp = normalize(tmp, param, mean_std_dct, add_noise=add_noise, noise_scale=noise_scale)
+ tmp = resample_2d_linear(x_64, y_64, tmp, t, s)
+ data_norm.append(tmp)
+ # --------
+ tmp = input_data[:, label_idx, y_128_2, x_128_2]
+ if label_param != 'cloud_fraction':
+ tmp = normalize(tmp, label_param, mean_std_dct, add_noise=add_noise, noise_scale=noise_scale)
+ else:
+ tmp = np.where(np.isnan(tmp), 0, tmp)
+ tmp = resample_2d_linear(x_64, y_64, tmp, t, s)
+ data_norm.append(tmp)
+ # ---------
+ data = np.stack(data_norm, axis=3)
+ data = data.astype(np.float32)
+ # -----------------------------------------------------
+ # -----------------------------------------------------
+ label = input_data[:, label_idx, y_128, x_128]
+ label = self.get_label_data(label)
+ label = np.expand_dims(label, axis=3)
+
+ data = data.astype(np.float32)
+ label = label.astype(np.int32)
+
+ 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, label
+
+ def get_label_data(self, grd_k):
+ num, leny, lenx = grd_k.shape
+ grd_down_2x = np.zeros((num, leny, lenx))
+ for t in range(len(num)):
+ for j in range(int(leny / 2)):
+ for i in range(int(lenx / 2)):
+ cell = grd_k[t, j:j + 2, i:i + 2]
+ if np.sum(np.isnan(cell)) == 0:
+ cnt = np.sum(cell[t, :, ] == 1.0)
+ if cnt == 0:
+ grd_down_2x[t, j, i] = 1
+ elif cnt == 1:
+ grd_down_2x[t, j, i] = 2
+ elif cnt == 2:
+ grd_down_2x[t, j, i] = 3
+ elif cnt == 3:
+ grd_down_2x[t, j, i] = 4
+ elif cnt == 4:
+ grd_down_2x[t, j, i] = 5
+ pass
+ else:
+ grd_down_2x[t, j, i] = 0
+
+ return grd_down_2x
+
+ 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)
+
+ return data
+
+ @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])
+ 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])
+ 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])
+ 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, test_data_files, num_train_samples):
+
+ self.train_data_files = train_data_files
+ self.test_data_files = test_data_files
+
+ trn_idxs = np.arange(len(train_data_files))
+ np.random.shuffle(trn_idxs)
+ tst_idxs = np.arange(len(test_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, test_data_files):
+ self.test_data_files = test_data_files
+ tst_idxs = np.arange(len(test_data_files))
+ self.get_test_dataset(tst_idxs)
+ print('setup_test_pipeline: Done')
+
+ def setup_eval_pipeline(self, filename):
+ idxs = [0]
+ self.num_data_samples = idxs.shape[0]
+
+ self.get_evaluate_dataset(idxs)
+
+ def build_srcnn(self, do_drop_out=False, do_batch_norm=False, drop_rate=0.5, factor=2):
+ print('build_cnn')
+ padding = "SAME"
+
+ # activation = tf.nn.relu
+ # activation = tf.nn.elu
+ activation = tf.nn.relu
+ momentum = 0.99
+
+ num_filters = 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 = input_2d
+ print('input: ', conv.shape)
+
+ conv = conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, kernel_initializer='he_uniform', activation=activation, padding='SAME')(input_2d)
+ print(conv.shape)
+
+ if NOISE_TRAINING:
+ conv = conv_b = tf.keras.layers.GaussianNoise(stddev=NOISE_STDDEV)(conv)
+
+ scale = 0.2
+
+ conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_1', scale=scale)
+
+ conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_2', scale=scale)
+
+ conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_3', scale=scale)
+
+ # conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_4', scale=scale)
+
+ # conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_5', scale=scale)
+
+ conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, kernel_initializer='he_uniform', padding=padding)(conv_b)
+
+ conv = conv + conv_b
+ print(conv.shape)
+
+ self.logits = tf.keras.layers.Conv2D(1, kernel_size=3, strides=1, padding=padding, name='regression')(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.MeanAbsoluteError() # Regression
+ # 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)
+ 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_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')
+
+ @tf.function
+ def train_step(self, mini_batch):
+ inputs = [mini_batch[0]]
+ labels = mini_batch[1]
+ 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]]
+ labels = mini_batch[1]
+ pred = self.model(inputs, training=False)
+ t_loss = self.loss(labels, pred)
+
+ self.test_loss(t_loss)
+ self.test_accuracy(labels, pred)
+
+ def predict(self, mini_batch):
+ inputs = [mini_batch[0]]
+ labels = mini_batch[1]
+ 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)
+
+ def reset_test_metrics(self):
+ self.test_loss.reset_states()
+ self.test_accuracy.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)
+ ckpt.restore(ckpt_manager.latest_checkpoint)
+
+ 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
+
+ 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 data, label in self.train_dataset:
+ trn_ds = tf.data.Dataset.from_tensor_slices((data, 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 data_tst, label_tst in self.test_dataset:
+ tst_ds = tf.data.Dataset.from_tensor_slices((data_tst, label_tst))
+ tst_ds = tst_ds.batch(BATCH_SIZE)
+ for mini_batch_test in tst_ds:
+ self.test_step(mini_batch_test)
+
+ 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)
+
+ 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 += data.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 data, label in self.test_dataset:
+ ds = tf.data.Dataset.from_tensor_slices((data, 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())
+ print('------------------------------------------------------')
+
+ tst_loss = self.test_loss.result().numpy()
+ if tst_loss < best_test_loss:
+ best_test_loss = tst_loss
+ ckpt_manager.save()
+
+ 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()
+
+ # 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_srcnn()
+ 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 data, label in self.test_dataset:
+ ds = tf.data.Dataset.from_tensor_slices((data, label))
+ ds = ds.batch(BATCH_SIZE)
+ for mini_batch_test in ds:
+ self.predict(mini_batch_test)
+
+ print('loss, acc: ', self.test_loss.result().numpy(), self.test_accuracy.result().numpy())
+
+ def do_evaluate(self, data, 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()
+
+ pred = self.model([data], training=False)
+ self.test_probs = pred
+ pred = pred.numpy()
+
+ return pred
+
+ def run(self, directory, ckpt_dir=None, num_data_samples=50000):
+ train_data_files = glob.glob(directory+'data_train_*.npy')
+ valid_data_files = glob.glob(directory+'data_valid_*.npy')
+ train_data_files = train_data_files[::2]
+ valid_data_files = valid_data_files[::2]
+
+ self.setup_pipeline(train_data_files, valid_data_files, num_data_samples)
+ self.build_model()
+ self.build_training()
+ self.build_evaluation()
+ self.do_training(ckpt_dir=ckpt_dir)
+
+ def run_restore(self, directory, ckpt_dir):
+ valid_data_files = glob.glob(directory + 'data_*.npy')
+ self.num_data_samples = 1000
+ self.setup_test_pipeline(valid_data_files)
+ self.build_model()
+ self.build_training()
+ self.build_evaluation()
+ self.restore(ckpt_dir)
+
+ def run_evaluate(self, data, ckpt_dir):
+ self.num_data_samples = 80000
+ self.build_model()
+ self.build_training()
+ self.build_evaluation()
+ return self.do_evaluate(data, ckpt_dir)
+
+
+def run_restore_static(directory, ckpt_dir):
+ nn = CNN()
+ nn.run_restore(directory, ckpt_dir)
+
+
+def run_evaluate_static(in_file, out_file, ckpt_dir):
+ h5f = h5py.File(in_file, 'r')
+ grd_a = get_grid_values_all(h5f, 'temp_11_0um_nom')
+ grd_a = grd_a[2432:4032, 2432:4032]
+ grd_a = grd_a[::2, ::2]
+
+ grd_b = get_grid_values_all(h5f, 'refl_0_65um_nom')
+ grd_b = grd_b[2432:4032, 2432:4032]
+
+ grd_c = get_grid_values_all(h5f, label_param)
+ grd_c = grd_c[2432:4032, 2432:4032]
+ grd_c = grd_c[::2, ::2]
+
+ leny, lenx = grd_a.shape
+ x = np.arange(lenx)
+ y = np.arange(leny)
+ x_up = np.arange(0, lenx, 0.5)
+ y_up = np.arange(0, leny, 0.5)
+
+ grd_a = normalize(grd_a, 'temp_11_0um_nom', mean_std_dct)
+ grd_a = resample_2d_linear_one(x, y, grd_a, x_up, y_up)
+
+ grd_b = normalize(grd_b, 'refl_0_65um_nom', mean_std_dct)
+
+ if label_param == 'cloud_fraction':
+ grd_c = np.where(np.isnan(grd_c), 0, grd_c)
+ else:
+ grd_c = normalize(grd_c, label_param, mean_std_dct)
+ grd_c = resample_2d_linear_one(x, y, grd_c, x_up, y_up)
+
+ data = np.stack([grd_a, grd_b, grd_c], axis=2)
+ data = np.expand_dims(data, axis=0)
+
+ nn = CNN()
+ out_sr = nn.run_evaluate(data, ckpt_dir)
+ if label_param != 'cloud_fraction':
+ out_sr = denormalize(out_sr, label_param, mean_std_dct)
+ if out_file is not None:
+ np.save(out_file, out_sr)
+ else:
+ return out_sr
+
+
+def run_evaluate_static_2(in_file, out_file, ckpt_dir):
+ nda = np.load(in_file)
+ grd_a = nda[:, 0, :, :]
+ grd_a = grd_a[:, 3:131:2, 3:131:2]
+
+ grd_b = nda[:, 2, 3:131, 3:131]
+
+ grd_c = nda[:, 3, :, :]
+ grd_c = grd_c[:, 3:131:2, 3:131:2]
+
+ num, leny, lenx = grd_a.shape
+ x = np.arange(lenx)
+ y = np.arange(leny)
+ x_up = np.arange(0, lenx, 0.5)
+ y_up = np.arange(0, leny, 0.5)
+
+ grd_a = normalize(grd_a, 'temp_11_0um_nom', mean_std_dct)
+ grd_a = resample_2d_linear(x, y, grd_a, x_up, y_up)
+
+ grd_b = normalize(grd_b, 'refl_0_65um_nom', mean_std_dct)
+
+ if label_param == 'cloud_fraction':
+ grd_c = np.where(np.isnan(grd_c), 0, grd_c)
+ else:
+ grd_c = normalize(grd_c, label_param, mean_std_dct)
+ grd_c = resample_2d_linear(x, y, grd_c, x_up, y_up)
+
+ data = np.stack([grd_a, grd_b, grd_c], axis=3)
+ print(data.shape)
+
+ nn = CNN()
+ out_sr = nn.run_evaluate(data, ckpt_dir)
+ if label_param != 'cloud_fraction':
+ # out_sr = denormalize(out_sr, label_param, mean_std_dct)
+ pass
+ if out_file is not None:
+ np.save(out_file, out_sr)
+ else:
+ return out_sr
+
+
+def analyze(fpath='/Users/tomrink/clavrx_snpp_viirs.A2019080.0100.001.2019080064252.uwssec_B00038315.level2.h5', param='cloud_fraction'):
+ h5f = h5py.File(fpath, 'r')
+ grd = get_grid_values_all(h5f, param)
+ grd = np.where(np.isnan(grd), 0, grd)
+ bt = get_grid_values_all(h5f, 'temp_11_0um_nom')
+ refl = get_grid_values_all(h5f, 'refl_0_65um_nom')
+ grd = grd[2432:4032, 2432:4032]
+ bt = bt[2432:4032, 2432:4032]
+ refl = refl[2432:4032, 2432:4032]
+ print(grd.shape)
+
+ grd_lr = grd[::2, ::2]
+ print(grd_lr.shape)
+ leny, lenx = grd_lr.shape
+ rnd = np.random.normal(loc=0, scale=0.001, size=grd_lr.size)
+ grd_lr = grd_lr + rnd.reshape(grd_lr.shape)
+ if param == 'cloud_fraction':
+ grd_lr = np.where(grd_lr < 0, 0, grd_lr)
+ grd_lr = np.where(grd_lr > 1, 1, grd_lr)
+
+ x = np.arange(lenx)
+ y = np.arange(leny)
+ x_up = np.arange(0, lenx, 0.5)
+ y_up = np.arange(0, leny, 0.5)
+
+ grd_hr = resample_2d_linear_one(x, y, grd_lr, x_up, y_up)
+ print(grd_hr.shape)
+
+ h5f.close()
+
+ return grd, grd_lr, grd_hr, bt, refl
+
+
+if __name__ == "__main__":
+ nn = CNN()
+ nn.run('matchup_filename')
--
GitLab