srcnn.py 23.36 KiB
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_one, resample_2d_linear, 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 = 2
if NumClasses == 2:
NumLogits = 1
else:
NumLogits = NumClasses
BATCH_SIZE = 128
NUM_EPOCHS = 80
TRACK_MOVING_AVERAGE = False
EARLY_STOP = True
NOISE_TRAINING = False
NOISE_STDDEV = 0.10
DO_AUGMENT = True
# 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']
data_params = ['temp_11_0um_nom', 'temp_12_0um_nom', 'cloud_fraction']
label_params = ['temp_11_0um_nom', 'temp_12_0um_nom', 'cloud_fraction']
DO_ZERO_OUT = False
data_idx, label_idx = 0, 0
data_param = data_params[data_idx]
label_param = label_params[label_idx]
print(data_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]
#x_134_2 = x_134[2:133:2]
#y_134_2 = y_134[2:133:2]
t = np.arange(0, 64, 0.5)
s = np.arange(0, 64, 0.5)
def build_residual_conv2d_block(conv, num_filters, block_name, activation=tf.nn.relu, padding='SAME', kernel_initializer='he_uniform', scale=None):
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)
conv = conv + skip
print(block_name+':', conv.shape)
return conv
class SRCNN:
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=(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
label_s = []
for k in idxs:
f = files[k]
nda = np.load(f)
label_s.append(nda)
data = np.concatenate(label_s)
label = data.copy()
data = data[:, data_idx, 3:131:2, 3:131:2]
data = resample(y_64, x_64, data, s, t)
data = np.expand_dims(data, axis=3)
# label = label[:, label_idx, 3:131:2, 3:131:2]
label = label[:, label_idx, 3:131, 3:131]
label = np.expand_dims(label, axis=3)
data = data.astype(np.float32)
label = label.astype(np.float32)
if data_param != 'cloud_fraction':
data = normalize(data, data_param, mean_std_dct, add_noise=True, noise_scale=0.005)
if label_param != 'cloud_fraction':
label = normalize(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, 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)
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, padding=padding)(input_2d)
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.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_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)
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)
# 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)
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, nda_lr, param, 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)
data = normalize(nda_lr, param, mean_std_dct)
data = np.expand_dims(data, axis=0)
data = np.expand_dims(data, axis=3)
self.reset_test_metrics()
pred = self.model([data], training=False)
self.test_probs = pred
pred = pred.numpy()
return denormalize(pred, param, mean_std_dct)
def run(self, directory):
train_data_files = glob.glob(directory+'data_train*.npy')
valid_data_files = glob.glob(directory+'data_valid*.npy')
self.setup_pipeline(train_data_files, valid_data_files, 50000)
self.build_model()
self.build_training()
self.build_evaluation()
self.do_training()
def run_restore(self, directory, ckpt_dir):
valid_data_files = glob.glob(directory + 'data_valid*.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, nda_lr, param, ckpt_dir):
self.num_data_samples = 80000
self.build_model()
self.build_training()
self.build_evaluation()
return self.do_evaluate(nda_lr, param, ckpt_dir)
def run_evaluate_static(in_file, out_file, ckpt_dir):
nda = np.load(in_file)
nda = nda[:, data_idx, 3:131:2, 3:131:2]
nda = resample(y_64, x_64, nda, s, t)
nda = np.expand_dims(nda, axis=3)
nn = SRCNN()
out_sr = nn.run_evaluate(nda, data_param, ckpt_dir)
if out_file is not None:
np.save(out_file, out_sr)
else:
return out_sr
def run_evaluate_static_new(in_file, out_file, ckpt_dir):
h5f = h5py.File(in_file, 'r')
grd = get_grid_values_all(h5f, data_param)
grd = grd[::2, ::2]
leny, lenx = grd.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 = resample_one(y, x, grd, y_up, x_up)
nn = SRCNN()
out_sr = nn.run_evaluate(grd, data_param, ckpt_dir)
if out_file is not None:
np.save(out_file, out_sr)
else:
return out_sr
if __name__ == "__main__":
nn = SRCNN()
nn.run('matchup_filename')