srcnn_l1b_l2.py 29.97 KiB
import glob
import tensorflow as tf
import util.util
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, add_noise, smooth_2d, smooth_2d_single, median_filter_2d,\
median_filter_2d_single, downscale_2x
import os, datetime
import numpy as np
import pickle
import h5py
from scipy.ndimage import gaussian_filter
# 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 = 4
PROC_BATCH_BUFFER_SIZE = 5000
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 = 0.01
DO_AUGMENT = False
DO_SMOOTH = False
SIGMA = 1.0
DO_ZERO_OUT = False
DO_ESPCN = False # Note: If True, cannot do mixed resolution input fields (Adjust accordingly below)
# 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)
IMG_DEPTH = 1
# label_param = 'cloud_fraction'
label_param = 'cld_opd_dcomp'
# label_param = 'cloud_probability'
params = ['temp_11_0um_nom', 'refl_0_65um_nom', label_param]
data_params_half = ['temp_11_0um_nom']
data_params_full = ['refl_0_65um_nom']
label_idx = params.index(label_param)
print('data_params_half: ', data_params_half)
print('data_params_full: ', data_params_full)
print('label_param: ', label_param)
KERNEL_SIZE = 3 # target size: (128, 128)
N = 1
if KERNEL_SIZE == 3:
slc_x = slice(2, N*128 + 4)
slc_y = slice(2, N*128 + 4)
slc_x_2 = slice(1, N*128 + 6, 2)
slc_y_2 = slice(1, N*128 + 6, 2)
x_2 = np.arange(int((N*128)/2) + 3)
y_2 = np.arange(int((N*128)/2) + 3)
t = np.arange(0, int((N*128)/2) + 3, 0.5)
s = np.arange(0, int((N*128)/2) + 3, 0.5)
x_k = slice(1, N*128 + 3)
y_k = slice(1, N*128 + 3)
x_128 = slice(3, N*128 + 3)
y_128 = slice(3, N*128 + 3)
elif KERNEL_SIZE == 5:
slc_x = slice(3, 135)
slc_y = slice(3, 135)
slc_x_2 = slice(2, 137, 2)
slc_y_2 = slice(2, 137, 2)
x_128 = slice(5, 133)
y_128 = slice(5, 133)
t = np.arange(1, 67, 0.5)
s = np.arange(1, 67, 0.5)
x_2 = np.arange(68)
y_2 = np.arange(68)
# ----------------------------------------
# Exp for ESPCN version
if DO_ESPCN:
slc_x_2 = slice(0, 132, 2)
slc_y_2 = slice(0, 132, 2)
x_128 = slice(2, 130)
y_128 = slice(2, 130)
def build_residual_conv2d_block(conv, num_filters, block_name, activation=tf.nn.relu, padding='SAME',
kernel_initializer='he_uniform', scale=None, kernel_size=3,
do_drop_out=True, drop_rate=0.5, do_batch_norm=True):
with tf.name_scope(block_name):
skip = tf.keras.layers.Conv2D(num_filters, kernel_size=kernel_size, padding=padding, kernel_initializer=kernel_initializer, activation=activation)(conv)
skip = tf.keras.layers.Conv2D(num_filters, kernel_size=kernel_size, 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
def upsample(tmp):
tmp = tmp[:, slc_y_2, slc_x_2]
tmp = resample_2d_linear(x_2, y_2, tmp, t, s)
tmp = tmp[:, y_k, x_k]
return tmp
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 = len(data_params_half) + len(data_params_full) + 1
self.X_img = tf.keras.Input(shape=(None, None, 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]
try:
nda = np.load(f)
except Exception:
print(f)
continue
data_s.append(nda)
input_data = np.concatenate(data_s)
DO_ADD_NOISE = False
if is_training and NOISE_TRAINING:
DO_ADD_NOISE = True
data_norm = []
for param in data_params_half:
idx = params.index(param)
tmp = input_data[:, idx, :, :]
tmp = np.where(np.isnan(tmp), 0, tmp)
if DO_ESPCN:
tmp = tmp[:, slc_y_2, slc_x_2]
else: # Half res upsampled to full res:
tmp = upsample(tmp)
tmp = normalize(tmp, param, mean_std_dct)
if DO_ADD_NOISE:
tmp = add_noise(tmp, noise_scale=NOISE_STDDEV)
data_norm.append(tmp)
for param in data_params_full:
idx = params.index(param)
tmp = input_data[:, idx, :, :]
tmp = np.where(np.isnan(tmp), 0, tmp)
# Full res:
tmp = tmp[:, slc_y, slc_x]
tmp = normalize(tmp, param, mean_std_dct)
if DO_ADD_NOISE:
tmp = add_noise(tmp, noise_scale=NOISE_STDDEV)
data_norm.append(tmp)
# ---------------------------------------------------
tmp = input_data[:, label_idx, :, :]
tmp = np.where(np.isnan(tmp), 0, tmp)
if DO_SMOOTH:
tmp = smooth_2d(tmp, sigma=SIGMA)
# tmp = median_filter_2d(tmp)
if DO_ESPCN:
tmp = tmp[:, slc_y_2, slc_x_2]
else: # Half res upsampled to full res:
tmp = upsample(tmp)
if label_param != 'cloud_probability':
tmp = normalize(tmp, label_param, mean_std_dct)
if DO_ADD_NOISE:
tmp = add_noise(tmp, noise_scale=NOISE_STDDEV)
else:
if DO_ADD_NOISE:
tmp = add_noise(tmp, noise_scale=NOISE_STDDEV)
tmp = np.where(tmp < 0.0, 0.0, tmp)
tmp = np.where(tmp > 1.0, 1.0, tmp)
data_norm.append(tmp)
# ---------
data = np.stack(data_norm, axis=3)
data = data.astype(np.float32)
# -----------------------------------------------------
# -----------------------------------------------------
label = input_data[:, label_idx, :, :]
if DO_SMOOTH:
label = np.where(np.isnan(label), 0, label)
label = smooth_2d(label, sigma=SIGMA)
# label = median_filter_2d(label)
label = label[:, y_128, x_128]
if label_param != 'cloud_probability':
label = normalize(label, label_param, mean_std_dct)
else:
label = np.where(np.isnan(label), 0, label)
label = np.expand_dims(label, axis=3)
data = data.astype(np.float32)
label = label.astype(np.float32)
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)
@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
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 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 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 = conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=KERNEL_SIZE, kernel_initializer='he_uniform', activation=activation, padding='VALID')(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', kernel_size=KERNEL_SIZE, scale=scale)
conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_2', kernel_size=KERNEL_SIZE, scale=scale)
conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_3', kernel_size=KERNEL_SIZE, scale=scale)
conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_4', kernel_size=KERNEL_SIZE, scale=scale)
conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_5', kernel_size=KERNEL_SIZE, scale=scale)
conv_b = build_residual_conv2d_block(conv_b, num_filters, 'Residual_Block_6', kernel_size=KERNEL_SIZE, scale=scale)
conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, activation=activation, kernel_initializer='he_uniform', padding=padding)(conv_b)
conv = conv + conv_b
print(conv.shape)
if not DO_ESPCN:
# This is effectively a Dense layer
self.logits = tf.keras.layers.Conv2D(1, kernel_size=1, strides=1, padding=padding, name='regression')(conv)
else:
conv = tf.keras.layers.Conv2D(num_filters * (factor ** 2), 3, padding=padding, activation=activation)(conv)
print(conv.shape)
conv = tf.nn.depth_to_space(conv, factor)
print(conv.shape)
self.logits = tf.keras.layers.Conv2D(IMG_DEPTH, 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) * 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)
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()
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())
labels = np.concatenate(self.test_labels)
preds = np.concatenate(self.test_preds)
print(labels.shape, preds.shape)
labels_denorm = denormalize(labels, label_param, mean_std_dct)
preds_denorm = denormalize(preds, label_param, mean_std_dct)
return labels_denorm, preds_denorm
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()
if label_param != 'cloud_probability':
pred = denormalize(pred, label_param, mean_std_dct)
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')
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_valid*.npy')
self.num_data_samples = 1000
self.setup_test_pipeline(valid_data_files)
self.build_model()
self.build_training()
self.build_evaluation()
return self.restore(ckpt_dir)
def run_evaluate(self, data, ckpt_dir):
data = tf.convert_to_tensor(data, dtype=tf.float32)
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, out_file=None):
nn = SRCNN()
labels_denorm, preds_denorm = nn.run_restore(directory, ckpt_dir)
if out_file is not None:
np.save(out_file, [labels_denorm, preds_denorm])
def run_evaluate_static(in_file, out_file, ckpt_dir):
N = 10
slc_x = slice(2, N*128 + 4)
slc_y = slice(2, N*128 + 4)
slc_x_2 = slice(1, N*128 + 6, 2)
slc_y_2 = slice(1, N*128 + 6, 2)
x_2 = np.arange(int((N*128)/2) + 3)
y_2 = np.arange(int((N*128)/2) + 3)
t = np.arange(0, int((N*128)/2) + 3, 0.5)
s = np.arange(0, int((N*128)/2) + 3, 0.5)
x_k = slice(1, N*128 + 3)
y_k = slice(1, N*128 + 3)
x_128 = slice(3, N*128 + 3)
y_128 = slice(3, N*128 + 3)
sub_y, sub_x = (N * 128) + 10, (N * 128) + 10
y_0, x_0, = 3232 - int(sub_y/2), 3200 - int(sub_x/2)
h5f = h5py.File(in_file, 'r')
grd_a = get_grid_values_all(h5f, 'temp_11_0um_nom')
grd_a = grd_a[y_0:y_0+sub_y, x_0:x_0+sub_x]
grd_a = grd_a.copy()
grd_a = np.where(np.isnan(grd_a), 0, grd_a)
hr_grd_a = grd_a.copy()
hr_grd_a = hr_grd_a[y_128, x_128]
# Full res:
# grd_a = grd_a[slc_y, slc_x]
# Half res:
grd_a = grd_a[slc_y_2, slc_x_2]
grd_a = resample_2d_linear_one(x_2, y_2, grd_a, t, s)
grd_a = grd_a[y_k, x_k]
grd_a = normalize(grd_a, 'temp_11_0um_nom', mean_std_dct)
# ------------------------------------------------------
grd_b = get_grid_values_all(h5f, 'refl_0_65um_nom')
grd_b = grd_b[y_0:y_0+sub_y, x_0:x_0+sub_x]
grd_b = grd_b.copy()
grd_b = np.where(np.isnan(grd_b), 0, grd_b)
hr_grd_b = grd_b.copy()
hr_grd_b = hr_grd_b[y_128, x_128]
grd_b = grd_b[slc_y, slc_x]
grd_b = normalize(grd_b, 'refl_0_65um_nom', mean_std_dct)
grd_c = get_grid_values_all(h5f, label_param)
grd_c = grd_c[y_0:y_0+sub_y, x_0:x_0+sub_x]
hr_grd_c = grd_c.copy()
hr_grd_c = np.where(np.isnan(hr_grd_c), 0, grd_c)
hr_grd_c = hr_grd_c[y_128, x_128]
# hr_grd_c = smooth_2d_single(hr_grd_c, sigma=1.0)
grd_c = np.where(np.isnan(grd_c), 0, grd_c)
grd_c = grd_c.copy()
# grd_c = smooth_2d_single(grd_c, sigma=1.0)
grd_c = grd_c[slc_y_2, slc_x_2]
grd_c = resample_2d_linear_one(x_2, y_2, grd_c, t, s)
grd_c = grd_c[y_k, x_k]
if label_param != 'cloud_probability':
grd_c = normalize(grd_c, label_param, mean_std_dct)
data = np.stack([grd_a, grd_b, grd_c], axis=2)
data = np.expand_dims(data, axis=0)
h5f.close()
nn = SRCNN()
out_sr = nn.run_evaluate(data, ckpt_dir)
if out_file is not None:
np.save(out_file, (out_sr[0, :, :, 0], hr_grd_a, hr_grd_b, hr_grd_c))
else:
return out_sr, hr_grd_a, hr_grd_b, hr_grd_c
def analyze(file='/Users/tomrink/cld_opd_out.npy'):
# Save this:
# nn.test_data_files = glob.glob('/Users/tomrink/data/clavrx_opd_valid_DAY/data_valid*.npy')
# idxs = np.arange(50)
# dat, lbl = nn.get_in_mem_data_batch(idxs, False)
# tmp = dat[:, 1:128, 1:128, 1]
# tmp = dat[:, 1:129, 1:129, 1]
tup = np.load(file, allow_pickle=True)
lbls = tup[0]
pred = tup[1]
lbls = lbls[:, :, :, 0]
pred = pred[:, :, :, 0]
print('Total num pixels: ', lbls.size)
pred = pred.flatten()
pred = np.where(pred < 0.0, 0.0, pred)
lbls = lbls.flatten()
diff = pred - lbls
mae = (np.sum(np.abs(diff))) / diff.size
print('MAE: ', mae)
bin_edges = []
bin_ranges = []
# bin_ranges.append([0.0, 1.0])
# bin_edges.append(0.0)
bin_ranges.append([1.0, 5.0])
bin_edges.append(1.0)
bin_ranges.append([5.0, 10.0])
bin_edges.append(5.0)
bin_ranges.append([10.0, 15.0])
bin_edges.append(10.0)
bin_ranges.append([15.0, 20.0])
bin_edges.append(15.0)
bin_ranges.append([20.0, 30.0])
bin_edges.append(20.0)
bin_ranges.append([30.0, 40.0])
bin_edges.append(30.0)
bin_ranges.append([40.0, 60.0])
bin_edges.append(40.0)
bin_ranges.append([60.0, 80.0])
bin_edges.append(60.0)
bin_ranges.append([80.0, 100.0])
bin_edges.append(80.0)
bin_ranges.append([100.0, 120.0])
bin_edges.append(100.0)
bin_ranges.append([120.0, 140.0])
bin_edges.append(120.0)
bin_ranges.append([140.0, 160.0])
bin_edges.append(140.0)
bin_edges.append(160.0)
diff_by_value_bins = util.util.bin_data_by(diff, lbls, bin_ranges)
values = []
for k in range(len(bin_ranges)):
diff_k = diff_by_value_bins[k]
mae_k = (np.sum(np.abs(diff_k)) / diff_k.size)
values.append(int(mae_k/bin_ranges[k][1] * 100.0))
print('MAE: ', diff_k.size, bin_ranges[k], mae_k)
return np.array(values), bin_edges
if __name__ == "__main__":
nn = SRCNN()
nn.run('matchup_filename')