From 3bada8818338fed550e821be16d38f6990c63cc8 Mon Sep 17 00:00:00 2001
From: tomrink <rink@ssec.wisc.edu>
Date: Tue, 8 Nov 2022 13:45:24 -0600
Subject: [PATCH] snapshot...
---
modules/deeplearning/espcn_l1b_l2.py | 181 ++++++++++++++++-----------
1 file changed, 111 insertions(+), 70 deletions(-)
diff --git a/modules/deeplearning/espcn_l1b_l2.py b/modules/deeplearning/espcn_l1b_l2.py
index 6dc9e816..2b3ebc57 100644
--- a/modules/deeplearning/espcn_l1b_l2.py
+++ b/modules/deeplearning/espcn_l1b_l2.py
@@ -1,7 +1,8 @@
import glob
import tensorflow as tf
-from util.setup import logdir, modeldir, cachepath, now, ancillary_path
-from util.util import EarlyStop, normalize, denormalize, resample
+from util.setup import logdir, modeldir, now, ancillary_path
+from util.util import EarlyStop, normalize, denormalize, resample, resample_2d_linear, get_grid_values_all, \
+ resample_2d_linear_one
import os, datetime
import numpy as np
import pickle
@@ -32,6 +33,8 @@ NOISE_TRAINING = False
NOISE_STDDEV = 0.10
DO_AUGMENT = True
+IMG_DEPTH = 1
+
# setup scaling parameters dictionary
mean_std_dct = {}
mean_std_file = ancillary_path+'mean_std_lo_hi_l2.pkl'
@@ -47,26 +50,29 @@ f.close()
mean_std_dct.update(mean_std_dct_l1b)
mean_std_dct.update(mean_std_dct_l2)
-# data_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_10_4um_nom', 'temp_11_0um_nom', 'temp_12_0um_nom', 'temp_13_3um_nom', 'temp_3_9um_nom',
- 'temp_6_7um_nom']
-# data_params = ['refl_0_65um_nom', 'temp_11_0um_nom', 'cld_temp_acha', 'cld_press_acha', 'cloud_fraction']
-label_params = ['refl_0_65um_nom', 'temp_11_0um_nom', 'cld_temp_acha', 'cld_press_acha', 'cloud_fraction', 'cld_opd_acha']
+DO_ZERO_OUT = False
+# label_param = 'cloud_fraction'
+label_param = 'cld_opd_dcomp'
+# label_param = 'cloud_probability'
-DO_ZERO_OUT = False
+params = ['temp_11_0um_nom', 'temp_12_0um_nom', 'refl_0_65um_nom', label_param]
+data_params = ['temp_11_0um_nom', 'refl_0_65um_nom']
+
+label_idx = params.index(label_param)
+
+print('data_params: ', data_params)
+print('label_param: ', label_param)
-label_idx = 1
-label_param = label_params[label_idx]
x_134 = np.arange(134)
y_134 = np.arange(134)
-#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]
+slc_x = slice(3, 131)
+slc_y = slice(3, 131)
+
def build_residual_conv2d_block(conv, num_filters, block_name, activation=tf.nn.leaky_relu, padding='SAME', scale=None):
# kernel_initializer = 'glorot_uniform'
@@ -179,12 +185,9 @@ class ESPCN:
self.test_data_nda = None
self.test_label_nda = None
- self.n_chans = len(data_params)
+ self.n_chans = len(data_params) + 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)
@@ -192,25 +195,16 @@ class ESPCN:
def get_in_mem_data_batch(self, idxs, is_training):
if is_training:
- label_files = self.train_label_files
- data_files = self.train_data_files
+ files = self.train_data_files
else:
- label_files = self.test_label_files
- data_files = self.test_data_files
+ files = self.test_data_files
- label_s = []
data_s = []
for k in idxs:
- f = label_files[k]
- nda = np.load(f)
- label_s.append(nda)
-
- f = data_files[k]
+ f = files[k]
nda = np.load(f)
data_s.append(nda)
-
- label = np.concatenate(label_s)
- data = np.concatenate(data_s)
+ input_data = np.concatenate(data_s)
add_noise = None
noise_scale = None
@@ -220,22 +214,30 @@ class ESPCN:
data_norm = []
for k, param in enumerate(data_params):
- tmp = data[:, k, :, :]
- tmp = resample(x_134, y_134, tmp, x_134_2, y_134_2)
+ tmp = input_data[:, k, :, :]
tmp = normalize(tmp, param, mean_std_dct, add_noise=add_noise, noise_scale=noise_scale)
+ tmp = resample_2d_linear(x_134, y_134, tmp, x_134_2, y_134_2)
data_norm.append(tmp)
- data = np.stack(data_norm, axis=3)
- data = data.astype(np.float32)
- # label = label[:, label_idx, :, :]
- 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)
- label = label.astype(np.float32)
+ tmp = input_data[:, label_idx, :, ]
+ 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_134, y_134, tmp, x_134_2, y_134_2)
+ data_norm.append(tmp)
+ data = np.stack(data_norm, axis=3)
+
+ label = input_data[:, label_idx, slc_y, slc_x]
if label_param != 'cloud_fraction':
label = normalize(label, label_param, mean_std_dct)
- # label = label = scale(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)
@@ -312,16 +314,14 @@ class ESPCN:
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):
+ 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
- self.train_label_files = train_label_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))
+ tst_idxs = np.arange(len(test_data_files))
self.get_train_dataset(trn_idxs)
self.get_test_dataset(tst_idxs)
@@ -336,6 +336,7 @@ class ESPCN:
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))
@@ -359,7 +360,7 @@ class ESPCN:
kernel_initializer = 'he_uniform'
momentum = 0.99
- num_filters = 32
+ num_filters = 64
input_2d = self.inputs[0]
print('input: ', input_2d.shape)
@@ -382,18 +383,19 @@ class ESPCN:
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, padding=padding, kernel_initializer=kernel_initializer)(conv_b)
+ # conv_b = tf.keras.layers.Conv2D(num_filters, kernel_size=3, strides=1, padding=padding, kernel_initializer=kernel_initializer)(conv_b)
- conv = conv + conv_b
+ # conv = conv + conv_b
+ conv = conv_b
print(conv.shape)
- # conv = tf.keras.layers.Conv2D(num_filters * (factor ** 2), 3, padding='same')(conv)
- # print(conv.shape)
+ conv = tf.keras.layers.Conv2D(IMG_DEPTH * (factor ** 2), 3, padding='same')(conv)
+ print(conv.shape)
conv = tf.nn.depth_to_space(conv, factor)
print(conv.shape)
- self.logits = tf.keras.layers.Conv2D(1, kernel_size=3, strides=1, padding=padding, name='regression')(conv)
+ self.logits = tf.keras.layers.Conv2D(IMG_DEPTH, kernel_size=1, strides=1, padding=padding, activation=activation, name='regression')(conv)
print(self.logits.shape)
@@ -591,7 +593,6 @@ class ESPCN:
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()
@@ -604,42 +605,35 @@ class ESPCN:
print('loss, acc: ', self.test_loss.result().numpy(), self.test_accuracy.result().numpy())
- def do_evaluate(self, nda_lr, param, ckpt_dir):
+ 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)
- 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')
- train_label_files = glob.glob(directory+'label_train*.npy')
- valid_label_files = glob.glob(directory+'label_valid*.npy')
+ return pred
- train_data_files.sort()
- valid_data_files.sort()
+ 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, train_label_files, valid_data_files, valid_label_files, 100000)
+ self.setup_pipeline(train_data_files, valid_data_files, num_data_samples)
self.build_model()
self.build_training()
self.build_evaluation()
- self.do_training()
+ self.do_training(ckpt_dir=ckpt_dir)
def run_restore(self, directory, ckpt_dir):
- valid_data_files = glob.glob(directory + 'data_valid*.npy')
+ valid_data_files = glob.glob(directory + 'data_*.npy')
self.num_data_samples = 1000
self.setup_test_pipeline(valid_data_files)
self.build_model()
@@ -647,12 +641,59 @@ class ESPCN:
self.build_evaluation()
self.restore(ckpt_dir)
- def run_evaluate(self, nda_lr, param, 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(nda_lr, param, ckpt_dir)
+ return self.do_evaluate(data, ckpt_dir)
+
+
+def run_restore_static(directory, ckpt_dir):
+ nn = ESPCN()
+ nn.run_restore(directory, ckpt_dir)
+
+
+def run_evaluate_static(in_file, out_file, ckpt_dir):
+ N = 8
+ sub_y, sub_x = (N+1) * 128, (N+1) * 128
+ y_0, x_0, = 2500 - int(sub_y/2), 2500 - int(sub_x/2)
+
+ slc_y_2, slc_x_2 = slice(1, 128*N + 6, 2), slice(1, 128*N + 6, 2)
+ y_2, x_2 = np.arange((128*N)/2 + 3), np.arange((128*N)/2 + 3)
+ t, s = np.arange(1, (128*N)/2 + 2, 0.5), np.arange(1, (128*N)/2 + 2, 0.5)
+
+ 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[slc_y_2, slc_x_2]
+ grd_a = normalize(grd_a, 'temp_11_0um_nom', mean_std_dct)
+ grd_a = resample_2d_linear_one(x_2, y_2, grd_a, t, s)
+
+ 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[slc_y_2, slc_x_2]
+ grd_b = normalize(grd_b, 'refl_0_65um_nom', mean_std_dct)
+ grd_b = resample_2d_linear_one(x_2, y_2, grd_b, t, s)
+
+ 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]
+ grd_c = grd_c[slc_y_2, slc_x_2]
+ if label_param != 'cloud_fraction':
+ grd_c = normalize(grd_c, label_param, mean_std_dct)
+ grd_c = resample_2d_linear_one(x_2, y_2, grd_c, t, s)
+
+ data = np.stack([grd_a, grd_b, grd_c], axis=2)
+ data = np.expand_dims(data, axis=0)
+
+ nn = ESPCN()
+ 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
if __name__ == "__main__":
--
GitLab