diff --git a/modules/deeplearning/cloud_opd_fcn_abi.py b/modules/deeplearning/cloud_opd_fcn_abi.py
index 8bf3107f30828e180cd9bc7fc7584ac93964ee72..c26dcdc4320ba6222137da29cec36c25d1a0ed51 100644
--- a/modules/deeplearning/cloud_opd_fcn_abi.py
+++ b/modules/deeplearning/cloud_opd_fcn_abi.py
@@ -852,21 +852,20 @@ class SRCNN:
refl_lo = get_grid_values_all(h5f, 'refl_0_65um_nom_min_sub')
refl_hi = get_grid_values_all(h5f, 'refl_0_65um_nom_max_sub')
refl_std = get_grid_values_all(h5f, 'refl_0_65um_nom_stddev_sub')
- cp = get_grid_values_all(h5f, label_param)
- # lons = get_grid_values_all(h5f, 'longitude')
- # lats = get_grid_values_all(h5f, 'latitude')
+ cp = get_grid_values_all(h5f, 'cloud_probability')
+ opd = get_grid_values_all(h5f, label_param)
- cld_frac = self.run_inference_(bt, refl, refl_lo, refl_hi, refl_std, cp)
+ cldy_frac_opd = self.run_inference_(bt, refl, refl_lo, refl_hi, refl_std, cp, opd)
- cld_frac_out = np.zeros((y_len, x_len), dtype=np.int8)
+ cldy_frac_opd_out = np.zeros((y_len, x_len), dtype=np.int8)
border = int((KERNEL_SIZE - 1) / 2)
- cld_frac_out[border:y_len - border, border:x_len - border] = cld_frac[0, :, :]
+ cldy_frac_opd_out[border:y_len - border, border:x_len - border] = cldy_frac_opd[0, :, :]
# Use this hack for now.
off_earth = (bt <= 161.0)
night = np.isnan(refl)
- cld_frac_out[off_earth] = -1
- cld_frac_out[np.invert(off_earth) & night] = -1
+ cldy_frac_opd_out[off_earth] = -1
+ cldy_frac_opd_out[np.invert(off_earth) & night] = -1
# --- Make a DataArray ----------------------------------------------------
# var_names = ['cloud_fraction', 'temp_11_0um', 'refl_0_65um']
@@ -882,10 +881,10 @@ class SRCNN:
h5f.close()
if out_file is not None:
- np.save(out_file, (cld_frac_out, bt, refl, cp))
+ np.save(out_file, (cldy_frac_opd_out, bt, refl, cp))
else:
# return [cld_frac_out, bt, refl, cp, lons, lats]
- return cld_frac_out
+ return cldy_frac_opd_out
def run_inference_full_disk(self, in_file, out_file):
gc.collect()
@@ -900,7 +899,8 @@ class SRCNN:
refl_lo = get_grid_values_all(h5f, 'refl_0_65um_nom_min_sub')
refl_hi = get_grid_values_all(h5f, 'refl_0_65um_nom_max_sub')
refl_std = get_grid_values_all(h5f, 'refl_0_65um_nom_stddev_sub')
- cp = get_grid_values_all(h5f, label_param)
+ cp = get_grid_values_all(h5f, 'cloud_probability')
+ opd = get_grid_values_all(h5f, label_param)
t1 = time.time()
print(' read time:', (t1-t0))
@@ -910,6 +910,7 @@ class SRCNN:
refl_hi_nh = refl_hi[0:h_y_len + 1, :]
refl_std_nh = refl_std[0:h_y_len + 1, :]
cp_nh = cp[0:h_y_len + 1, :]
+ opd_nh = opd[0:h_y_len + 1, :]
bt_sh = bt[h_y_len - 1:y_len, :]
refl_sh = refl[h_y_len - 1:y_len, :]
@@ -917,23 +918,24 @@ class SRCNN:
refl_hi_sh = refl_hi[h_y_len - 1:y_len, :]
refl_std_sh = refl_std[h_y_len - 1:y_len, :]
cp_sh = cp[h_y_len - 1:y_len, :]
+ opd_sh = opd[h_y_len - 1:y_len, :]
t0 = time.time()
- cld_frac_nh = self.run_inference_(bt_nh, refl_nh, refl_lo_nh, refl_hi_nh, refl_std_nh, cp_nh)
- cld_frac_sh = self.run_inference_(bt_sh, refl_sh, refl_lo_sh, refl_hi_sh, refl_std_sh, cp_sh)
+ cldy_frac_opd_nh = self.run_inference_(bt_nh, refl_nh, refl_lo_nh, refl_hi_nh, refl_std_nh, cp_nh, opd_nh)
+ cldy_frac_opd_sh = self.run_inference_(bt_sh, refl_sh, refl_lo_sh, refl_hi_sh, refl_std_sh, cp_sh, opd_sh)
t1 = time.time()
print(' inference time: ', (t1-t0))
- cld_frac_out = np.zeros((y_len, x_len), dtype=np.int8)
+ cldy_frac_opd_out = np.zeros((y_len, x_len), dtype=np.int8)
border = int((KERNEL_SIZE - 1) / 2)
- cld_frac_out[border:h_y_len, border:x_len - border] = cld_frac_nh[0, :, :]
- cld_frac_out[h_y_len:y_len - border, border:x_len - border] = cld_frac_sh[0, :, :]
+ cldy_frac_opd_out[border:h_y_len, border:x_len - border] = cldy_frac_opd_nh[0, :, :]
+ cldy_frac_opd_out[h_y_len:y_len - border, border:x_len - border] = cldy_frac_opd_sh[0, :, :]
# Use this hack for now.
off_earth = (bt <= 161.0)
night = np.isnan(refl)
- cld_frac_out[off_earth] = -1
- cld_frac_out[np.invert(off_earth) & night] = -1
+ cldy_frac_opd_out[off_earth] = -1
+ cldy_frac_opd_out[np.invert(off_earth) & night] = -1
# --- Make DataArray -------------------------------------------------
# var_names = ['cloud_fraction', 'temp_11_0um', 'refl_0_65um']
@@ -949,26 +951,26 @@ class SRCNN:
h5f.close()
if out_file is not None:
- np.save(out_file, (cld_frac_out, bt, refl, cp))
+ np.save(out_file, (cldy_frac_opd_out, bt, refl, cp))
else:
# return [cld_frac_out, bt, refl, cp, lons, lats]
- return cld_frac_out
-
- def run_inference_(self, bt, refl, refl_lo, refl_hi, refl_std, cp):
- bt = normalize(bt, 'temp_11_0um_nom', mean_std_dct)
- refl = normalize(refl, 'refl_0_65um_nom', mean_std_dct)
- refl_lo = normalize(refl_lo, 'refl_0_65um_nom', mean_std_dct)
- refl_hi = normalize(refl_hi, 'refl_0_65um_nom', mean_std_dct)
- refl_std = np.where(np.isnan(refl_std), 0, refl_std)
+ return cldy_frac_opd_out
+
+ def run_inference_(self, bt, refl, refl_lo, refl_hi, refl_std, cp, opd):
+ bt = scale(bt, 'temp_11_0um_nom', mean_std_dct)
+ refl = scale(refl, 'refl_0_65um_nom', mean_std_dct)
+ refl_lo = scale(refl_lo, 'refl_0_65um_nom', mean_std_dct)
+ refl_hi = scale(refl_hi, 'refl_0_65um_nom', mean_std_dct)
+ refl_rng = refl_hi - refl_lo
+ refl_std = scale2(refl_std, 0.0, 30.0)
cp = np.where(np.isnan(cp), 0, cp)
+ opd = scale(opd, label_param, mean_std_dct)
- data = np.stack([bt, refl, refl_lo, refl_hi, refl_std, cp], axis=2)
+ data = np.stack([bt, cp, refl, refl_rng, refl_std, opd], axis=2)
data = np.expand_dims(data, axis=0)
- probs = self.do_inference(data)
- cld_frac = probs.argmax(axis=3)
- cld_frac = cld_frac.astype(np.int8)
+ opd = self.do_inference(data)
- return cld_frac
+ return opd
def run_restore_static(directory, ckpt_dir, out_file=None):