Skip to content
Snippets Groups Projects
Commit 4fb4d92d authored by tomrink's avatar tomrink
Browse files

snapshot...

parent 637db97d
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
modules/deeplearning/cloud_fraction_fcn.py
+ 207
− 49
View file @ 4fb4d92d
import glob import glob
import tensorflow as tf import tensorflow as tf
import util.util from util.plot_cm import confusion_matrix_values
from util.setup import logdir, modeldir, now, ancillary_path from util.setup import logdir, modeldir, now, ancillary_path
from util.util import EarlyStop, normalize, denormalize, get_grid_values_all from util.util import EarlyStop, normalize, denormalize, get_grid_values_all
import os, datetime import os, datetime
...@@ -811,74 +811,232 @@ def run_evaluate_static(in_file, out_file, ckpt_dir): ...@@ -811,74 +811,232 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
return cld_frac_out, bt, refl_avg, cp return cld_frac_out, bt, refl_avg, cp
def analyze2(nda_m, nda_i): def analyze_3cat(file):
n_imgs = nda_m.shape[0]
nda_m = np.where(nda_m < 0.5, 0, 1)
nda_i = np.where(nda_i < 0.5, 0, 1)
cf_m = np.zeros((n_imgs, 64, 64)) tup = np.load(file, allow_pickle=True)
cf_i = np.zeros((n_imgs, 64, 64)) lbls = tup[0]
pred = tup[1]
prob_0 = tup[2]
prob_1 = tup[3]
prob_2 = tup[4]
for k in range(n_imgs): lbls = lbls.flatten()
for j in range(1, 65): pred = pred.flatten()
for i in range(1, 65): print(np.sum(lbls == 0), np.sum(lbls == 1), np.sum(lbls == 2))
sub_3x3 = nda_m[k, j-1:j+2, i-1:i+2]
cf_m[k, j-1, i-1] = np.sum(sub_3x3)
sub_4x4 = nda_i[k, j*2-1:j*2+3, i*2-1:i*2+3] msk_0_1 = lbls != 2
cf_i[k, j-1, i-1] = np.sum(sub_4x4) msk_1_2 = lbls != 0
msk_0_2 = lbls != 1
for k in range(n_imgs): lbls_0_1 = lbls[msk_0_1]
cat_0 = (cf_m[k, ] == 0)
cat_1 = (cf_m[k, ] > 0) & (cf_m[k, ] < 9)
cat_2 = cf_m[k, ] == 9
cf_m[k, cat_0] = 0 pred_0_1 = pred[msk_0_1]
cf_m[k, cat_1] = 1 pred_0_1 = np.where(pred_0_1 == 2, 1, pred_0_1)
cf_m[k, cat_2] = 2
cat_0 = (cf_i[k, ] == 0) # ----
cat_1 = (cf_i[k, ] > 0) & (cf_i[k, ] < 16) lbls_1_2 = lbls[msk_1_2]
cat_2 = cf_i[k, ] == 16 lbls_1_2 = np.where(lbls_1_2 == 1, 0, lbls_1_2)
lbls_1_2 = np.where(lbls_1_2 == 2, 1, lbls_1_2)
cf_i[k, cat_0] = 0 pred_1_2 = pred[msk_1_2]
cf_i[k, cat_1] = 1 pred_1_2 = np.where(pred_1_2 == 0, -9, pred_1_2)
cf_i[k, cat_2] = 2 pred_1_2 = np.where(pred_1_2 == 1, 0, pred_1_2)
pred_1_2 = np.where(pred_1_2 == 2, 1, pred_1_2)
pred_1_2 = np.where(pred_1_2 == -9, 1, pred_1_2)
return cf_m, cf_i # ----
lbls_0_2 = lbls[msk_0_2]
lbls_0_2 = np.where(lbls_0_2 == 2, 1, lbls_0_2)
pred_0_2 = pred[msk_0_2]
pred_0_2 = np.where(pred_0_2 == 2, 1, pred_0_2)
def helper(lbls, pred, file='/Users/tomrink/clavrx_surfrad_viirs_cld_prob_valid.npy'): cm_0_1 = confusion_matrix_values(lbls_0_1, pred_0_1)
nda = np.load(file, allow_pickle=True) cm_1_2 = confusion_matrix_values(lbls_1_2, pred_1_2)
cm_0_2 = confusion_matrix_values(lbls_0_2, pred_0_2)
bt = nda[:, 0, :, :] true_0_1 = (lbls_0_1 == 0) & (pred_0_1 == 0)
refl = nda[:, 1, :, :] false_0_1 = (lbls_0_1 == 1) & (pred_0_1 == 0)
cp = nda[:, 2, :, :]
bt = get_grid_cell_mean(bt) true_no_0_1 = (lbls_0_1 == 1) & (pred_0_1 == 1)
bt = bt[:, 0:66, 0:66] false_no_0_1 = (lbls_0_1 == 0) & (pred_0_1 == 1)
lo, hi, std, avg = get_min_max_std(refl) true_0_2 = (lbls_0_2 == 0) & (pred_0_2 == 0)
false_0_2 = (lbls_0_2 == 1) & (pred_0_2 == 0)
cp = np.where(np.isnan(cp), 0, cp) true_no_0_2 = (lbls_0_2 == 1) & (pred_0_2 == 1)
cp = get_grid_cell_mean(cp) false_no_0_2 = (lbls_0_2 == 0) & (pred_0_2 == 1)
cp = np.where(np.isnan(cp), 0, cp)
cp = cp[:, 1:65, 1:65] true_1_2 = (lbls_1_2 == 0) & (pred_1_2 == 0)
cp = cp.flatten() false_1_2 = (lbls_1_2 == 1) & (pred_1_2 == 0)
true_no_1_2 = (lbls_1_2 == 1) & (pred_1_2 == 1)
false_no_1_2 = (lbls_1_2 == 0) & (pred_1_2 == 1)
tp_0 = np.sum(true_0_1).astype(np.float64)
tp_1 = np.sum(true_1_2).astype(np.float64)
tp_2 = np.sum(true_0_2).astype(np.float64)
tn_0 = np.sum(true_no_0_1).astype(np.float64)
tn_1 = np.sum(true_no_1_2).astype(np.float64)
tn_2 = np.sum(true_no_0_2).astype(np.float64)
fp_0 = np.sum(false_0_1).astype(np.float64)
fp_1 = np.sum(false_1_2).astype(np.float64)
fp_2 = np.sum(false_0_2).astype(np.float64)
fn_0 = np.sum(false_no_0_1).astype(np.float64)
fn_1 = np.sum(false_no_1_2).astype(np.float64)
fn_2 = np.sum(false_no_0_2).astype(np.float64)
recall_0 = tp_0 / (tp_0 + fn_0)
recall_1 = tp_1 / (tp_1 + fn_1)
recall_2 = tp_2 / (tp_2 + fn_2)
precision_0 = tp_0 / (tp_0 + fp_0)
precision_1 = tp_1 / (tp_1 + fp_1)
precision_2 = tp_2 / (tp_2 + fp_2)
mcc_0 = ((tp_0 * tn_0) - (fp_0 * fn_0)) / np.sqrt((tp_0 + fp_0) * (tp_0 + fn_0) * (tn_0 + fp_0) * (tn_0 + fn_0))
mcc_1 = ((tp_1 * tn_1) - (fp_1 * fn_1)) / np.sqrt((tp_1 + fp_1) * (tp_1 + fn_1) * (tn_1 + fp_1) * (tn_1 + fn_1))
mcc_2 = ((tp_2 * tn_2) - (fp_2 * fn_2)) / np.sqrt((tp_2 + fp_2) * (tp_2 + fn_2) * (tn_2 + fp_2) * (tn_2 + fn_2))
acc_0 = np.sum(lbls_0_1 == pred_0_1)/pred_0_1.size
acc_1 = np.sum(lbls_1_2 == pred_1_2)/pred_1_2.size
acc_2 = np.sum(lbls_0_2 == pred_0_2)/pred_0_2.size
print(acc_0, recall_0, precision_0, mcc_0)
print(acc_1, recall_1, precision_1, mcc_1)
print(acc_2, recall_2, precision_2, mcc_2)
return cm_0_1, cm_1_2, cm_0_2, [acc_0, acc_1, acc_2], [recall_0, recall_1, recall_2],\
[precision_0, precision_1, precision_2], [mcc_0, mcc_1, mcc_2]
def analyze_5cat(file='/Users/tomrink/cld_opd_frac.npy'):
tup = np.load(file, allow_pickle=True)
lbls = tup[0]
pred = tup[1]
# prob_0 = tup[2]
# prob_1 = tup[3]
# prob_2 = tup[4]
lbls = lbls.flatten() lbls = lbls.flatten()
pred = pred.flatten() pred = pred.flatten()
print(lbls.shape, pred.shape, cp.shape) np.histogram(lbls, bins=5)
np.histogram(pred, bins=5)
new_lbls = np.zeros(lbls.size, dtype=np.int32)
new_pred = np.zeros(pred.size, dtype=np.int32)
new_lbls[lbls == 0] = 0
new_lbls[lbls == 1] = 1
new_lbls[lbls == 2] = 1
new_lbls[lbls == 3] = 1
new_lbls[lbls == 4] = 2
new_pred[pred == 0] = 0
new_pred[pred == 1] = 1
new_pred[pred == 2] = 1
new_pred[pred == 3] = 1
new_pred[pred == 4] = 2
np.histogram(new_lbls, bins=3)
np.histogram(new_pred, bins=3)
lbls = new_lbls
pred = new_pred
print(np.sum(lbls == 0), np.sum(lbls == 1), np.sum(lbls == 2))
msk_0_1 = lbls != 2
msk_1_2 = lbls != 0
msk_0_2 = lbls != 1
lbls_0_1 = lbls[msk_0_1]
pred_0_1 = pred[msk_0_1]
pred_0_1 = np.where(pred_0_1 == 2, 1, pred_0_1)
# ----
lbls_1_2 = lbls[msk_1_2]
lbls_1_2 = np.where(lbls_1_2 == 1, 0, lbls_1_2)
lbls_1_2 = np.where(lbls_1_2 == 2, 1, lbls_1_2)
pred_1_2 = pred[msk_1_2]
pred_1_2 = np.where(pred_1_2 == 0, -9, pred_1_2)
pred_1_2 = np.where(pred_1_2 == 1, 0, pred_1_2)
pred_1_2 = np.where(pred_1_2 == 2, 1, pred_1_2)
pred_1_2 = np.where(pred_1_2 == -9, 1, pred_1_2)
# ----
lbls_0_2 = lbls[msk_0_2]
lbls_0_2 = np.where(lbls_0_2 == 2, 1, lbls_0_2)
pred_0_2 = pred[msk_0_2]
pred_0_2 = np.where(pred_0_2 == 2, 1, pred_0_2)
cm_0_1 = confusion_matrix_values(lbls_0_1, pred_0_1)
cm_1_2 = confusion_matrix_values(lbls_1_2, pred_1_2)
cm_0_2 = confusion_matrix_values(lbls_0_2, pred_0_2)
true_0_1 = (lbls_0_1 == 0) & (pred_0_1 == 0)
false_0_1 = (lbls_0_1 == 1) & (pred_0_1 == 0)
true_no_0_1 = (lbls_0_1 == 1) & (pred_0_1 == 1)
false_no_0_1 = (lbls_0_1 == 0) & (pred_0_1 == 1)
true_0_2 = (lbls_0_2 == 0) & (pred_0_2 == 0)
false_0_2 = (lbls_0_2 == 1) & (pred_0_2 == 0)
true_no_0_2 = (lbls_0_2 == 1) & (pred_0_2 == 1)
false_no_0_2 = (lbls_0_2 == 0) & (pred_0_2 == 1)
true_1_2 = (lbls_1_2 == 0) & (pred_1_2 == 0)
false_1_2 = (lbls_1_2 == 1) & (pred_1_2 == 0)
true_no_1_2 = (lbls_1_2 == 1) & (pred_1_2 == 1)
false_no_1_2 = (lbls_1_2 == 0) & (pred_1_2 == 1)
tp_0 = np.sum(true_0_1).astype(np.float64)
tp_1 = np.sum(true_1_2).astype(np.float64)
tp_2 = np.sum(true_0_2).astype(np.float64)
tn_0 = np.sum(true_no_0_1).astype(np.float64)
tn_1 = np.sum(true_no_1_2).astype(np.float64)
tn_2 = np.sum(true_no_0_2).astype(np.float64)
fp_0 = np.sum(false_0_1).astype(np.float64)
fp_1 = np.sum(false_1_2).astype(np.float64)
fp_2 = np.sum(false_0_2).astype(np.float64)
fn_0 = np.sum(false_no_0_1).astype(np.float64)
fn_1 = np.sum(false_no_1_2).astype(np.float64)
fn_2 = np.sum(false_no_0_2).astype(np.float64)
recall_0 = tp_0 / (tp_0 + fn_0)
recall_1 = tp_1 / (tp_1 + fn_1)
recall_2 = tp_2 / (tp_2 + fn_2)
precision_0 = tp_0 / (tp_0 + fp_0)
precision_1 = tp_1 / (tp_1 + fp_1)
precision_2 = tp_2 / (tp_2 + fp_2)
mcc_0 = ((tp_0 * tn_0) - (fp_0 * fn_0)) / np.sqrt((tp_0 + fp_0) * (tp_0 + fn_0) * (tn_0 + fp_0) * (tn_0 + fn_0))
mcc_1 = ((tp_1 * tn_1) - (fp_1 * fn_1)) / np.sqrt((tp_1 + fp_1) * (tp_1 + fn_1) * (tn_1 + fp_1) * (tn_1 + fn_1))
mcc_2 = ((tp_2 * tn_2) - (fp_2 * fn_2)) / np.sqrt((tp_2 + fp_2) * (tp_2 + fn_2) * (tn_2 + fp_2) * (tn_2 + fn_2))
cp_cm = np.zeros((5, 5)) acc_0 = np.sum(lbls_0_1 == pred_0_1)/pred_0_1.size
acc_1 = np.sum(lbls_1_2 == pred_1_2)/pred_1_2.size
acc_2 = np.sum(lbls_0_2 == pred_0_2)/pred_0_2.size
for j in range(5): print(acc_0, recall_0, precision_0, mcc_0)
for i in range(5): print(acc_1, recall_1, precision_1, mcc_1)
keep = (lbls == j) & (pred == i) print(acc_2, recall_2, precision_2, mcc_2)
cp_avg = np.sum(cp[keep])/ np.sum(keep)
cp_cm[j, i] = cp_avg
return cp_cm return cm_0_1, cm_1_2, cm_0_2, [acc_0, acc_1, acc_2], [recall_0, recall_1, recall_2],\
[precision_0, precision_1, precision_2], [mcc_0, mcc_1, mcc_2], lbls, pred
if __name__ == "__main__": if __name__ == "__main__":
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment