diff --git a/modules/deeplearning/srcnn_cld_frac.py b/modules/deeplearning/srcnn_cld_frac.py
index f136b92efd6b88f07d8275123713d24c36a26e8e..a9895659daf5a0ed9a823a2f37e844abc801bac7 100644
--- a/modules/deeplearning/srcnn_cld_frac.py
+++ b/modules/deeplearning/srcnn_cld_frac.py
@@ -799,7 +799,7 @@ def run_restore_static(directory, ckpt_dir, out_file=None):
     nn = SRCNN()
     labels, preds = nn.run_restore(directory, ckpt_dir)
     if out_file is not None:
-        np.save(out_file, [np.squeeze(labels), preds.argmax(axis=3)])
+        np.save(out_file, [np.squeeze(labels), preds.argmax(axis=3), preds[:,:,:,0], preds[:,:,:,1], preds[:,:,:,2]])
 
 
 def run_evaluate_static(in_file, out_file, ckpt_dir):
@@ -874,82 +874,58 @@ def run_evaluate_static(in_file, out_file, ckpt_dir):
         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]
+from util.plot_cm import confusion_matrix_values
+
+
+def analyze(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[:, :, :, 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, 5.0])
-    bin_edges.append(0.0)
-
-    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)
+    pred = pred.flatten()
 
-    bin_ranges.append([30.0, 40.0])
-    bin_edges.append(30.0)
+    msk_0_1 = lbls != 2
+    msk_1_2 = lbls != 0
+    msk_0_2 = lbls != 1
 
-    bin_ranges.append([40.0, 60.0])
-    bin_edges.append(40.0)
+    lbls_0_1 = lbls[msk_0_1]
 
-    bin_ranges.append([60.0, 80.0])
-    bin_edges.append(60.0)
+    pred_0_1 = pred[msk_0_1]
+    pred_0_1 = np.where(pred_0_1 == 2, 1, pred_0_1)
 
-    bin_ranges.append([80.0, 100.0])
-    bin_edges.append(80.0)
+    # ----
+    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)
 
-    bin_ranges.append([100.0, 120.0])
-    bin_edges.append(100.0)
+    pred_1_2 = pred[msk_1_2]
+    pred_1_2 = np.where(pred_1_2 == 0, 1, 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)
 
-    bin_ranges.append([120.0, 140.0])
-    bin_edges.append(120.0)
+    # ----
+    lbls_0_2 = lbls[msk_0_2]
+    lbls_0_2 = np.where(lbls_0_2 == 0, 0, lbls_0_2)
+    lbls_0_2 = np.where(lbls_0_2 == 2, 1, lbls_0_2)
 
-    bin_ranges.append([140.0, 160.0])
-    bin_edges.append(140.0)
+    pred_0_2 = pred[msk_0_2]
+    pred_0_2 = np.where(pred_0_2 == 0, 0, pred_0_2)
+    pred_0_2 = np.where(pred_0_2 == 1, 1, pred_0_2)
+    pred_0_2 = np.where(pred_0_2 == 2, 1, pred_0_2)
 
-    bin_edges.append(160.0)
+    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)
 
-    diff_by_value_bins = util.util.bin_data_by(diff, lbls, bin_ranges)
+    return cm_0_1, cm_1_2,  cm_0_2
 
-    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__":