Fix wrong percentile values returned during calibration (#10847)

* Use numpy.percentile to get the lookup value.

* Use 1.0 as float value rather than integer.

* Add missing cdf parameter for `np.percentile`.

* Use 100. instead of 1.0

* Remove print.

* Update from @yufenglee

onnxruntime/python/tools/quantization/calibrate.py

@@ -599,19 +599,20 @@ def compute_percentile(self):
 
         print("Number of tensors : {}".format(len(histogram_dict)))
         print("Number of histogram bins : {}".format(self.num_bins))
-        print("Percentile : {}".format(percentile))
+        print("Percentile : ({},{})".format(100.0 - percentile, percentile))
 
         for tensor, histogram in histogram_dict.items():
             hist = histogram[0]
             hist_edges = histogram[1]
             total = hist.sum()
             cdf = np.cumsum(hist/total)
             if self.symmetric:
-                idx_right = np.searchsorted(cdf, percentile/100)
-                thresholds_dict[tensor] = (-float(hist_edges[idx_right]), float(hist_edges[idx_right]))
+                idx_right = np.searchsorted(cdf, percentile / 100.0)
+                thresholds_dict[tensor] = (-float(hist_edges[idx_ringht]), float(hist_edges[idx_right]))
             else:
-                idx_right = np.searchsorted(cdf, percentile/200)
-                idx_left = np.searchsorted(cdf, (1.0 - percentile/200))
+                percent_to_cut_one_side = (100.0 - percentile) / 200.0
+                idx_right = np.searchsorted(cdf, 1.0 - percent_to_cut_one_side)
+                idx_left = np.searchsorted(cdf, percent_to_cut_one_side)
                 thresholds_dict[tensor] = (float(hist_edges[idx_left]), float(hist_edges[idx_right]))
 
             # Plot histogram for debug only