diff --git a/CheckSamples.ipynb b/CheckSamples.ipynb
index eafd6dd..e26debb 100644
--- a/CheckSamples.ipynb
+++ b/CheckSamples.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -10,22 +10,22 @@
      "output_type": "stream",
      "text": [
       "(625000, 4)\n",
-      "2.5738147384822754 2.3159877105736997 14979.560000000001\n"
+      "2.1872637879001546 2.9715624660714797 14997.66\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "<matplotlib.collections.PathCollection at 0x7fe5d47a16a0>"
+       "<matplotlib.collections.PathCollection at 0x7fc5365d78e0>"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -39,14 +39,14 @@
     "import matplotlib.pyplot as plt\n",
     "import h5py\n",
     "\n",
-    "data = np.load('/home/xie_x1/MLXID/McGeneration/Samples/15keV_Moench040_150V_15.npz')\n",
+    "data = np.load('/mnt/sls_det_storage/moench_data/MLXID/Samples/Simulation/Moench040/15keV_Moench040_150V_4.npz')\n",
     "samples = data['samples']\n",
     "labels = data['labels']\n",
     "# with h5py.File('/home/xie_x1/MLXID/McGeneration/Samples/15keV_Moench040_150V_15.h5', 'r') as hf:\n",
     "#     samples = hf['samples'][:]\n",
     "#     labels = hf['labels'][:]\n",
     "print(labels.shape)\n",
-    "idx = 6\n",
+    "idx = 1000\n",
     "plt.imshow(samples[idx], origin='lower', extent = (0, samples.shape[1], 0, samples.shape[2]))\n",
     "x,y,z,e = labels[idx]\n",
     "print(x,y,e)\n",
diff --git a/McGenerator.py b/McGenerator.py
index 24a9db9..59fe2f8 100644
--- a/McGenerator.py
+++ b/McGenerator.py
@@ -181,7 +181,7 @@ def singleProcess(thredIdx):
                         carrierArray = _carrierArray
                     x_center = x_center - (highestPixel[1] - _frameWidth//2 + j) * pixelSize
                     y_center = y_center - (highestPixel[0] - _frameWidth//2 + i) * pixelSize
-        samples[i] = pixelArray
+        samples[i] = pixelArray / 1000.0 ### keV
         labels[i] = np.array([x_center/pixelSize, y_center/pixelSize, z0, np.sum(_energyArray)])
     sampleOutputPath = _cfg['sampleOutputPath']
     element = _cfg['element']