ohnosan code

2eda7b39 · Mgr. Filip Münz PhD. · a45f47de · 2eda7b39
Commit 2eda7b39 authored Mar 01, 2021 by Mgr. Filip Münz PhD.
--- a/notebooks/TensorTest.ipynb
+++ b/notebooks/TensorTest.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from tensorflow import config\n",
+    "config.list_physical_devices('GPU')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy\n",
+    "#import matplotlib.pyplot as plt\n",
+    "\n",
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Dense\n",
+    "\n",
+    "nlayer=3\n",
+    "activ='sigmoid'\n",
+    "optim='adam'\n",
+    "xnorm_flag=1\n",
+    "ynorm_flag=1\n",
+    "ntrain=20000\n",
+    "nepochs=40\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "traindataset='D:/Data/time/lcurve2_1ms_pack%i.npz'\n",
+    "validdataset=traindataset%8\n",
+    "npz=[numpy.load(traindataset%i) for i in range(1,4)]\n",
+    "#npz=numpy.load(traindataset%1)\n",
+    "#xdata=npz['lc']\n",
+    "#ydata=npz['delay']\n",
+    "xdata=numpy.concatenate([[npq['set%s%i'%(str(j) if j>0 else \"\",i)] for i in range(1,10)] for j,npq in enumerate(npz)])\n",
+    "ydata=numpy.concatenate([[npq['del%s%i'%(str(j) if j>0 else \"\",i)] for i in range(1,10)] for j,npq in enumerate(npz)])\n",
+    "\n",
+    "xmin,xmax=numpy.min(xdata),numpy.max(xdata)\n",
+    "if xnorm_flag == 1:\n",
+    "\txdata=(xdata-xmin)/(xmax-xmin)\n",
+    "#xdata=xdata/numpy.max(xdata,axis=1)[:,numpy.newaxis]\n",
+    "ymin,ymax=numpy.min(ydata),numpy.max(ydata)\n",
+    "if ynorm_flag == 1:\n",
+    "\tydata=(ydata-ymin)/(ymax-ymin)\n",
+    "\n",
+    "xtrain=xdata[:ntrain]\n",
+    "ytrain=ydata[:ntrain]\n",
+    "\n",
+    "npz_valid=numpy.load(validdataset)\n",
+    "j=8\n",
+    "xdata=numpy.concatenate([npz_valid['set%i%i'%(j-1,i)] for i in range(4)])\n",
+    "ydata=numpy.concatenate([npz_valid['del%i%i'%(j-1,i)] for i in range(4)])\n",
+    "    \n",
+    "#xdata=npz_valid['lc']\n",
+    "#ydata=npz_valid['delay']\n",
+    "\n",
+    "xmin,xmax=numpy.min(xdata),numpy.max(xdata)\n",
+    "if xnorm_flag == 1:\n",
+    "\txdata=(xdata-xmin)/(xmax-xmin)\n",
+    "#xdata=xdata/numpy.max(xdata,axis=1)[:,numpy.newaxis]\n",
+    "ymin,ymax=numpy.min(ydata),numpy.max(ydata)\n",
+    "if ynorm_flag == 1:\n",
+    "\tydata=(ydata-ymin)/(ymax-ymin)\n",
+    "\n",
+    "xvalid=xdata\n",
+    "yvalid=ydata\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from neural import next# import train_me\n",
+    "next.xtrain,next.ytrain=xtrain,ytrain\n",
+    "next.xvalid,next.yvalid=xvalid,yvalid"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/100\n",
+      "WARNING:tensorflow:Model was constructed with shape (None, 10000) for input KerasTensor(type_spec=TensorSpec(shape=(None, 10000), dtype=tf.float32, name='dense_4_input'), name='dense_4_input', description=\"created by layer 'dense_4_input'\"), but it was called on an input with incompatible shape (None, 1000, 10000).\n",
+      "WARNING:tensorflow:Model was constructed with shape (None, 10000) for input KerasTensor(type_spec=TensorSpec(shape=(None, 10000), dtype=tf.float32, name='dense_4_input'), name='dense_4_input', description=\"created by layer 'dense_4_input'\"), but it was called on an input with incompatible shape (None, 1000, 10000).\n",
+      "1/1 [==============================] - 3s 3s/step - loss: 0.8164 - val_loss: 0.3632\n",
+      "Epoch 2/100\n",
+      "1/1 [==============================] - 0s 475ms/step - loss: 0.3784 - val_loss: 0.1531\n",
+      "Epoch 3/100\n",
+      "1/1 [==============================] - 0s 500ms/step - loss: 0.1630 - val_loss: 0.0880\n",
+      "Epoch 4/100\n",
+      "1/1 [==============================] - 0s 475ms/step - loss: 0.0901 - val_loss: 0.0908\n",
+      "Epoch 5/100\n",
+      "1/1 [==============================] - 1s 542ms/step - loss: 0.0870 - val_loss: 0.1164\n",
+      "Epoch 6/100\n",
+      "1/1 [==============================] - 1s 538ms/step - loss: 0.1092 - val_loss: 0.1431\n",
+      "Epoch 7/100\n",
+      "1/1 [==============================] - 1s 548ms/step - loss: 0.1343 - val_loss: 0.1620\n",
+      "Epoch 8/100\n",
+      "1/1 [==============================] - 1s 545ms/step - loss: 0.1526 - val_loss: 0.1711\n",
+      "Epoch 9/100\n",
+      "1/1 [==============================] - 1s 544ms/step - loss: 0.1619 - val_loss: 0.1715\n",
+      "Epoch 10/100\n",
+      "1/1 [==============================] - 1s 538ms/step - loss: 0.1627 - val_loss: 0.1653\n",
+      "Epoch 11/100\n",
+      "1/1 [==============================] - 1s 549ms/step - loss: 0.1571 - val_loss: 0.1547\n",
+      "Epoch 12/100\n",
+      "1/1 [==============================] - 1s 541ms/step - loss: 0.1472 - val_loss: 0.1416\n",
+      "Epoch 13/100\n",
+      "1/1 [==============================] - 1s 543ms/step - loss: 0.1350 - val_loss: 0.1279\n",
+      "Epoch 14/100\n",
+      "1/1 [==============================] - 1s 521ms/step - loss: 0.1221 - val_loss: 0.1150\n",
+      "Epoch 15/100\n",
+      "1/1 [==============================] - 1s 552ms/step - loss: 0.1099 - val_loss: 0.1037\n",
+      "Epoch 16/100\n",
+      "1/1 [==============================] - 1s 543ms/step - loss: 0.0995 - val_loss: 0.0947\n",
+      "Epoch 17/100\n",
+      "1/1 [==============================] - 1s 550ms/step - loss: 0.0914 - val_loss: 0.0884\n",
+      "Epoch 18/100\n",
+      "1/1 [==============================] - 1s 546ms/step - loss: 0.0859 - val_loss: 0.0847\n",
+      "Epoch 19/100\n",
+      "1/1 [==============================] - 1s 552ms/step - loss: 0.0830 - val_loss: 0.0833\n",
+      "Epoch 20/100\n",
+      "1/1 [==============================] - 1s 567ms/step - loss: 0.0824 - val_loss: 0.0838\n",
+      "Epoch 21/100\n",
+      "1/1 [==============================] - 1s 563ms/step - loss: 0.0835 - val_loss: 0.0854\n",
+      "Epoch 22/100\n",
+      "1/1 [==============================] - 1s 546ms/step - loss: 0.0856 - val_loss: 0.0876\n",
+      "Epoch 23/100\n",
+      "1/1 [==============================] - 1s 561ms/step - loss: 0.0882 - val_loss: 0.0897\n",
+      "Epoch 24/100\n",
+      "1/1 [==============================] - 1s 550ms/step - loss: 0.0907 - val_loss: 0.0913\n",
+      "Epoch 25/100\n",
+      "1/1 [==============================] - 1s 562ms/step - loss: 0.0925 - val_loss: 0.0921\n",
+      "Epoch 26/100\n",
+      "1/1 [==============================] - 1s 553ms/step - loss: 0.0934 - val_loss: 0.0921\n",
+      "Epoch 27/100\n",
+      "1/1 [==============================] - 1s 551ms/step - loss: 0.0934 - val_loss: 0.0913\n",
+      "Epoch 28/100\n",
+      "1/1 [==============================] - 1s 555ms/step - loss: 0.0925 - val_loss: 0.0900\n",
+      "Epoch 29/100\n",
+      "1/1 [==============================] - 1s 554ms/step - loss: 0.0909 - val_loss: 0.0883\n",
+      "Epoch 30/100\n",
+      "1/1 [==============================] - 1s 550ms/step - loss: 0.0891 - val_loss: 0.0866\n",
+      "Epoch 31/100\n",
+      "1/1 [==============================] - 1s 570ms/step - loss: 0.0871 - val_loss: 0.0851\n",
+      "Epoch 32/100\n",
+      "1/1 [==============================] - 1s 571ms/step - loss: 0.0852 - val_loss: 0.0839\n",
+      "Epoch 33/100\n",
+      "1/1 [==============================] - 1s 576ms/step - loss: 0.0837 - val_loss: 0.0831\n",
+      "Epoch 34/100\n",
+      "1/1 [==============================] - 1s 539ms/step - loss: 0.0826 - val_loss: 0.0828\n",
+      "Epoch 35/100\n",
+      "1/1 [==============================] - 1s 556ms/step - loss: 0.0820 - val_loss: 0.0828\n",
+      "Epoch 36/100\n",
+      "1/1 [==============================] - 1s 550ms/step - loss: 0.0818 - val_loss: 0.0832\n",
+      "Epoch 37/100\n",
+      "1/1 [==============================] - 1s 575ms/step - loss: 0.0818 - val_loss: 0.0837\n",
+      "Epoch 38/100\n",
+      "1/1 [==============================] - 1s 550ms/step - loss: 0.0822 - val_loss: 0.0843\n",
+      "Epoch 39/100\n",
+      "1/1 [==============================] - 1s 556ms/step - loss: 0.0826 - val_loss: 0.0849\n",
+      "Epoch 40/100\n",
+      "1/1 [==============================] - 1s 549ms/step - loss: 0.0830 - val_loss: 0.0853\n",
+      "Epoch 41/100\n",
+      "1/1 [==============================] - 1s 551ms/step - loss: 0.0833 - val_loss: 0.0855\n",
+      "Epoch 42/100\n",
+      "1/1 [==============================] - 1s 554ms/step - loss: 0.0835 - val_loss: 0.0856\n",
+      "Epoch 43/100\n",
+      "1/1 [==============================] - 1s 553ms/step - loss: 0.0835 - val_loss: 0.0854\n",
+      "Epoch 44/100\n",
+      "1/1 [==============================] - 1s 517ms/step - loss: 0.0834 - val_loss: 0.0851\n",
+      "Epoch 45/100\n",
+      "1/1 [==============================] - 1s 563ms/step - loss: 0.0831 - val_loss: 0.0846\n",
+      "Epoch 46/100\n",
+      "1/1 [==============================] - 1s 548ms/step - loss: 0.0827 - val_loss: 0.0841\n",
+      "Epoch 47/100\n",
+      "1/1 [==============================] - 1s 549ms/step - loss: 0.0823 - val_loss: 0.0835\n",
+      "Epoch 48/100\n",
+      "1/1 [==============================] - 1s 557ms/step - loss: 0.0819 - val_loss: 0.0830\n",
+      "Epoch 49/100\n",
+      "1/1 [==============================] - 1s 554ms/step - loss: 0.0815 - val_loss: 0.0826\n",
+      "Epoch 50/100\n",
+      "1/1 [==============================] - 1s 553ms/step - loss: 0.0812 - val_loss: 0.0822\n",
+      "Epoch 51/100\n",
+      "1/1 [==============================] - 1s 544ms/step - loss: 0.0810 - val_loss: 0.0819\n",
+      "Epoch 52/100\n",
+      "1/1 [==============================] - 1s 568ms/step - loss: 0.0808 - val_loss: 0.0817\n",
+      "Epoch 53/100\n",
+      "1/1 [==============================] - 1s 572ms/step - loss: 0.0808 - val_loss: 0.0816\n",
+      "Epoch 54/100\n",
+      "1/1 [==============================] - 1s 530ms/step - loss: 0.0807 - val_loss: 0.0815\n",
+      "Epoch 55/100\n",
+      "1/1 [==============================] - 1s 557ms/step - loss: 0.0808 - val_loss: 0.0815\n",
+      "Epoch 56/100\n",
+      "1/1 [==============================] - 1s 549ms/step - loss: 0.0808 - val_loss: 0.0814\n",
+      "Epoch 57/100\n",
+      "1/1 [==============================] - 1s 575ms/step - loss: 0.0808 - val_loss: 0.0813\n",
+      "Epoch 58/100\n",
+      "1/1 [==============================] - 1s 554ms/step - loss: 0.0807 - val_loss: 0.0812\n",
+      "Epoch 59/100\n",
+      "1/1 [==============================] - 1s 556ms/step - loss: 0.0806 - val_loss: 0.0811\n",
+      "Epoch 60/100\n",
+      "1/1 [==============================] - 1s 588ms/step - loss: 0.0805 - val_loss: 0.0810\n",
+      "Epoch 61/100\n",
+      "1/1 [==============================] - 1s 567ms/step - loss: 0.0803 - val_loss: 0.0808\n",
+      "Epoch 62/100\n",
+      "1/1 [==============================] - 1s 549ms/step - loss: 0.0801 - val_loss: 0.0807\n",
+      "Epoch 63/100\n",
+      "1/1 [==============================] - 1s 553ms/step - loss: 0.0799 - val_loss: 0.0806\n",
+      "Epoch 64/100\n",
+      "1/1 [==============================] - 1s 536ms/step - loss: 0.0797 - val_loss: 0.0804\n",
+      "Epoch 65/100\n",
+      "1/1 [==============================] - 1s 563ms/step - loss: 0.0795 - val_loss: 0.0803\n",
+      "Epoch 66/100\n",
+      "1/1 [==============================] - 1s 550ms/step - loss: 0.0794 - val_loss: 0.0803\n",
+      "Epoch 67/100\n",
+      "1/1 [==============================] - 1s 557ms/step - loss: 0.0792 - val_loss: 0.0802\n",
+      "Epoch 68/100\n",
+      "1/1 [==============================] - 1s 549ms/step - loss: 0.0791 - val_loss: 0.0801\n",
+      "Epoch 69/100\n",
+      "1/1 [==============================] - 1s 562ms/step - loss: 0.0790 - val_loss: 0.0800\n",
+      "Epoch 70/100\n",
+      "1/1 [==============================] - 1s 555ms/step - loss: 0.0788 - val_loss: 0.0799\n",
+      "Epoch 71/100\n",
+      "1/1 [==============================] - 1s 556ms/step - loss: 0.0787 - val_loss: 0.0798\n",
+      "Epoch 72/100\n",
+      "1/1 [==============================] - 1s 562ms/step - loss: 0.0786 - val_loss: 0.0796\n",
+      "Epoch 73/100\n",
+      "1/1 [==============================] - 1s 567ms/step - loss: 0.0784 - val_loss: 0.0794\n",
+      "Epoch 74/100\n",
+      "1/1 [==============================] - 1s 538ms/step - loss: 0.0782 - val_loss: 0.0791\n",
+      "Epoch 75/100\n",
+      "1/1 [==============================] - 1s 557ms/step - loss: 0.0780 - val_loss: 0.0789\n",
+      "Epoch 76/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1/1 [==============================] - 1s 557ms/step - loss: 0.0778 - val_loss: 0.0786\n",
+      "Epoch 77/100\n",
+      "1/1 [==============================] - 1s 562ms/step - loss: 0.0775 - val_loss: 0.0783\n",
+      "Epoch 78/100\n",
+      "1/1 [==============================] - 1s 552ms/step - loss: 0.0773 - val_loss: 0.0780\n",
+      "Epoch 79/100\n",
+      "1/1 [==============================] - 1s 560ms/step - loss: 0.0771 - val_loss: 0.0777\n",
+      "Epoch 80/100\n",
+      "1/1 [==============================] - 1s 566ms/step - loss: 0.0768 - val_loss: 0.0775\n",
+      "Epoch 81/100\n",
+      "1/1 [==============================] - 1s 556ms/step - loss: 0.0766 - val_loss: 0.0772\n",
+      "Epoch 82/100\n",
+      "1/1 [==============================] - 1s 552ms/step - loss: 0.0764 - val_loss: 0.0769\n",
+      "Epoch 83/100\n",
+      "1/1 [==============================] - 1s 559ms/step - loss: 0.0761 - val_loss: 0.0766\n",
+      "Epoch 84/100\n",
+      "1/1 [==============================] - 1s 539ms/step - loss: 0.0759 - val_loss: 0.0763\n",
+      "Epoch 85/100\n",
+      "1/1 [==============================] - 1s 561ms/step - loss: 0.0756 - val_loss: 0.0760\n",
+      "Epoch 86/100\n",
+      "1/1 [==============================] - 1s 554ms/step - loss: 0.0753 - val_loss: 0.0757\n",
+      "Epoch 87/100\n",
+      "1/1 [==============================] - 1s 553ms/step - loss: 0.0750 - val_loss: 0.0754\n",
+      "Epoch 88/100\n",
+      "1/1 [==============================] - 1s 555ms/step - loss: 0.0747 - val_loss: 0.0751\n",
+      "Epoch 89/100\n",
+      "1/1 [==============================] - 1s 555ms/step - loss: 0.0744 - val_loss: 0.0747\n",
+      "Epoch 90/100\n",
+      "1/1 [==============================] - 1s 564ms/step - loss: 0.0740 - val_loss: 0.0744\n",
+      "Epoch 91/100\n",
+      "1/1 [==============================] - 1s 570ms/step - loss: 0.0737 - val_loss: 0.0740\n",
+      "Epoch 92/100\n",
+      "1/1 [==============================] - 1s 504ms/step - loss: 0.0733 - val_loss: 0.0737\n",
+      "Epoch 93/100\n",
+      "1/1 [==============================] - 0s 498ms/step - loss: 0.0730 - val_loss: 0.0733\n",
+      "Epoch 94/100\n",
+      "1/1 [==============================] - 0s 491ms/step - loss: 0.0726 - val_loss: 0.0729\n",
+      "Epoch 95/100\n",
+      "1/1 [==============================] - 1s 513ms/step - loss: 0.0722 - val_loss: 0.0724\n",
+      "Epoch 96/100\n",
+      "1/1 [==============================] - 0s 496ms/step - loss: 0.0718 - val_loss: 0.0720\n",
+      "Epoch 97/100\n",
+      "1/1 [==============================] - 1s 508ms/step - loss: 0.0714 - val_loss: 0.0715\n",
+      "Epoch 98/100\n",
+      "1/1 [==============================] - 1s 508ms/step - loss: 0.0709 - val_loss: 0.0710\n",
+      "Epoch 99/100\n",
+      "1/1 [==============================] - 1s 531ms/step - loss: 0.0704 - val_loss: 0.0705\n",
+      "Epoch 100/100\n",
+      "1/1 [==============================] - 1s 751ms/step - loss: 0.0700 - val_loss: 0.0700\n",
+      "{'loss': [0.8163502812385559, 0.37836092710494995, 0.16299152374267578, 0.09008520096540451, 0.08696170896291733, 0.1092318519949913, 0.13427534699440002, 0.15262632071971893, 0.16185811161994934, 0.16272039711475372, 0.15711943805217743, 0.14719893038272858, 0.13495542109012604, 0.1220879852771759, 0.10994517058134079, 0.09951166063547134, 0.09141222387552261, 0.08592653274536133, 0.083015576004982, 0.08236584812402725, 0.08345473557710648, 0.08563636988401413, 0.08824030309915543, 0.09066823869943619, 0.09247046709060669, 0.093387670814991, 0.09335416555404663, 0.09246870875358582, 0.09094493836164474, 0.08905428647994995, 0.08707279711961746, 0.08523936569690704, 0.08372866362333298, 0.08263950049877167, 0.08199633657932281, 0.08176089823246002, 0.08184991776943207, 0.08215530961751938, 0.08256322890520096, 0.082970030605793, 0.0832933858036995, 0.08347869664430618, 0.08350080996751785, 0.08336189389228821, 0.08308640122413635, 0.08271430432796478, 0.08229335397481918, 0.08187145739793777, 0.08149012178182602, 0.0811794251203537, 0.0809551551938057, 0.08081825822591782, 0.08075647056102753, 0.08074785023927689, 0.08076538145542145, 0.08078188449144363, 0.08077438920736313, 0.08072733134031296, 0.0806339904665947, 0.08049636334180832, 0.08032337576150894, 0.08012831956148148, 0.07992562651634216, 0.07972826063632965, 0.07954539358615875, 0.07938137650489807, 0.07923559844493866, 0.07910327613353729, 0.07897699624300003, 0.07884839177131653, 0.07870981097221375, 0.0785556361079216, 0.07838300615549088, 0.07819198817014694, 0.07798504829406738, 0.07776623964309692, 0.07754009962081909, 0.07731056213378906, 0.07708016037940979, 0.076849564909935, 0.0766175165772438, 0.07638127356767654, 0.07613734155893326, 0.07588224112987518, 0.07561319321393967, 0.07532869279384613, 0.07502857595682144, 0.07471384853124619, 0.07438614964485168, 0.07404714822769165, 0.07369804382324219, 0.0733390673995018, 0.07296944409608841, 0.07258769124746323, 0.07219190150499344, 0.07178036123514175, 0.07135189324617386, 0.07090598344802856, 0.07044275850057602, 0.06996259093284607], 'val_loss': [0.3632182478904724, 0.15310396254062653, 0.088015116751194, 0.09076758474111557, 0.11644914746284485, 0.14310957491397858, 0.1619814783334732, 0.17111456394195557, 0.1715390831232071, 0.16531631350517273, 0.1546715348958969, 0.14164240658283234, 0.12794919312000275, 0.11495472490787506, 0.10365840047597885, 0.09470260888338089, 0.08838701993227005, 0.08469322323799133, 0.08332712948322296, 0.0837831124663353, 0.0854291096329689, 0.0876045674085617, 0.08971644192934036, 0.09131535142660141, 0.09213797003030777, 0.0921105369925499, 0.09132073074579239, 0.0899684876203537, 0.08831020444631577, 0.08660601824522018, 0.08507896214723587, 0.08388873189687729, 0.0831204503774643, 0.08278664201498032, 0.08283895254135132, 0.08318615704774857, 0.08371421694755554, 0.08430524170398712, 0.08485326915979385, 0.08527533710002899, 0.0855175107717514, 0.0855565220117569, 0.08539736270904541, 0.08506830036640167, 0.08461374789476395, 0.08408660441637039, 0.08354026824235916, 0.08302222192287445, 0.08256847411394119, 0.08220074325799942, 0.08192568272352219, 0.08173610270023346, 0.08161447942256927, 0.08153733611106873, 0.08148004114627838, 0.08142103999853134, 0.08134515583515167, 0.08124500513076782, 0.08112092316150665, 0.08097942918539047, 0.08083070069551468, 0.08068563789129257, 0.08055336028337479, 0.08043909817934036, 0.08034338802099228, 0.08026199787855148, 0.08018693327903748, 0.08010806143283844, 0.08001504838466644, 0.07989875227212906, 0.07975289225578308, 0.07957471907138824, 0.07936503738164902, 0.07912764698266983, 0.07886850833892822, 0.07859446853399277, 0.07831203192472458, 0.0780264362692833, 0.07774097472429276, 0.07745680212974548, 0.07717332243919373, 0.07688867300748825, 0.07660047709941864, 0.07630657404661179, 0.07600542157888412, 0.07569630444049835, 0.07537909597158432, 0.07505399733781815, 0.07472077012062073, 0.07437862455844879, 0.0740257054567337, 0.07365924119949341, 0.07327597588300705, 0.07287269830703735, 0.07244677096605301, 0.07199685275554657, 0.07152265310287476, 0.07102520018815994, 0.07050613313913345, 0.06996720284223557]}\n"
+     ]
+    },
+    {
+     "ename": "NameError",
+     "evalue": "name 'npatterns' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-44-7411c487e279>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[0mmodel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mnext\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtrain_me\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"D:/Data/\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msave\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"D:/Data/model_%dlayer_%dtrain_%depochs_noynorm_%dpatterns_batch.h5\"\u001b[0m\u001b[1;33m%\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnlayer\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mntrain\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mnepochs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mnpatterns\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m: name 'npatterns' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "model=next.train_me(\"D:/Data/\")\n",
+    "model.save(\"D:/Data/model_%dlayer_%dtrain_%depochs_noynorm_%dpatterns_batch.h5\"%(nlayer,ntrain,nepochs,npatterns))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<module 'neural.next' from 'C:\\\\Users\\\\159565\\\\Code\\\\neural\\\\next.py'>"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from imp import reload\n",
+    "from neural import next\n",
+    "reload(next)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.save(\"D:/Data/model_%dlayer_%dtrain_%depochs_noynorm_%dpatterns_batch.h5\"%(nlayer,ntrain,nepochs,10000))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "next.ynorm_flag=1\n",
+    "diff=next.predict(model,xvalid,yvalid,\"D:/Data/\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(0.2273918786375855, 4000)"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from matplotlib import pyplot as pl\n",
+    "%matplotlib inline\n",
+    "pl.hist(diff)\n",
+    "abs(diff).mean(),len(diff)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
+%% Cell type:code id: tags:
+
+``` python
+from tensorflow import config
+config.list_physical_devices('GPU')
+```
+
+%% Output
+
+    [PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]
+
+%% Cell type:code id: tags:
+
+``` python
+import numpy
+#import matplotlib.pyplot as plt
+
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense
+
+nlayer=3
+activ='sigmoid'
+optim='adam'
+xnorm_flag=1
+ynorm_flag=1
+ntrain=20000
+nepochs=40
+```
+
+%% Cell type:code id: tags:
+
+``` python
+traindataset='D:/Data/time/lcurve2_1ms_pack%i.npz'
+validdataset=traindataset%8
+npz=[numpy.load(traindataset%i) for i in range(1,4)]
+#npz=numpy.load(traindataset%1)
+#xdata=npz['lc']
+#ydata=npz['delay']
+xdata=numpy.concatenate([[npq['set%s%i'%(str(j) if j>0 else "",i)] for i in range(1,10)] for j,npq in enumerate(npz)])
+ydata=numpy.concatenate([[npq['del%s%i'%(str(j) if j>0 else "",i)] for i in range(1,10)] for j,npq in enumerate(npz)])
+
+xmin,xmax=numpy.min(xdata),numpy.max(xdata)
+if xnorm_flag == 1:
+	xdata=(xdata-xmin)/(xmax-xmin)
+#xdata=xdata/numpy.max(xdata,axis=1)[:,numpy.newaxis]
+ymin,ymax=numpy.min(ydata),numpy.max(ydata)
+if ynorm_flag == 1:
+	ydata=(ydata-ymin)/(ymax-ymin)
+
+xtrain=xdata[:ntrain]
+ytrain=ydata[:ntrain]
+
+npz_valid=numpy.load(validdataset)
+j=8
+xdata=numpy.concatenate([npz_valid['set%i%i'%(j-1,i)] for i in range(4)])
+ydata=numpy.concatenate([npz_valid['del%i%i'%(j-1,i)] for i in range(4)])
+
+#xdata=npz_valid['lc']
+#ydata=npz_valid['delay']
+
+xmin,xmax=numpy.min(xdata),numpy.max(xdata)
+if xnorm_flag == 1:
+	xdata=(xdata-xmin)/(xmax-xmin)
+#xdata=xdata/numpy.max(xdata,axis=1)[:,numpy.newaxis]
+ymin,ymax=numpy.min(ydata),numpy.max(ydata)
+if ynorm_flag == 1:
+	ydata=(ydata-ymin)/(ymax-ymin)
+
+xvalid=xdata
+yvalid=ydata
+```
+
+%% Cell type:code id: tags:
+
+``` python
+from neural import next# import train_me
+next.xtrain,next.ytrain=xtrain,ytrain
+next.xvalid,next.yvalid=xvalid,yvalid
+```
+
+%% Cell type:code id: tags:
+
+``` python
+model=next.train_me("D:/Data/")
+model.save("D:/Data/model_%dlayer_%dtrain_%depochs_noynorm_%dpatterns_batch.h5"%(nlayer,ntrain,nepochs,npatterns))
+```
+
+%% Output
+
+    Epoch 1/100
+    WARNING:tensorflow:Model was constructed with shape (None, 10000) for input KerasTensor(type_spec=TensorSpec(shape=(None, 10000), dtype=tf.float32, name='dense_4_input'), name='dense_4_input', description="created by layer 'dense_4_input'"), but it was called on an input with incompatible shape (None, 1000, 10000).
+    WARNING:tensorflow:Model was constructed with shape (None, 10000) for input KerasTensor(type_spec=TensorSpec(shape=(None, 10000), dtype=tf.float32, name='dense_4_input'), name='dense_4_input', description="created by layer 'dense_4_input'"), but it was called on an input with incompatible shape (None, 1000, 10000).
+    1/1 [==============================] - 3s 3s/step - loss: 0.8164 - val_loss: 0.3632
+    Epoch 2/100
+    1/1 [==============================] - 0s 475ms/step - loss: 0.3784 - val_loss: 0.1531
+    Epoch 3/100
+    1/1 [==============================] - 0s 500ms/step - loss: 0.1630 - val_loss: 0.0880
+    Epoch 4/100
+    1/1 [==============================] - 0s 475ms/step - loss: 0.0901 - val_loss: 0.0908
+    Epoch 5/100
+    1/1 [==============================] - 1s 542ms/step - loss: 0.0870 - val_loss: 0.1164
+    Epoch 6/100
+    1/1 [==============================] - 1s 538ms/step - loss: 0.1092 - val_loss: 0.1431
+    Epoch 7/100
+    1/1 [==============================] - 1s 548ms/step - loss: 0.1343 - val_loss: 0.1620
+    Epoch 8/100
+    1/1 [==============================] - 1s 545ms/step - loss: 0.1526 - val_loss: 0.1711
+    Epoch 9/100
+    1/1 [==============================] - 1s 544ms/step - loss: 0.1619 - val_loss: 0.1715
+    Epoch 10/100
+    1/1 [==============================] - 1s 538ms/step - loss: 0.1627 - val_loss: 0.1653
+    Epoch 11/100
+    1/1 [==============================] - 1s 549ms/step - loss: 0.1571 - val_loss: 0.1547
+    Epoch 12/100
+    1/1 [==============================] - 1s 541ms/step - loss: 0.1472 - val_loss: 0.1416
+    Epoch 13/100
+    1/1 [==============================] - 1s 543ms/step - loss: 0.1350 - val_loss: 0.1279
+    Epoch 14/100
+    1/1 [==============================] - 1s 521ms/step - loss: 0.1221 - val_loss: 0.1150
+    Epoch 15/100
+    1/1 [==============================] - 1s 552ms/step - loss: 0.1099 - val_loss: 0.1037
+    Epoch 16/100
+    1/1 [==============================] - 1s 543ms/step - loss: 0.0995 - val_loss: 0.0947
+    Epoch 17/100
+    1/1 [==============================] - 1s 550ms/step - loss: 0.0914 - val_loss: 0.0884
+    Epoch 18/100
+    1/1 [==============================] - 1s 546ms/step - loss: 0.0859 - val_loss: 0.0847
+    Epoch 19/100
+    1/1 [==============================] - 1s 552ms/step - loss: 0.0830 - val_loss: 0.0833
+    Epoch 20/100
+    1/1 [==============================] - 1s 567ms/step - loss: 0.0824 - val_loss: 0.0838
+    Epoch 21/100
+    1/1 [==============================] - 1s 563ms/step - loss: 0.0835 - val_loss: 0.0854
+    Epoch 22/100
+    1/1 [==============================] - 1s 546ms/step - loss: 0.0856 - val_loss: 0.0876
+    Epoch 23/100
+    1/1 [==============================] - 1s 561ms/step - loss: 0.0882 - val_loss: 0.0897
+    Epoch 24/100
+    1/1 [==============================] - 1s 550ms/step - loss: 0.0907 - val_loss: 0.0913
+    Epoch 25/100
+    1/1 [==============================] - 1s 562ms/step - loss: 0.0925 - val_loss: 0.0921
+    Epoch 26/100
+    1/1 [==============================] - 1s 553ms/step - loss: 0.0934 - val_loss: 0.0921
+    Epoch 27/100
+    1/1 [==============================] - 1s 551ms/step - loss: 0.0934 - val_loss: 0.0913
+    Epoch 28/100
+    1/1 [==============================] - 1s 555ms/step - loss: 0.0925 - val_loss: 0.0900
+    Epoch 29/100
+    1/1 [==============================] - 1s 554ms/step - loss: 0.0909 - val_loss: 0.0883
+    Epoch 30/100
+    1/1 [==============================] - 1s 550ms/step - loss: 0.0891 - val_loss: 0.0866
+    Epoch 31/100
+    1/1 [==============================] - 1s 570ms/step - loss: 0.0871 - val_loss: 0.0851
+    Epoch 32/100
+    1/1 [==============================] - 1s 571ms/step - loss: 0.0852 - val_loss: 0.0839
+    Epoch 33/100
+    1/1 [==============================] - 1s 576ms/step - loss: 0.0837 - val_loss: 0.0831
+    Epoch 34/100
+    1/1 [==============================] - 1s 539ms/step - loss: 0.0826 - val_loss: 0.0828
+    Epoch 35/100
+    1/1 [==============================] - 1s 556ms/step - loss: 0.0820 - val_loss: 0.0828
+    Epoch 36/100
+    1/1 [==============================] - 1s 550ms/step - loss: 0.0818 - val_loss: 0.0832
+    Epoch 37/100
+    1/1 [==============================] - 1s 575ms/step - loss: 0.0818 - val_loss: 0.0837
+    Epoch 38/100
+    1/1 [==============================] - 1s 550ms/step - loss: 0.0822 - val_loss: 0.0843
+    Epoch 39/100
+    1/1 [==============================] - 1s 556ms/step - loss: 0.0826 - val_loss: 0.0849
+    Epoch 40/100
+    1/1 [==============================] - 1s 549ms/step - loss: 0.0830 - val_loss: 0.0853
+    Epoch 41/100
+    1/1 [==============================] - 1s 551ms/step - loss: 0.0833 - val_loss: 0.0855
+    Epoch 42/100
+    1/1 [==============================] - 1s 554ms/step - loss: 0.0835 - val_loss: 0.0856
+    Epoch 43/100
+    1/1 [==============================] - 1s 553ms/step - loss: 0.0835 - val_loss: 0.0854
+    Epoch 44/100
+    1/1 [==============================] - 1s 517ms/step - loss: 0.0834 - val_loss: 0.0851
+    Epoch 45/100
+    1/1 [==============================] - 1s 563ms/step - loss: 0.0831 - val_loss: 0.0846
+    Epoch 46/100
+    1/1 [==============================] - 1s 548ms/step - loss: 0.0827 - val_loss: 0.0841
+    Epoch 47/100
+    1/1 [==============================] - 1s 549ms/step - loss: 0.0823 - val_loss: 0.0835
+    Epoch 48/100
+    1/1 [==============================] - 1s 557ms/step - loss: 0.0819 - val_loss: 0.0830
+    Epoch 49/100
+    1/1 [==============================] - 1s 554ms/step - loss: 0.0815 - val_loss: 0.0826
+    Epoch 50/100
+    1/1 [==============================] - 1s 553ms/step - loss: 0.0812 - val_loss: 0.0822
+    Epoch 51/100
+    1/1 [==============================] - 1s 544ms/step - loss: 0.0810 - val_loss: 0.0819
+    Epoch 52/100
+    1/1 [==============================] - 1s 568ms/step - loss: 0.0808 - val_loss: 0.0817
+    Epoch 53/100
+    1/1 [==============================] - 1s 572ms/step - loss: 0.0808 - val_loss: 0.0816
+    Epoch 54/100
+    1/1 [==============================] - 1s 530ms/step - loss: 0.0807 - val_loss: 0.0815
+    Epoch 55/100
+    1/1 [==============================] - 1s 557ms/step - loss: 0.0808 - val_loss: 0.0815
+    Epoch 56/100
+    1/1 [==============================] - 1s 549ms/step - loss: 0.0808 - val_loss: 0.0814
+    Epoch 57/100
+    1/1 [==============================] - 1s 575ms/step - loss: 0.0808 - val_loss: 0.0813
+    Epoch 58/100
+    1/1 [==============================] - 1s 554ms/step - loss: 0.0807 - val_loss: 0.0812
+    Epoch 59/100
+    1/1 [==============================] - 1s 556ms/step - loss: 0.0806 - val_loss: 0.0811
+    Epoch 60/100
+    1/1 [==============================] - 1s 588ms/step - loss: 0.0805 - val_loss: 0.0810
+    Epoch 61/100