From 63aae23e80afd77fa60ab674d84c0ea0e19902d6 Mon Sep 17 00:00:00 2001
From: Indrakanti Aishwarya <cb.en.p2cys21014@cb.students.amrita.edu>
Date: Thu, 10 Aug 2023 14:45:44 +0530
Subject: [PATCH] Upload New File
---
LCB/LCB_Dynamic_0000836F.ipynb | 996 +++++++++++++++++++++++++++++++++
1 file changed, 996 insertions(+)
create mode 100644 LCB/LCB_Dynamic_0000836F.ipynb
diff --git a/LCB/LCB_Dynamic_0000836F.ipynb b/LCB/LCB_Dynamic_0000836F.ipynb
new file mode 100644
index 0000000..730be59
--- /dev/null
+++ b/LCB/LCB_Dynamic_0000836F.ipynb
@@ -0,0 +1,996 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#1#Header\n",
+ "import csv\n",
+ "import numpy as np\n",
+ "import os \n",
+ "from os import urandom\n",
+ "from keras.models import model_from_json"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#2#Defining Global Variables\n",
+ "num_rounds = 10\n",
+ "m = 0\n",
+ "o = 0"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#3#Defining WORDSIZE\n",
+ "def WORD_SIZE():\n",
+ " return(16);"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#4#Defining S-Box\n",
+ "s_box_mapping_np = np.array([0, 4, 1, 5, 2, 6, 3, 7, 8, 12, 9, 13, 10, 14, 11, 15], dtype=np.uint8)\n",
+ "\n",
+ "def s_box(input_bits):\n",
+ " input_bits_int = int(input_bits)\n",
+ " output_bits_int = s_box_mapping_np[input_bits_int]\n",
+ " return output_bits_int"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#5#Defining P-Box\n",
+ "def decimal_to_binary_list(value, num_bits=4):\n",
+ " return np.array([int(x) for x in format(value, f'0{num_bits}b')], dtype=np.uint8)\n",
+ "\n",
+ "def p_box(c_decimal, d_decimal):\n",
+ " c = decimal_to_binary_list(c_decimal)\n",
+ " d = decimal_to_binary_list(d_decimal)\n",
+ "\n",
+ " e = np.zeros(8, dtype=np.uint8)\n",
+ "\n",
+ " e[0] = c[0]\n",
+ " e[1] = d[0]\n",
+ " e[2] = c[3]\n",
+ " e[3] = d[3]\n",
+ " e[4] = c[1]\n",
+ " e[5] = d[1]\n",
+ " e[6] = c[2]\n",
+ " e[7] = d[2]\n",
+ "\n",
+ " return e"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#6#Defining L-Box\n",
+ "def l_box(f, g):\n",
+ " if len(f) != 8 or len(g) != 8:\n",
+ " raise ValueError(\"Both input arrays f and g should have exactly 8 elements\")\n",
+ "\n",
+ " h = np.zeros(16, dtype=np.uint8)\n",
+ " h[0] = f[0]\n",
+ " h[1] = g[0]\n",
+ " h[2] = f[7]\n",
+ " h[3] = g[7]\n",
+ " h[4] = f[1]\n",
+ " h[5] = g[1]\n",
+ " h[6] = f[6]\n",
+ " h[7] = g[6]\n",
+ " h[8] = f[2]\n",
+ " h[9] = g[2]\n",
+ " h[10] = f[5]\n",
+ " h[11] = g[5]\n",
+ " h[12] = f[3]\n",
+ " h[13] = g[3]\n",
+ " h[14] = f[4]\n",
+ " h[15] = g[4]\n",
+ " #print(h)\n",
+ " return h"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#7#Defining F-function for Right Side of Plaintext\n",
+ "def binary_array_to_integer(output):\n",
+ " int_output = ''.join(map(str, output))\n",
+ " return int(int_output, 2)\n",
+ "\n",
+ "def f_function(x, key, d):\n",
+ " q=0\n",
+ " global m\n",
+ " if isinstance(x, int):\n",
+ " x = [x]\n",
+ " input_parts = np.zeros((len(x), 4), dtype=np.uint16)\n",
+ " for i, val in enumerate(x):\n",
+ " input_parts[i] = np.array([val >> 12, (val >> 8) & 0xF, (val >> 4) & 0xF, val & 0xF])\n",
+ " \n",
+ " s_box_outputs = np.array([[s_box(element) for element in part] for part in input_parts])\n",
+ " p_box_outputs = np.zeros((len(x), 2, 8), dtype=np.uint8)\n",
+ " for i in range(len(x)):\n",
+ " p_box_outputs[i] = np.array([p_box(s_box_outputs[i][0], s_box_outputs[i][1]), p_box(s_box_outputs[i][2], s_box_outputs[i][3])])\n",
+ " \n",
+ " final_outputs = np.zeros(len(x), dtype=np.uint32)\n",
+ " for i in range(len(x)):\n",
+ " final_output = np.array(l_box(p_box_outputs[i][0], p_box_outputs[i][1]))\n",
+ " k = key[q][(m+1) % 4]\n",
+ " output = final_output ^ k\n",
+ " output = binary_array_to_integer(output)\n",
+ " final_outputs[i] = output\n",
+ " q +=1 \n",
+ " if (m < 2):\n",
+ " m +=2\n",
+ " else:\n",
+ " m = 0\n",
+ " return final_outputs"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#8#Defining F-function for Left Side of Plaintext\n",
+ "def binary_array_to_integer(output):\n",
+ " int_output = ''.join(map(str, output))\n",
+ " return int(int_output, 2)\n",
+ "\n",
+ "def ff_function(x, key, d):\n",
+ " q=0\n",
+ " global o\n",
+ " if isinstance(x, int):\n",
+ " x = [x]\n",
+ " \n",
+ " input_parts = np.zeros((len(x), 4), dtype=np.uint16)\n",
+ " for i, val in enumerate(x):\n",
+ " input_parts[i] = np.array([val >> 12, (val >> 8) & 0xF, (val >> 4) & 0xF, val & 0xF])\n",
+ " \n",
+ " s_box_outputs = np.array([[s_box(element) for element in part] for part in input_parts])\n",
+ " p_box_outputs = np.zeros((len(x), 2, 8), dtype=np.uint8)\n",
+ " for i in range(len(x)):\n",
+ " p_box_outputs[i] = np.array([p_box(s_box_outputs[i][0], s_box_outputs[i][1]), p_box(s_box_outputs[i][2], s_box_outputs[i][3])])\n",
+ " \n",
+ " final_outputs = np.zeros(len(x), dtype=np.uint32)\n",
+ " for i in range(len(x)):\n",
+ " final_output = np.array(l_box(p_box_outputs[i][0], p_box_outputs[i][1]))\n",
+ " k = key[q][o % 4]\n",
+ " output = final_output ^ k\n",
+ " output = binary_array_to_integer(output)\n",
+ " final_outputs[i] = output\n",
+ " q +=1 \n",
+ " if (o < 2):\n",
+ " o +=2\n",
+ " else:\n",
+ " o = 0\n",
+ " return final_outputs"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#9#Convert the ciphertext pairs into Binary array\n",
+ "def convert_to_binary(row):\n",
+ " bin_array = np.zeros(64, dtype=np.uint8)\n",
+ " for i, num in enumerate(row):\n",
+ " binary_str = format(num, '016b')\n",
+ " for j, b in enumerate(binary_str):\n",
+ " bin_array[i * 16 + j] = int(b)\n",
+ " return bin_array"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#10#Encryption Function\n",
+ "def lcb_encrypt(plaintext, key, rounds, d):\n",
+ " \n",
+ " left_plaintext = np.uint16(plaintext[0])\n",
+ " right_plaintext = np.uint16(plaintext[1])\n",
+ " L, R = left_plaintext, right_plaintext\n",
+ "\n",
+ " n = 0\n",
+ " \n",
+ " while n < rounds:\n",
+ " L, R = f_function(R, key, d), ff_function(L, key, d)\n",
+ " n += 1\n",
+ " \n",
+ " return (L, R)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#11#Fuction for generation of keys\n",
+ "import random\n",
+ "\n",
+ "def generate_hex_keys(num_keys, length=16):\n",
+ " hex_chars = \"0123456789ABCDEF\"\n",
+ " keys_str = [\"\".join(random.choices(hex_chars, k=length)) for _ in range(num_keys)]\n",
+ "\n",
+ " return keys_str\n",
+ "\n",
+ "\n",
+ "def to_binary(value, bits):\n",
+ " return format(value, f'0{bits}b')\n",
+ "\n",
+ "def generate_round_keys(num_keys):\n",
+ " random_keys_hex = generate_hex_keys(num_keys)\n",
+ " round_keys = []\n",
+ " \n",
+ " for random_key_hex in random_keys_hex:\n",
+ " random_key = int(random_key_hex, 16)\n",
+ "\n",
+ " K1 = (random_key >> 48) & 0xFFFF\n",
+ " K2 = (random_key >> 32) & 0xFFFF\n",
+ " K3 = (random_key >> 16) & 0xFFFF\n",
+ " K4 = random_key & 0xFFFF\n",
+ " \n",
+ " k1_bin = to_binary(K1, 16)\n",
+ " k2_bin = to_binary(K2, 16)\n",
+ " k3_bin = to_binary(K3, 16)\n",
+ " k4_bin = to_binary(K4, 16)\n",
+ "\n",
+ " k1_np_array = np.array([int(bit) for bit in k1_bin])\n",
+ " k2_np_array = np.array([int(bit) for bit in k2_bin])\n",
+ " k3_np_array = np.array([int(bit) for bit in k3_bin])\n",
+ " k4_np_array = np.array([int(bit) for bit in k4_bin])\n",
+ "\n",
+ " round_key = np.array([k1_np_array, k2_np_array, k3_np_array, k4_np_array])\n",
+ " round_keys.append(round_key)\n",
+ " round_key = np.array(round_keys)\n",
+ " \n",
+ " return round_key"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#12#Make dataset\n",
+ "\n",
+ "def make_train_data(n, nr, diff=(0,0x836F)):\n",
+ " Y = np.frombuffer(urandom(n), dtype=np.uint8); \n",
+ " Y = Y & 1;\n",
+ " plaintext = np.frombuffer(urandom(4*n), dtype=np.uint32);\n",
+ " plain0l = np.empty(n, dtype=np.uint16)\n",
+ " plain0r = np.empty(n, dtype=np.uint16)\n",
+ " \n",
+ " for i in range(n):\n",
+ " plain0l[i] = (plaintext[i] >> 16) & 0xffff\n",
+ " plain0r[i] = plaintext[i] & 0xffff\n",
+ " \n",
+ " plain1l = plain0l ^ diff[0]; plain1r = plain0r ^ diff[1];\n",
+ " \n",
+ " num_rand_samples = np.sum(Y==0);\n",
+ " plain1l[Y==0] = np.frombuffer(urandom(2*num_rand_samples),dtype=np.uint16);\n",
+ " plain1r[Y==0] = np.frombuffer(urandom(2*num_rand_samples),dtype=np.uint16);\n",
+ " \n",
+ " round_key = generate_round_keys(n)\n",
+ " \n",
+ " ctdata0l, ctdata0r = lcb_encrypt((plain0l, plain0r), round_key, nr, n)\n",
+ " ctdata1l, ctdata1r = lcb_encrypt((plain1l, plain1r), round_key, nr, n)\n",
+ " \n",
+ " ctdata = np.vstack((ctdata0l, ctdata0r, ctdata1l, ctdata1r)).T\n",
+ " X = np.array([convert_to_binary(row) for row in ctdata])\n",
+ " \n",
+ "\n",
+ " with open(\"VDataset_NewP.csv\", \"w\", newline='') as f:\n",
+ " writer = csv.writer(f)\n",
+ " writer.writerow([\"plain0l\", \"plain0r\", \"plain1l\", \"plain1r\",\"Y\"])\n",
+ " for i in range(n):\n",
+ " writer.writerow([plain0l[i], plain0r[i], plain1l[i], plain1r[i],Y[i]])\n",
+ "\n",
+ " with open(\"VDataset_NewC.csv\", \"w\", newline='') as f:\n",
+ " writer = csv.writer(f)\n",
+ " writer.writerow([\"ctdata0l\", \"ctdata0r\", \"ctdata1l\", \"ctdata1r\",\"Y\"])\n",
+ " for i in range(n):\n",
+ " writer.writerow([ctdata0l[i], ctdata0r[i], ctdata1l[i], ctdata1r[i],Y[i]])\n",
+ " \n",
+ " return(X,Y);"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(array([[1, 1, 0, ..., 0, 1, 0],\n",
+ " [0, 0, 0, ..., 1, 0, 1],\n",
+ " [1, 1, 1, ..., 1, 1, 0],\n",
+ " ...,\n",
+ " [0, 1, 0, ..., 0, 1, 0],\n",
+ " [1, 0, 1, ..., 0, 0, 0],\n",
+ " [1, 0, 0, ..., 1, 0, 0]], dtype=uint8),\n",
+ " array([1, 1, 1, ..., 0, 0, 0], dtype=uint8))"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "make_train_data(10**5, num_rounds)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#13#Creation of Model\n",
+ "\n",
+ "from pickle import dump\n",
+ "\n",
+ "from keras.callbacks import ModelCheckpoint, LearningRateScheduler\n",
+ "from keras.models import Model\n",
+ "from keras.optimizers import Adam\n",
+ "from keras.layers import Dense, Conv1D, Input, Reshape, Permute, Add, Flatten, BatchNormalization, Activation\n",
+ "from keras import backend as K\n",
+ "from keras.regularizers import l2\n",
+ "\n",
+ "bs = 5000;\n",
+ "wdir = './freshly_trained_nets/'\n",
+ "\n",
+ "def cyclic_lr(num_epochs, high_lr, low_lr):\n",
+ " res = lambda i: low_lr + ((num_epochs-1) - i % num_epochs)/(num_epochs-1) * (high_lr - low_lr);\n",
+ " return(res);\n",
+ "\n",
+ "def make_checkpoint(datei):\n",
+ " res = ModelCheckpoint(datei, monitor='val_loss', save_best_only = True);\n",
+ " return(res);\n",
+ "\n",
+ "#make residual tower of convolutional blocks\n",
+ "def make_resnet(num_blocks=2, num_filters=32, num_outputs=1, d1=64, d2=64, word_size=16, ks=3,depth=5, reg_param=0.0001, final_activation='sigmoid'):\n",
+ " #Input and preprocessing layers\n",
+ " inp = Input(shape=(num_blocks * word_size * 2,));\n",
+ " rs = Reshape((2 * num_blocks, word_size))(inp);\n",
+ " perm = Permute((2,1))(rs);\n",
+ " #add a single residual layer that will expand the data to num_filters channels\n",
+ " #this is a bit-sliced layer\n",
+ " conv0 = Conv1D(num_filters, kernel_size=1, padding='same', kernel_regularizer=l2(reg_param))(perm);\n",
+ " conv0 = BatchNormalization()(conv0);\n",
+ " conv0 = Activation('relu')(conv0);\n",
+ " #add residual blocks\n",
+ " shortcut = conv0;\n",
+ " for i in range(depth):\n",
+ " conv1 = Conv1D(num_filters, kernel_size=ks, padding='same', kernel_regularizer=l2(reg_param))(shortcut);\n",
+ " conv1 = BatchNormalization()(conv1);\n",
+ " conv1 = Activation('relu')(conv1);\n",
+ " conv2 = Conv1D(num_filters, kernel_size=ks, padding='same',kernel_regularizer=l2(reg_param))(conv1);\n",
+ " conv2 = BatchNormalization()(conv2);\n",
+ " conv2 = Activation('relu')(conv2);\n",
+ " shortcut = Add()([shortcut, conv2]);\n",
+ " #add prediction head\n",
+ " flat1 = Flatten()(shortcut);\n",
+ " dense1 = Dense(d1,kernel_regularizer=l2(reg_param))(flat1);\n",
+ " dense1 = BatchNormalization()(dense1);\n",
+ " dense1 = Activation('relu')(dense1);\n",
+ " dense2 = Dense(d2, kernel_regularizer=l2(reg_param))(dense1);\n",
+ " dense2 = BatchNormalization()(dense2);\n",
+ " dense2 = Activation('relu')(dense2);\n",
+ " out = Dense(num_outputs, activation=final_activation, kernel_regularizer=l2(reg_param))(dense2);\n",
+ " model = Model(inputs=inp, outputs=out);\n",
+ " return(model);\n",
+ "\n",
+ "def train_LCB_distinguisher(num_epochs, num_rounds, depth):\n",
+ " #create the network\n",
+ " print(num_rounds)\n",
+ " print(depth)\n",
+ " net = make_resnet(depth=depth, reg_param=10**-5);\n",
+ " net.compile(optimizer='adam',loss='mse',metrics=['acc']);\n",
+ " #generate training and validation data\n",
+ " X, Y = make_train_data(10**6,num_rounds);\n",
+ " X_eval, Y_eval = make_train_data(10**5, num_rounds);\n",
+ " #set up model checkpoint\n",
+ " check = make_checkpoint(wdir+'ghor_Rk_0000_836F_Round_'+str(num_rounds)+'_depth_'+str(depth)+'.h5');\n",
+ " #create learnrate schedule\n",
+ " lr = LearningRateScheduler(cyclic_lr(10,0.002, 0.0001));\n",
+ " #train and evaluate\n",
+ " #print(X_eval)\n",
+ " h = net.fit(X,Y,epochs=num_epochs,batch_size=bs,validation_data=(X_eval, Y_eval), callbacks=[lr,check]);\n",
+ " np.save(wdir+'h'+str(num_rounds)+'r_depth'+str(depth)+'.npy', h.history['val_acc']);\n",
+ " np.save(wdir+'h'+str(num_rounds)+'r_depth'+str(depth)+'.npy', h.history['val_loss']);\n",
+ " dump(h.history,open(wdir+'hist'+str(num_rounds)+'r_depth'+str(depth)+'.p','wb'));\n",
+ " print(\"Best validation accuracy: \", np.max(h.history['val_acc']));\n",
+ " return(net, h);\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "10\n",
+ "10\n",
+ "Epoch 1/200\n",
+ "200/200 [==============================] - 185s 909ms/step - loss: 0.0114 - acc: 0.9959 - val_loss: 0.0240 - val_acc: 0.9776 - lr: 0.0020\n",
+ "Epoch 2/200\n",
+ "200/200 [==============================] - 182s 909ms/step - loss: 0.0064 - acc: 1.0000 - val_loss: 0.0056 - val_acc: 0.9999 - lr: 0.0018\n",
+ "Epoch 3/200\n",
+ "200/200 [==============================] - 190s 951ms/step - loss: 0.0049 - acc: 1.0000 - val_loss: 0.0044 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 4/200\n",
+ "200/200 [==============================] - 183s 916ms/step - loss: 0.0038 - acc: 1.0000 - val_loss: 0.0037 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 5/200\n",
+ "200/200 [==============================] - 183s 914ms/step - loss: 0.0030 - acc: 1.0000 - val_loss: 0.0030 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 6/200\n",
+ "200/200 [==============================] - 185s 923ms/step - loss: 0.0024 - acc: 1.0000 - val_loss: 0.0023 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 7/200\n",
+ "200/200 [==============================] - 183s 916ms/step - loss: 0.0020 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 8/200\n",
+ "200/200 [==============================] - 180s 902ms/step - loss: 0.0017 - acc: 1.0000 - val_loss: 0.0017 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 9/200\n",
+ "200/200 [==============================] - 181s 903ms/step - loss: 0.0016 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 10/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 0.0015 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 11/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 0.0011 - acc: 1.0000 - val_loss: 0.4747 - val_acc: 0.5018 - lr: 0.0020\n",
+ "Epoch 12/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 6.9676e-04 - acc: 1.0000 - val_loss: 0.1912 - val_acc: 0.6449 - lr: 0.0018\n",
+ "Epoch 13/200\n",
+ "200/200 [==============================] - 186s 931ms/step - loss: 5.0213e-04 - acc: 1.0000 - val_loss: 8.2996e-04 - val_acc: 0.9995 - lr: 0.0016\n",
+ "Epoch 14/200\n",
+ "200/200 [==============================] - 181s 908ms/step - loss: 3.9845e-04 - acc: 1.0000 - val_loss: 0.3903 - val_acc: 0.5018 - lr: 0.0014\n",
+ "Epoch 15/200\n",
+ "200/200 [==============================] - 183s 915ms/step - loss: 2.6665e-04 - acc: 1.0000 - val_loss: 0.4915 - val_acc: 0.5018 - lr: 0.0012\n",
+ "Epoch 16/200\n",
+ "200/200 [==============================] - 182s 910ms/step - loss: 2.0211e-04 - acc: 1.0000 - val_loss: 0.4945 - val_acc: 0.5018 - lr: 9.4444e-04\n",
+ "Epoch 17/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 1.6426e-04 - acc: 1.0000 - val_loss: 0.4659 - val_acc: 0.5018 - lr: 7.3333e-04\n",
+ "Epoch 18/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 1.4096e-04 - acc: 1.0000 - val_loss: 0.1450 - val_acc: 0.7232 - lr: 5.2222e-04\n",
+ "Epoch 19/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 1.2714e-04 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 20/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 1.2059e-04 - acc: 1.0000 - val_loss: 1.2217e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 21/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 0.0044 - acc: 0.9980 - val_loss: 0.0059 - val_acc: 0.9974 - lr: 0.0020\n",
+ "Epoch 22/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 0.0037 - acc: 1.0000 - val_loss: 0.0036 - val_acc: 1.0000 - lr: 0.0018\n",
+ "Epoch 23/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 0.0034 - acc: 1.0000 - val_loss: 0.0033 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 24/200\n",
+ "200/200 [==============================] - 181s 903ms/step - loss: 0.0032 - acc: 1.0000 - val_loss: 0.0031 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 25/200\n",
+ "200/200 [==============================] - 181s 903ms/step - loss: 0.0031 - acc: 1.0000 - val_loss: 0.0030 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 26/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 0.0029 - acc: 1.0000 - val_loss: 0.0029 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 27/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 0.0028 - acc: 1.0000 - val_loss: 0.0028 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 28/200\n",
+ "200/200 [==============================] - 181s 903ms/step - loss: 0.0027 - acc: 1.0000 - val_loss: 0.0027 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 29/200\n",
+ "200/200 [==============================] - 180s 902ms/step - loss: 0.0027 - acc: 1.0000 - val_loss: 0.0027 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 30/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 0.0026 - acc: 1.0000 - val_loss: 0.0026 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 31/200\n",
+ "200/200 [==============================] - 183s 917ms/step - loss: 0.0025 - acc: 1.0000 - val_loss: 0.0034 - val_acc: 1.0000 - lr: 0.0020\n",
+ "Epoch 32/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 0.0022 - acc: 1.0000 - val_loss: 0.0025 - val_acc: 1.0000 - lr: 0.0018\n",
+ "Epoch 33/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 0.0020 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 34/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 0.0018 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 35/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 0.0017 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 36/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 0.0016 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 37/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 0.0015 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 38/200\n",
+ "200/200 [==============================] - 182s 909ms/step - loss: 0.0014 - acc: 1.0000 - val_loss: 0.0014 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 39/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 0.0014 - acc: 1.0000 - val_loss: 0.0014 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 40/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 0.0013 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 41/200\n",
+ "200/200 [==============================] - 182s 909ms/step - loss: 0.0012 - acc: 1.0000 - val_loss: 0.0375 - val_acc: 0.9868 - lr: 0.0020\n",
+ "Epoch 42/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 0.0010 - acc: 1.0000 - val_loss: 0.1601 - val_acc: 0.6503 - lr: 0.0018\n",
+ "Epoch 43/200\n",
+ "200/200 [==============================] - 182s 909ms/step - loss: 8.7272e-04 - acc: 1.0000 - val_loss: 0.0358 - val_acc: 0.9965 - lr: 0.0016\n",
+ "Epoch 44/200\n",
+ "200/200 [==============================] - 199s 996ms/step - loss: 7.5967e-04 - acc: 1.0000 - val_loss: 0.2835 - val_acc: 0.5024 - lr: 0.0014\n",
+ "Epoch 45/200\n",
+ "200/200 [==============================] - 187s 934ms/step - loss: 6.7187e-04 - acc: 1.0000 - val_loss: 0.0131 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 46/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 6.0448e-04 - acc: 1.0000 - val_loss: 0.0045 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 47/200\n",
+ "200/200 [==============================] - 187s 938ms/step - loss: 5.5327e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 48/200\n",
+ "200/200 [==============================] - 204s 1s/step - loss: 5.1591e-04 - acc: 1.0000 - val_loss: 5.5068e-04 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 49/200\n",
+ "200/200 [==============================] - 191s 956ms/step - loss: 4.9090e-04 - acc: 1.0000 - val_loss: 5.0161e-04 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 50/200\n",
+ "200/200 [==============================] - 187s 934ms/step - loss: 4.7809e-04 - acc: 1.0000 - val_loss: 4.7770e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 51/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 0.0014 - acc: 0.9998 - val_loss: 0.1151 - val_acc: 0.8641 - lr: 0.0020\n",
+ "Epoch 52/200\n",
+ "200/200 [==============================] - 187s 934ms/step - loss: 9.5738e-04 - acc: 1.0000 - val_loss: 0.3482 - val_acc: 0.5020 - lr: 0.0018\n",
+ "Epoch 53/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 6.7179e-04 - acc: 1.0000 - val_loss: 0.4190 - val_acc: 0.5018 - lr: 0.0016\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Epoch 54/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 5.1030e-04 - acc: 1.0000 - val_loss: 0.3700 - val_acc: 0.5019 - lr: 0.0014\n",
+ "Epoch 55/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 4.0714e-04 - acc: 1.0000 - val_loss: 0.2277 - val_acc: 0.5630 - lr: 0.0012\n",
+ "Epoch 56/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 3.3943e-04 - acc: 1.0000 - val_loss: 0.0590 - val_acc: 0.9308 - lr: 9.4444e-04\n",
+ "Epoch 57/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 2.9440e-04 - acc: 1.0000 - val_loss: 0.0220 - val_acc: 0.9963 - lr: 7.3333e-04\n",
+ "Epoch 58/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 2.6228e-04 - acc: 1.0000 - val_loss: 4.3736e-04 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 59/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 2.4230e-04 - acc: 1.0000 - val_loss: 2.6776e-04 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 60/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 2.3241e-04 - acc: 1.0000 - val_loss: 2.3119e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 61/200\n",
+ "200/200 [==============================] - 180s 902ms/step - loss: 3.1112e-04 - acc: 1.0000 - val_loss: 8.1905e-04 - val_acc: 0.9997 - lr: 0.0020\n",
+ "Epoch 62/200\n",
+ "200/200 [==============================] - 181s 903ms/step - loss: 3.3318e-04 - acc: 1.0000 - val_loss: 0.4971 - val_acc: 0.5018 - lr: 0.0018\n",
+ "Epoch 63/200\n",
+ "200/200 [==============================] - 183s 914ms/step - loss: 1.6852e-04 - acc: 1.0000 - val_loss: 0.4981 - val_acc: 0.5018 - lr: 0.0016\n",
+ "Epoch 64/200\n",
+ "200/200 [==============================] - 187s 934ms/step - loss: 1.1411e-04 - acc: 1.0000 - val_loss: 0.4975 - val_acc: 0.5018 - lr: 0.0014\n",
+ "Epoch 65/200\n",
+ "200/200 [==============================] - 189s 943ms/step - loss: 8.4985e-05 - acc: 1.0000 - val_loss: 0.4952 - val_acc: 0.5018 - lr: 0.0012\n",
+ "Epoch 66/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 1.0603e-04 - acc: 1.0000 - val_loss: 0.0023 - val_acc: 0.9974 - lr: 9.4444e-04\n",
+ "Epoch 67/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 1.2690e-04 - acc: 1.0000 - val_loss: 0.0074 - val_acc: 0.9999 - lr: 7.3333e-04\n",
+ "Epoch 68/200\n",
+ "200/200 [==============================] - 187s 933ms/step - loss: 8.4066e-05 - acc: 1.0000 - val_loss: 0.0879 - val_acc: 0.8975 - lr: 5.2222e-04\n",
+ "Epoch 69/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 6.8841e-05 - acc: 1.0000 - val_loss: 5.1311e-04 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 70/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 6.3039e-05 - acc: 1.0000 - val_loss: 6.8196e-05 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 71/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 2.2853e-04 - acc: 1.0000 - val_loss: 0.5024 - val_acc: 0.4984 - lr: 0.0020\n",
+ "Epoch 72/200\n",
+ "200/200 [==============================] - 180s 900ms/step - loss: 4.0886e-04 - acc: 1.0000 - val_loss: 0.4943 - val_acc: 0.5018 - lr: 0.0018\n",
+ "Epoch 73/200\n",
+ "200/200 [==============================] - 183s 913ms/step - loss: 1.9104e-04 - acc: 1.0000 - val_loss: 0.4975 - val_acc: 0.5018 - lr: 0.0016\n",
+ "Epoch 74/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 1.1183e-04 - acc: 1.0000 - val_loss: 0.4980 - val_acc: 0.5018 - lr: 0.0014\n",
+ "Epoch 75/200\n",
+ "200/200 [==============================] - 188s 939ms/step - loss: 6.2444e-05 - acc: 1.0000 - val_loss: 0.4977 - val_acc: 0.5018 - lr: 0.0012\n",
+ "Epoch 76/200\n",
+ "200/200 [==============================] - 189s 943ms/step - loss: 4.3502e-05 - acc: 1.0000 - val_loss: 0.4976 - val_acc: 0.5018 - lr: 9.4444e-04\n",
+ "Epoch 77/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 3.2875e-05 - acc: 1.0000 - val_loss: 0.4972 - val_acc: 0.5018 - lr: 7.3333e-04\n",
+ "Epoch 78/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 2.6406e-05 - acc: 1.0000 - val_loss: 0.4931 - val_acc: 0.5018 - lr: 5.2222e-04\n",
+ "Epoch 79/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 2.3363e-05 - acc: 1.0000 - val_loss: 0.4424 - val_acc: 0.5018 - lr: 3.1111e-04\n",
+ "Epoch 80/200\n",
+ "200/200 [==============================] - 184s 920ms/step - loss: 2.2037e-05 - acc: 1.0000 - val_loss: 2.0193e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 81/200\n",
+ "200/200 [==============================] - 193s 966ms/step - loss: 1.7932e-05 - acc: 1.0000 - val_loss: 0.4637 - val_acc: 0.5018 - lr: 0.0020\n",
+ "Epoch 82/200\n",
+ "200/200 [==============================] - 189s 944ms/step - loss: 0.0020 - acc: 0.9994 - val_loss: 0.5345 - val_acc: 0.4482 - lr: 0.0018\n",
+ "Epoch 83/200\n",
+ "200/200 [==============================] - 182s 910ms/step - loss: 0.0025 - acc: 1.0000 - val_loss: 0.0024 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 84/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 0.0023 - acc: 1.0000 - val_loss: 0.0022 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 85/200\n",
+ "200/200 [==============================] - 186s 930ms/step - loss: 0.0022 - acc: 1.0000 - val_loss: 0.0021 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 86/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 0.0020 - acc: 1.0000 - val_loss: 0.0020 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 87/200\n",
+ "200/200 [==============================] - 182s 910ms/step - loss: 0.0019 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 88/200\n",
+ "200/200 [==============================] - 183s 915ms/step - loss: 0.0019 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 89/200\n",
+ "200/200 [==============================] - 183s 914ms/step - loss: 0.0018 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 90/200\n",
+ "200/200 [==============================] - 182s 911ms/step - loss: 0.0018 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 91/200\n",
+ "200/200 [==============================] - 182s 912ms/step - loss: 0.0017 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 1.0000 - lr: 0.0020\n",
+ "Epoch 92/200\n",
+ "200/200 [==============================] - 182s 910ms/step - loss: 0.0015 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 1.0000 - lr: 0.0018\n",
+ "Epoch 93/200\n",
+ "200/200 [==============================] - 182s 911ms/step - loss: 0.0013 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 94/200\n",
+ "200/200 [==============================] - 185s 925ms/step - loss: 0.0012 - acc: 1.0000 - val_loss: 0.0012 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 95/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 0.0011 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 96/200\n",
+ "200/200 [==============================] - 180s 902ms/step - loss: 0.0010 - acc: 1.0000 - val_loss: 0.0010 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 97/200\n",
+ "200/200 [==============================] - 180s 902ms/step - loss: 9.7535e-04 - acc: 1.0000 - val_loss: 9.5283e-04 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 98/200\n",
+ "200/200 [==============================] - 180s 901ms/step - loss: 9.2974e-04 - acc: 1.0000 - val_loss: 9.1339e-04 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 99/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 8.9887e-04 - acc: 1.0000 - val_loss: 8.8789e-04 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 100/200\n",
+ "200/200 [==============================] - 187s 934ms/step - loss: 8.8294e-04 - acc: 1.0000 - val_loss: 8.7880e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 101/200\n",
+ "200/200 [==============================] - 180s 902ms/step - loss: 0.0012 - acc: 0.9999 - val_loss: 0.0013 - val_acc: 0.9998 - lr: 0.0020\n",
+ "Epoch 102/200\n",
+ "200/200 [==============================] - 180s 902ms/step - loss: 0.0010 - acc: 1.0000 - val_loss: 9.3628e-04 - val_acc: 1.0000 - lr: 0.0018\n",
+ "Epoch 103/200\n",
+ "200/200 [==============================] - 179s 897ms/step - loss: 8.4824e-04 - acc: 1.0000 - val_loss: 8.5005e-04 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 104/200\n",
+ "200/200 [==============================] - 180s 900ms/step - loss: 7.1619e-04 - acc: 1.0000 - val_loss: 7.0104e-04 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 105/200\n",
+ "200/200 [==============================] - 214s 1s/step - loss: 6.2045e-04 - acc: 1.0000 - val_loss: 6.2361e-04 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 106/200\n",
+ "200/200 [==============================] - 183s 915ms/step - loss: 5.5093e-04 - acc: 1.0000 - val_loss: 5.3495e-04 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 107/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 4.9948e-04 - acc: 1.0000 - val_loss: 4.9466e-04 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 108/200\n",
+ "200/200 [==============================] - 187s 935ms/step - loss: 4.6283e-04 - acc: 1.0000 - val_loss: 5.3213e-04 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 109/200\n",
+ "200/200 [==============================] - 188s 941ms/step - loss: 4.3871e-04 - acc: 1.0000 - val_loss: 4.3065e-04 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 110/200\n",
+ "200/200 [==============================] - 194s 973ms/step - loss: 4.2627e-04 - acc: 1.0000 - val_loss: 4.2329e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 111/200\n",
+ "200/200 [==============================] - 206s 1s/step - loss: 3.6728e-04 - acc: 1.0000 - val_loss: 0.0929 - val_acc: 0.8698 - lr: 0.0020\n",
+ "Epoch 112/200\n",
+ "200/200 [==============================] - 214s 1s/step - loss: 2.8893e-04 - acc: 1.0000 - val_loss: 2.6767e-04 - val_acc: 1.0000 - lr: 0.0018\n",
+ "Epoch 113/200\n",
+ "200/200 [==============================] - 214s 1s/step - loss: 2.3273e-04 - acc: 1.0000 - val_loss: 0.1472 - val_acc: 0.6903 - lr: 0.0016\n",
+ "Epoch 114/200\n",
+ "200/200 [==============================] - 213s 1s/step - loss: 1.8670e-04 - acc: 1.0000 - val_loss: 0.1450 - val_acc: 0.7015 - lr: 0.0014\n",
+ "Epoch 115/200\n",
+ "200/200 [==============================] - 213s 1s/step - loss: 1.5695e-04 - acc: 1.0000 - val_loss: 0.0115 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 116/200\n",
+ "200/200 [==============================] - 214s 1s/step - loss: 1.3597e-04 - acc: 1.0000 - val_loss: 3.2649e-04 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 117/200\n",
+ "200/200 [==============================] - 214s 1s/step - loss: 1.2097e-04 - acc: 1.0000 - val_loss: 0.4788 - val_acc: 0.5018 - lr: 7.3333e-04\n",
+ "Epoch 118/200\n",
+ "200/200 [==============================] - 214s 1s/step - loss: 2.2300e-04 - acc: 1.0000 - val_loss: 2.4725e-04 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 119/200\n",
+ "200/200 [==============================] - 214s 1s/step - loss: 2.1805e-04 - acc: 1.0000 - val_loss: 2.0893e-04 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 120/200\n",
+ "200/200 [==============================] - 214s 1s/step - loss: 2.0614e-04 - acc: 1.0000 - val_loss: 2.0339e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 121/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 1.6093e-04 - acc: 1.0000 - val_loss: 0.4219 - val_acc: 0.5018 - lr: 0.0020\n",
+ "Epoch 122/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 1.1050e-04 - acc: 1.0000 - val_loss: 0.4460 - val_acc: 0.5018 - lr: 0.0018\n",
+ "Epoch 123/200\n",
+ "200/200 [==============================] - 183s 914ms/step - loss: 3.3806e-04 - acc: 1.0000 - val_loss: 2.9386e-04 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 124/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 1.9949e-04 - acc: 1.0000 - val_loss: 0.4264 - val_acc: 0.5018 - lr: 0.0014\n",
+ "Epoch 125/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 1.4096e-04 - acc: 1.0000 - val_loss: 0.2692 - val_acc: 0.5107 - lr: 0.0012\n",
+ "Epoch 126/200\n",
+ "200/200 [==============================] - 181s 903ms/step - loss: 1.0977e-04 - acc: 1.0000 - val_loss: 0.0105 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 127/200\n",
+ "200/200 [==============================] - 182s 909ms/step - loss: 9.1792e-05 - acc: 1.0000 - val_loss: 4.5129e-04 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 128/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 8.0692e-05 - acc: 1.0000 - val_loss: 1.1738e-04 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 129/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 7.4031e-05 - acc: 1.0000 - val_loss: 7.6682e-05 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 130/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 7.0827e-05 - acc: 1.0000 - val_loss: 7.0510e-05 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 131/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 5.6762e-05 - acc: 1.0000 - val_loss: 0.4818 - val_acc: 0.5018 - lr: 0.0020\n",
+ "Epoch 132/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 3.9235e-05 - acc: 1.0000 - val_loss: 0.4837 - val_acc: 0.5018 - lr: 0.0018\n",
+ "Epoch 133/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 2.9483e-05 - acc: 1.0000 - val_loss: 0.4621 - val_acc: 0.5018 - lr: 0.0016\n",
+ "Epoch 134/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 8.8404e-04 - acc: 0.9999 - val_loss: 9.7526e-04 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 135/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 8.3623e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 136/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 6.6218e-04 - acc: 1.0000 - val_loss: 0.0236 - val_acc: 0.9904 - lr: 9.4444e-04\n",
+ "Epoch 137/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 5.6179e-04 - acc: 1.0000 - val_loss: 8.9467e-04 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 138/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 4.9843e-04 - acc: 1.0000 - val_loss: 5.4970e-04 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 139/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 4.6030e-04 - acc: 1.0000 - val_loss: 4.5565e-04 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 140/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 4.4187e-04 - acc: 1.0000 - val_loss: 4.3794e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 141/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 3.5985e-04 - acc: 1.0000 - val_loss: 0.4717 - val_acc: 0.5018 - lr: 0.0020\n",
+ "Epoch 142/200\n",
+ "200/200 [==============================] - 212s 1s/step - loss: 2.5639e-04 - acc: 1.0000 - val_loss: 0.3537 - val_acc: 0.5018 - lr: 0.0018\n",
+ "Epoch 143/200\n",
+ "200/200 [==============================] - 190s 952ms/step - loss: 1.9486e-04 - acc: 1.0000 - val_loss: 0.0238 - val_acc: 0.9944 - lr: 0.0016\n",
+ "Epoch 144/200\n",
+ "200/200 [==============================] - 192s 961ms/step - loss: 1.5588e-04 - acc: 1.0000 - val_loss: 5.5978e-04 - val_acc: 0.9998 - lr: 0.0014\n",
+ "Epoch 145/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 1.2962e-04 - acc: 1.0000 - val_loss: 9.1726e-04 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 146/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 1.1111e-04 - acc: 1.0000 - val_loss: 2.5750e-04 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 147/200\n",
+ "200/200 [==============================] - 181s 903ms/step - loss: 9.8085e-05 - acc: 1.0000 - val_loss: 9.7593e-05 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 148/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 1.1093e-04 - acc: 1.0000 - val_loss: 0.6840 - val_acc: 0.2697 - lr: 5.2222e-04\n",
+ "Epoch 149/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 1.7264e-04 - acc: 1.0000 - val_loss: 1.5816e-04 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 150/200\n",
+ "200/200 [==============================] - 180s 902ms/step - loss: 1.5343e-04 - acc: 1.0000 - val_loss: 1.4886e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 151/200\n",
+ "200/200 [==============================] - 180s 900ms/step - loss: 1.1442e-04 - acc: 1.0000 - val_loss: 0.4817 - val_acc: 0.5018 - lr: 0.0020\n",
+ "Epoch 152/200\n",
+ "200/200 [==============================] - 180s 900ms/step - loss: 7.5607e-05 - acc: 1.0000 - val_loss: 0.4857 - val_acc: 0.5018 - lr: 0.0018\n",
+ "Epoch 153/200\n",
+ "200/200 [==============================] - 180s 900ms/step - loss: 5.0521e-05 - acc: 1.0000 - val_loss: 0.4959 - val_acc: 0.5018 - lr: 0.0016\n",
+ "Epoch 154/200\n",
+ "200/200 [==============================] - 182s 909ms/step - loss: 3.6988e-05 - acc: 1.0000 - val_loss: 0.4636 - val_acc: 0.5018 - lr: 0.0014\n",
+ "Epoch 155/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 2.9382e-05 - acc: 1.0000 - val_loss: 0.1145 - val_acc: 0.8209 - lr: 0.0012\n",
+ "Epoch 156/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 2.4769e-05 - acc: 1.0000 - val_loss: 5.0902e-04 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 157/200\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "200/200 [==============================] - 181s 904ms/step - loss: 2.1742e-05 - acc: 1.0000 - val_loss: 4.3060e-05 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 158/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 1.9691e-05 - acc: 1.0000 - val_loss: 2.2383e-05 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 159/200\n",
+ "200/200 [==============================] - 181s 903ms/step - loss: 1.8412e-05 - acc: 1.0000 - val_loss: 1.8346e-05 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 160/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 1.7785e-05 - acc: 1.0000 - val_loss: 1.7664e-05 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 161/200\n",
+ "200/200 [==============================] - 181s 904ms/step - loss: 0.0051 - acc: 0.9974 - val_loss: 0.0642 - val_acc: 0.9316 - lr: 0.0020\n",
+ "Epoch 162/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 0.0029 - acc: 1.0000 - val_loss: 0.0028 - val_acc: 1.0000 - lr: 0.0018\n",
+ "Epoch 163/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 0.0027 - acc: 1.0000 - val_loss: 0.0026 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 164/200\n",
+ "200/200 [==============================] - 181s 906ms/step - loss: 0.0025 - acc: 1.0000 - val_loss: 0.0025 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 165/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 0.0024 - acc: 1.0000 - val_loss: 0.0023 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 166/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 0.0023 - acc: 1.0000 - val_loss: 0.0022 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 167/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 0.0022 - acc: 1.0000 - val_loss: 0.0022 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 168/200\n",
+ "200/200 [==============================] - 181s 907ms/step - loss: 0.0022 - acc: 1.0000 - val_loss: 0.0021 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 169/200\n",
+ "200/200 [==============================] - 181s 905ms/step - loss: 0.0021 - acc: 1.0000 - val_loss: 0.0021 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 170/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 0.0021 - acc: 1.0000 - val_loss: 0.0021 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 171/200\n",
+ "200/200 [==============================] - 182s 908ms/step - loss: 0.0020 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 1.0000 - lr: 0.0020\n",
+ "Epoch 172/200\n",
+ "200/200 [==============================] - 182s 911ms/step - loss: 0.0018 - acc: 1.0000 - val_loss: 0.0017 - val_acc: 1.0000 - lr: 0.0018\n",
+ "Epoch 173/200\n",
+ "200/200 [==============================] - 183s 915ms/step - loss: 0.0017 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 174/200\n",
+ "200/200 [==============================] - 183s 917ms/step - loss: 0.0015 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 175/200\n",
+ "200/200 [==============================] - 184s 920ms/step - loss: 0.0015 - acc: 1.0000 - val_loss: 0.0014 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 176/200\n",
+ "200/200 [==============================] - 184s 918ms/step - loss: 0.0014 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 177/200\n",
+ "200/200 [==============================] - 183s 915ms/step - loss: 0.0013 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 178/200\n",
+ "200/200 [==============================] - 183s 913ms/step - loss: 0.0013 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 179/200\n",
+ "200/200 [==============================] - 182s 912ms/step - loss: 0.0013 - acc: 1.0000 - val_loss: 0.0012 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 180/200\n",
+ "200/200 [==============================] - 184s 918ms/step - loss: 0.0012 - acc: 1.0000 - val_loss: 0.0012 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 181/200\n",
+ "200/200 [==============================] - 187s 934ms/step - loss: 0.0012 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 1.0000 - lr: 0.0020\n",
+ "Epoch 182/200\n",
+ "200/200 [==============================] - 185s 927ms/step - loss: 0.0010 - acc: 1.0000 - val_loss: 9.6330e-04 - val_acc: 1.0000 - lr: 0.0018\n",
+ "Epoch 183/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 9.1766e-04 - acc: 1.0000 - val_loss: 8.7060e-04 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 184/200\n",
+ "200/200 [==============================] - 185s 927ms/step - loss: 8.3431e-04 - acc: 1.0000 - val_loss: 7.9592e-04 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 185/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 7.6764e-04 - acc: 1.0000 - val_loss: 7.3644e-04 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 186/200\n",
+ "200/200 [==============================] - 185s 927ms/step - loss: 7.1441e-04 - acc: 1.0000 - val_loss: 6.8889e-04 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 187/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 6.7345e-04 - acc: 1.0000 - val_loss: 6.5429e-04 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 188/200\n",
+ "200/200 [==============================] - 185s 925ms/step - loss: 6.4192e-04 - acc: 1.0000 - val_loss: 6.2633e-04 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 189/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 6.2029e-04 - acc: 1.0000 - val_loss: 6.0985e-04 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 190/200\n",
+ "200/200 [==============================] - 185s 926ms/step - loss: 6.0916e-04 - acc: 1.0000 - val_loss: 6.0429e-04 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Epoch 191/200\n",
+ "200/200 [==============================] - 184s 920ms/step - loss: 5.5169e-04 - acc: 1.0000 - val_loss: 5.0742e-04 - val_acc: 1.0000 - lr: 0.0020\n",
+ "Epoch 192/200\n",
+ "200/200 [==============================] - 184s 922ms/step - loss: 0.0027 - acc: 0.9986 - val_loss: 0.5014 - val_acc: 0.5005 - lr: 0.0018\n",
+ "Epoch 193/200\n",
+ "200/200 [==============================] - 184s 921ms/step - loss: 0.0024 - acc: 1.0000 - val_loss: 0.0023 - val_acc: 1.0000 - lr: 0.0016\n",
+ "Epoch 194/200\n",
+ "200/200 [==============================] - 185s 923ms/step - loss: 0.0023 - acc: 1.0000 - val_loss: 0.0022 - val_acc: 1.0000 - lr: 0.0014\n",
+ "Epoch 195/200\n",
+ "200/200 [==============================] - 183s 916ms/step - loss: 0.0022 - acc: 1.0000 - val_loss: 0.0021 - val_acc: 1.0000 - lr: 0.0012\n",
+ "Epoch 196/200\n",
+ "200/200 [==============================] - 183s 917ms/step - loss: 0.0021 - acc: 1.0000 - val_loss: 0.0020 - val_acc: 1.0000 - lr: 9.4444e-04\n",
+ "Epoch 197/200\n",
+ "200/200 [==============================] - 183s 917ms/step - loss: 0.0020 - acc: 1.0000 - val_loss: 0.0020 - val_acc: 1.0000 - lr: 7.3333e-04\n",
+ "Epoch 198/200\n",
+ "200/200 [==============================] - 184s 918ms/step - loss: 0.0020 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 1.0000 - lr: 5.2222e-04\n",
+ "Epoch 199/200\n",
+ "200/200 [==============================] - 184s 918ms/step - loss: 0.0019 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 1.0000 - lr: 3.1111e-04\n",
+ "Epoch 200/200\n",
+ "200/200 [==============================] - 183s 917ms/step - loss: 0.0019 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 1.0000 - lr: 1.0000e-04\n",
+ "Best validation accuracy: 1.0\n"
+ ]
+ }
+ ],
+ "source": [
+ "#14#Training the Model\n",
+ "num_epochs = 200\n",
+ "depth = 10\n",
+ "trained_net, history = train_LCB_distinguisher(num_epochs, num_rounds, depth)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "ghor_Rk_0000_836F_Round_10_depth_10.json\n"
+ ]
+ }
+ ],
+ "source": [
+ "#15#Create JSON File \n",
+ "# Convert the model architecture to JSON format\n",
+ "import json\n",
+ "from keras.models import model_from_json\n",
+ "model_json = trained_net.to_json()\n",
+ "\n",
+ " # Save the model architecture as a JSON file (optional)\n",
+ "filename = f'ghor_Rk_0000_836F_Round_{num_rounds}_depth_10.json'\n",
+ "print(filename)\n",
+ "with open(filename, \"w\") as json_file:\n",
+ " json.dump(json.loads(model_json), json_file, indent=4)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#16#Evaluate Function\n",
+ "def evaluate(net,X,Y):\n",
+ " Z = net.predict(X,batch_size=10000).flatten();\n",
+ " Zbin = (Z > 0.5);\n",
+ " diff = Y - Z; mse = np.mean(diff*diff);\n",
+ " n = len(Z); n0 = np.sum(Y==0); n1 = np.sum(Y==1);\n",
+ " acc = np.sum(Zbin == Y) / n;\n",
+ " tpr = np.sum(Zbin[Y==1]) / n1;\n",
+ " tnr = np.sum(Zbin[Y==0] == 0) / n0;\n",
+ " mreal = np.median(Z[Y==1]);\n",
+ " high_random = np.sum(Z[Y==0] > mreal) / n0;\n",
+ " print(\"Accuracy: \", acc, \"TPR: \", tpr, \"TNR: \", tnr, \"MSE:\", mse);\n",
+ " print(\"Percentage of random pairs with score higher than median of real pairs:\", 100*high_random);"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "metadata": {
+ "scrolled": false
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "10/10 [==============================] - 3s 273ms/step\n",
+ "Accuracy: 1.0 TPR: 1.0 TNR: 1.0 MSE: 3.327519e-07\n",
+ "Percentage of random pairs with score higher than median of real pairs: 0.0\n"
+ ]
+ }
+ ],
+ "source": [
+ "#17#Evaluate Function Call\n",
+ "import numpy as np\n",
+ "\n",
+ "from keras.models import model_from_json\n",
+ "\n",
+ "#load distinguishers\n",
+ "json_file = open('ghor_Rk_0000_836F_Round_10_depth_10.json','r');\n",
+ "json_model = json_file.read();\n",
+ "\n",
+ "net10 = model_from_json(json_model);\n",
+ "\n",
+ "net10.load_weights('ghor_Rk_0000_836F_Round_10_depth_10.h5');\n",
+ "\n",
+ "X_test_stacked, Y_test_stacked = make_train_data(100000, num_rounds)\n",
+ "evaluate(net10, X_test_stacked, Y_test_stacked);\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "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": "3.9.13"
+ },
+ "vscode": {
+ "interpreter": {
+ "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--
GitLab