From 92c83e9ac36ee021d74ca1a50fb292fe651c4d34 Mon Sep 17 00:00:00 2001 From: euisuk-chung Date: Tue, 7 Dec 2021 02:48:25 +0000 Subject: [PATCH] save csv debugging --- VRAE_evaluation.ipynb | 647 ++++++++++++++++++++++++++++++++++++++++++ run_vrae.py | 55 +++- vrae_experiment.sh | 12 +- 3 files changed, 698 insertions(+), 16 deletions(-) create mode 100644 VRAE_evaluation.ipynb diff --git a/VRAE_evaluation.ipynb b/VRAE_evaluation.ipynb new file mode 100644 index 0000000..4b5599c --- /dev/null +++ b/VRAE_evaluation.ipynb @@ -0,0 +1,647 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "a6a60e11", + "metadata": {}, + "outputs": [], + "source": [ + "from utils.visualization import *\n", + "import pandas as pd\n", + "import sys\n", + "import os" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "da49946e", + "metadata": {}, + "outputs": [], + "source": [ + "from os import listdir\n", + "from os.path import isfile, join" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "40f3154a", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'./gen_data_vae/train/'" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_loc = './gen_data_vae/train/'\n", + "train_loc" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "6d62ee29", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['./gen_data_vae/train/VRAE_Robust_un_False_hidden_2_win_30_ep_1000.csv',\n", + " './gen_data_vae/train/original_MinMax_un_False.csv',\n", + " './gen_data_vae/train/VRAE_MinMax_un_False_hidden_2_win_30_ep_1000.csv',\n", + " './gen_data_vae/train/VRAE_Standard_un_False_hidden_2_win_30_ep_1000.csv',\n", + " './gen_data_vae/train/VRAE_MinMax_un_False_hidden_1_win_30_ep_1000.csv',\n", + " './gen_data_vae/train/VRAE_Robust_un_False_hidden_1_win_30_ep_1000.csv',\n", + " './gen_data_vae/train/original_Standard_un_False.csv',\n", + " './gen_data_vae/train/original_Robust_un_False.csv',\n", + " './gen_data_vae/train/VRAE_MinMax_un_False_hidden_1_win_30_ep_1.csv',\n", + " './gen_data_vae/train/VRAE_Standard_un_False_hidden_1_win_30_ep_1000.csv']" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "train_files = []\n", + "for f in listdir(train_loc):\n", + " train_files.append(train_loc + f)\n", + "train_files" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "8b0c7770", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'./gen_data_vae/test/'" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "test_loc = './gen_data_vae/test/'\n", + "test_loc" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "c8ad3147", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['./gen_data_vae/test/VRAE_Robust_un_False_hidden_2_win_30_ep_1000.csv',\n", + " './gen_data_vae/test/original_MinMax_un_False.csv',\n", + " './gen_data_vae/test/VRAE_MinMax_un_False_hidden_2_win_30_ep_1000.csv',\n", + " './gen_data_vae/test/VRAE_Standard_un_False_hidden_2_win_30_ep_1000.csv',\n", + " './gen_data_vae/test/VRAE_MinMax_un_False_hidden_1_win_30_ep_1000.csv',\n", + " './gen_data_vae/test/VRAE_Robust_un_False_hidden_1_win_30_ep_1000.csv',\n", + " './gen_data_vae/test/original_Standard_un_False.csv',\n", + " './gen_data_vae/test/original_Robust_un_False.csv',\n", + " './gen_data_vae/test/VRAE_MinMax_un_False_hidden_1_win_30_ep_1.csv',\n", + " './gen_data_vae/test/VRAE_Standard_un_False_hidden_1_win_30_ep_1000.csv']" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "test_files = []\n", + "for f in listdir(test_loc):\n", + " test_files.append(test_loc + f)\n", + "test_files" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "0e39f441", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(22363, 92)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Device2Port1_AVG_INBPSDevice2Port1_AVG_OUTBPSDevice2Port4_AVG_INBPSDevice2Port4_AVG_OUTBPSDevice2Port6_AVG_INBPSDevice2Port6_AVG_OUTBPSDevice2Port8_AVG_INBPSDevice2Port8_AVG_OUTBPSDevice2Port10_AVG_INBPSDevice2Port10_AVG_OUTBPS...Device20Port3_AVG_INBPSDevice20Port3_AVG_OUTBPSDevice2_CPUDevice2_MemoryDevice4_CPUDevice7_CPUDevice8_CPUDevice4_MemoryDevice7_MemoryDevice8_Memory
00.0003660.0000250.0000290.0030350.0000100.0005700.0000370.0000240.0000620.000074...0.00.00.3750.0377360.2468750.0360270.0276360.3424460.4985970.165289
10.0002670.0000330.0000310.0022220.0000070.0001190.0000340.0000120.0007190.000091...0.00.00.3750.0330190.2500000.0116850.0368470.3510790.4978960.165289
20.0002020.0000140.0000300.0023760.0000030.0000850.0000370.0000130.0002990.000044...0.00.00.3750.0377360.2468750.0399220.0317300.3510790.4978960.123967
30.0002070.0000160.0000320.0026850.0000060.0001220.0000330.0000180.0000920.000058...0.00.00.3750.0235850.2479170.0107110.0419650.3496400.4978960.165289
40.0002150.0000290.0000320.0021910.0000030.0000500.0000340.0000070.0004210.000045...0.00.00.3750.0235850.2541670.0107110.0296830.3510790.4971950.165289
\n", + "

5 rows × 92 columns

\n", + "
" + ], + "text/plain": [ + " Device2Port1_AVG_INBPS Device2Port1_AVG_OUTBPS Device2Port4_AVG_INBPS \\\n", + "0 0.000366 0.000025 0.000029 \n", + "1 0.000267 0.000033 0.000031 \n", + "2 0.000202 0.000014 0.000030 \n", + "3 0.000207 0.000016 0.000032 \n", + "4 0.000215 0.000029 0.000032 \n", + "\n", + " Device2Port4_AVG_OUTBPS Device2Port6_AVG_INBPS Device2Port6_AVG_OUTBPS \\\n", + "0 0.003035 0.000010 0.000570 \n", + "1 0.002222 0.000007 0.000119 \n", + "2 0.002376 0.000003 0.000085 \n", + "3 0.002685 0.000006 0.000122 \n", + "4 0.002191 0.000003 0.000050 \n", + "\n", + " Device2Port8_AVG_INBPS Device2Port8_AVG_OUTBPS Device2Port10_AVG_INBPS \\\n", + "0 0.000037 0.000024 0.000062 \n", + "1 0.000034 0.000012 0.000719 \n", + "2 0.000037 0.000013 0.000299 \n", + "3 0.000033 0.000018 0.000092 \n", + "4 0.000034 0.000007 0.000421 \n", + "\n", + " Device2Port10_AVG_OUTBPS ... Device20Port3_AVG_INBPS \\\n", + "0 0.000074 ... 0.0 \n", + "1 0.000091 ... 0.0 \n", + "2 0.000044 ... 0.0 \n", + "3 0.000058 ... 0.0 \n", + "4 0.000045 ... 0.0 \n", + "\n", + " Device20Port3_AVG_OUTBPS Device2_CPU Device2_Memory Device4_CPU \\\n", + "0 0.0 0.375 0.037736 0.246875 \n", + "1 0.0 0.375 0.033019 0.250000 \n", + "2 0.0 0.375 0.037736 0.246875 \n", + "3 0.0 0.375 0.023585 0.247917 \n", + "4 0.0 0.375 0.023585 0.254167 \n", + "\n", + " Device7_CPU Device8_CPU Device4_Memory Device7_Memory Device8_Memory \n", + "0 0.036027 0.027636 0.342446 0.498597 0.165289 \n", + "1 0.011685 0.036847 0.351079 0.497896 0.165289 \n", + "2 0.039922 0.031730 0.351079 0.497896 0.123967 \n", + "3 0.010711 0.041965 0.349640 0.497896 0.165289 \n", + "4 0.010711 0.029683 0.351079 0.497195 0.165289 \n", + "\n", + "[5 rows x 92 columns]" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "org_train = pd.read_csv('./gen_data_vae/train/original_MinMax_un_False.csv')\n", + "print(org_train.shape)\n", + "org_train.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "c644a849", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(8790, 92)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Device2Port1_AVG_INBPSDevice2Port1_AVG_OUTBPSDevice2Port4_AVG_INBPSDevice2Port4_AVG_OUTBPSDevice2Port6_AVG_INBPSDevice2Port6_AVG_OUTBPSDevice2Port8_AVG_INBPSDevice2Port8_AVG_OUTBPSDevice2Port10_AVG_INBPSDevice2Port10_AVG_OUTBPS...Device20Port3_AVG_INBPSDevice20Port3_AVG_OUTBPSDevice2_CPUDevice2_MemoryDevice4_CPUDevice7_CPUDevice8_CPUDevice4_MemoryDevice7_MemoryDevice8_Memory
00.0022210.000560-0.000113-0.0015680.0027600.0050180.001306-0.0004060.0019170.001879...-0.001414-0.0002160.3833400.0391210.2471720.0260890.0340890.3631650.5166820.170150
10.0018350.0009490.000437-0.0012090.0021880.0039000.001273-0.0008350.0029100.001605...-0.001492-0.0000110.3781790.0384440.2455580.0248830.0341260.3573010.5091100.167471
20.0019280.0009970.000139-0.0019520.0022870.0044900.000790-0.0008510.0023260.001528...-0.0011570.0000470.3783100.0377540.2460040.0246820.0342710.3579220.5115360.168368
30.0020190.0010290.000200-0.0016680.0024350.0045770.000875-0.0010400.0022890.001431...-0.0011580.0000280.3772980.0373100.2457100.0251580.0340310.3571660.5098890.168465
40.0021590.0009950.000241-0.0014990.0024590.0046280.000995-0.0011240.0023150.001511...-0.0011830.0000080.3771550.0371010.2457060.0258170.0338870.3570920.5090760.168512
\n", + "

5 rows × 92 columns

\n", + "
" + ], + "text/plain": [ + " Device2Port1_AVG_INBPS Device2Port1_AVG_OUTBPS Device2Port4_AVG_INBPS \\\n", + "0 0.002221 0.000560 -0.000113 \n", + "1 0.001835 0.000949 0.000437 \n", + "2 0.001928 0.000997 0.000139 \n", + "3 0.002019 0.001029 0.000200 \n", + "4 0.002159 0.000995 0.000241 \n", + "\n", + " Device2Port4_AVG_OUTBPS Device2Port6_AVG_INBPS Device2Port6_AVG_OUTBPS \\\n", + "0 -0.001568 0.002760 0.005018 \n", + "1 -0.001209 0.002188 0.003900 \n", + "2 -0.001952 0.002287 0.004490 \n", + "3 -0.001668 0.002435 0.004577 \n", + "4 -0.001499 0.002459 0.004628 \n", + "\n", + " Device2Port8_AVG_INBPS Device2Port8_AVG_OUTBPS Device2Port10_AVG_INBPS \\\n", + "0 0.001306 -0.000406 0.001917 \n", + "1 0.001273 -0.000835 0.002910 \n", + "2 0.000790 -0.000851 0.002326 \n", + "3 0.000875 -0.001040 0.002289 \n", + "4 0.000995 -0.001124 0.002315 \n", + "\n", + " Device2Port10_AVG_OUTBPS ... Device20Port3_AVG_INBPS \\\n", + "0 0.001879 ... -0.001414 \n", + "1 0.001605 ... -0.001492 \n", + "2 0.001528 ... -0.001157 \n", + "3 0.001431 ... -0.001158 \n", + "4 0.001511 ... -0.001183 \n", + "\n", + " Device20Port3_AVG_OUTBPS Device2_CPU Device2_Memory Device4_CPU \\\n", + "0 -0.000216 0.383340 0.039121 0.247172 \n", + "1 -0.000011 0.378179 0.038444 0.245558 \n", + "2 0.000047 0.378310 0.037754 0.246004 \n", + "3 0.000028 0.377298 0.037310 0.245710 \n", + "4 0.000008 0.377155 0.037101 0.245706 \n", + "\n", + " Device7_CPU Device8_CPU Device4_Memory Device7_Memory Device8_Memory \n", + "0 0.026089 0.034089 0.363165 0.516682 0.170150 \n", + "1 0.024883 0.034126 0.357301 0.509110 0.167471 \n", + "2 0.024682 0.034271 0.357922 0.511536 0.168368 \n", + "3 0.025158 0.034031 0.357166 0.509889 0.168465 \n", + "4 0.025817 0.033887 0.357092 0.509076 0.168512 \n", + "\n", + "[5 rows x 92 columns]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gen_train = pd.read_csv('./gen_data_vae/train/VRAE_MinMax_un_False_hidden_2_win_30_ep_1000.csv')\n", + "print(gen_train.shape)\n", + "gen_train.head()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "39fa88fe", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "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": "3.6.9" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/run_vrae.py b/run_vrae.py index 129f635..0eeec1c 100644 --- a/run_vrae.py +++ b/run_vrae.py @@ -95,20 +95,37 @@ train_recon = vrae.reconstruct(train_gen_dataset) train_recon = concat_recon(train_recon) + # original train data + for window_num in range(len(train_gen_dataset)): + if window_num == 0: + # intialize train_org + train_org = train_gen_dataset[window_num] + else: + # get curr window + tmp_window = train_gen_dataset[window_num] + # concat next window + train_org = np.concatenate((train_org, tmp_window), axis=0) + # get loss - train_loss = eval_recon(recon = train_recon, real = TRAIN_DF if args.undo == True else TRAIN_SCALED, scaler = scaler, undo = args.undo) + # TODO : update unscaled version + train_loss = eval_recon(recon = train_recon, real = train_org, scaler = scaler, undo = args.undo) print(f'>> TRAIN RECONSTRUCTION LOSS : {train_loss}') # save original data - train_org = pd.DataFrame(TRAIN_DF if args.undo == True else TRAIN_SCALED, columns= cols) - train_org.to_csv(f'./gen_data_vae/train/original_{args.scale_type}_un_{args.undo}.csv') + train_org = pd.DataFrame(train_org, columns= cols) + # train_org = pd.DataFrame(TRAIN_DF if args.undo == True else TRAIN_SCALED, columns= cols) + train_org.to_csv(f'./gen_data_vae/train/original_{args.scale_type}_un_{args.undo}.csv', index=False) print('>> SAVED TRAIN ORIGINAL Data!! (Loc: gen_data_vae)') # save reconstructed data train_gen = pd.DataFrame(train_recon, columns= cols) - train_gen.to_csv(f'./gen_data_vae/train/VRAE_{args.scale_type}_un_{args.undo}_hidden_{args.hidden_layer_depth}_win_{args.sequence_length}_ep_{args.n_epochs}.csv') + train_gen.to_csv(f'./gen_data_vae/train/VRAE_{args.scale_type}_un_{args.undo}_hidden_{args.hidden_layer_depth}_win_{args.sequence_length}_ep_{args.n_epochs}.csv', index=False) print('>> SAVED TRAIN RECONSTRUCTED Data!! (Loc: gen_data_vae)') +# print(f'TRAIN ORG SHAPE : {train_org.shape}') +# print(f'TRAIN GEN SHAPE : {train_gen.shape}') +# print(f'SHAPE COMPARE : {train_org.shape==train_gen.shape}') + # TEST dataset reconstruction if args.is_generate_test: # FOR GENERATION MUST HAVE batch_size 1 @@ -128,22 +145,40 @@ test_recon = vrae.reconstruct(test_gen_dataset) test_recon = concat_recon(test_recon) + # original test data + for window_num in range(len(test_gen_dataset)): + if window_num == 0: + # intialize train_org + test_org = test_gen_dataset[window_num] + else: + # get curr window + tmp_window = test_gen_dataset[window_num] + # concat next window + test_org = np.concatenate((test_org, tmp_window), axis=0) + # get loss - test_loss = eval_recon(recon = test_recon, real = TEST_DF if args.undo == True else TEST_SCALED, scaler = scaler, undo = args.undo) + # TODO : update unscaled version + test_loss = eval_recon(recon = test_recon, real = test_org, scaler = scaler, undo = args.undo) print(f'>> TEST RECONSTRUCTION LOSS : {test_loss}') # save original data - test_org = pd.DataFrame(TRAIN_DF if args.undo == True else TRAIN_SCALED, columns= cols) - test_org.to_csv(f'./gen_data_vae/test/original_{args.scale_type}_un_{args.undo}.csv') + test_org = pd.DataFrame(test_org, columns= cols) + # test_org = pd.DataFrame(TRAIN_DF if args.undo == True else TRAIN_SCALED, columns= cols) + test_org.to_csv(f'./gen_data_vae/test/original_{args.scale_type}_un_{args.undo}.csv', index=False) print('>> SAVED TEST ORIGINAL Data!! (Loc: gen_data_vae)') # save reconstructed data test_gen = pd.DataFrame(test_recon, columns= cols) - test_gen.to_csv(f'./gen_data_vae/test/VRAE_{args.scale_type}_un_{args.undo}_hidden_{args.hidden_layer_depth}_win_{args.sequence_length}_ep_{args.n_epochs}.csv') + test_gen.to_csv(f'./gen_data_vae/test/VRAE_{args.scale_type}_un_{args.undo}_hidden_{args.hidden_layer_depth}_win_{args.sequence_length}_ep_{args.n_epochs}.csv', index=False) print('>> SAVED TEST RECONSTRUCTED Data!! (Loc: gen_data_vae)') + +# print(f'TEST ORG SHAPE : {test_org.shape}') +# print(f'TEST GEN SHAPE : {test_gen.shape}') +# print(f'SHAPE COMPARE : {test_org.shape==test_gen.shape}') -# IF Both TRAIN and TEST data reconstruction is conducted -if args.is_generate_train and args.is_generate_test: +# If we train and test at the same time +# to get train/test diff and loss history +if args.is_train and args.is_generate_train and args.is_generate_test: # train recon diff train_diff = pd.DataFrame(get_diff(recon = train_recon, real = TRAIN_DF if args.undo == True else TRAIN_SCALED, scaler = scaler, undo = args.undo), columns= cols) diff --git a/vrae_experiment.sh b/vrae_experiment.sh index 50f32b7..464ad0e 100644 --- a/vrae_experiment.sh +++ b/vrae_experiment.sh @@ -2,13 +2,13 @@ # TRAIN on diff scalers, and layers # Standard -python run_vrae.py --scale_type 'Standard' --hidden_layer_depth 1 -python run_vrae.py --scale_type 'Standard' --hidden_layer_depth 2 +python run_vrae.py --scale_type 'Standard' --hidden_layer_depth 1 --is_train False +python run_vrae.py --scale_type 'Standard' --hidden_layer_depth 2 --is_train False # MinMax -python run_vrae.py --scale_type 'MinMax' --hidden_layer_depth 1 -python run_vrae.py --scale_type 'MinMax' --hidden_layer_depth 2 +python run_vrae.py --scale_type 'MinMax' --hidden_layer_depth 1 --is_train False +python run_vrae.py --scale_type 'MinMax' --hidden_layer_depth 2 --is_train False # Robust -python run_vrae.py --scale_type 'Robust' --hidden_layer_depth 1 -python run_vrae.py --scale_type 'Robust' --hidden_layer_depth 2 \ No newline at end of file +python run_vrae.py --scale_type 'Robust' --hidden_layer_depth 1 --is_train False +python run_vrae.py --scale_type 'Robust' --hidden_layer_depth 2 --is_train False \ No newline at end of file