761 lines
26 KiB
Plaintext
761 lines
26 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 1,
|
||
|
|
"id": "a5b326e2",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import os\n",
|
||
|
|
"\n",
|
||
|
|
"glob_path = '/opt/iui-datarelease2-sose2021/*/split_letters_csv/*'\n",
|
||
|
|
"\n",
|
||
|
|
"pickle_file = 'data.pickle'\n",
|
||
|
|
"\n",
|
||
|
|
"checkpoint_path = \"training_copy/cp.ckpt\"\n",
|
||
|
|
"checkpoint_dir = os.path.dirname(checkpoint_path)\n",
|
||
|
|
"\n",
|
||
|
|
"# divisor for neuron count step downs (hard to describe), e.g. dense_step = 3: layer1=900, layer2 = 300, layer3 = 100, layer4 = 33...\n",
|
||
|
|
"dense_steps = 2\n",
|
||
|
|
"# amount of dense/dropout layers\n",
|
||
|
|
"layer_count = 3\n",
|
||
|
|
"# how much to drop\n",
|
||
|
|
"drop_count = 0.1"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 2,
|
||
|
|
"id": "e834add0",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"from glob import glob\n",
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"from tqdm import tqdm\n",
|
||
|
|
"\n",
|
||
|
|
"def dl_from_blob(filename) -> list:\n",
|
||
|
|
" all_data = []\n",
|
||
|
|
" \n",
|
||
|
|
" for path in tqdm(glob(filename)):\n",
|
||
|
|
" path = path\n",
|
||
|
|
" df = pd.read_csv(path, ';')\n",
|
||
|
|
" u = path.split('/')[3]\n",
|
||
|
|
" l = ''.join(filter(lambda x: x.isalpha(), path.split('/')[5]))[0] \n",
|
||
|
|
" d = {\n",
|
||
|
|
" 'file': path,\n",
|
||
|
|
" 'data': df,\n",
|
||
|
|
" 'user': u,\n",
|
||
|
|
" 'label': l\n",
|
||
|
|
" }\n",
|
||
|
|
" all_data.append(d)\n",
|
||
|
|
" return all_data"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 3,
|
||
|
|
"id": "ec9e9e4d",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def save_pickle(f, structure):\n",
|
||
|
|
" _p = open(f, 'wb')\n",
|
||
|
|
" pickle.dump(structure, _p)\n",
|
||
|
|
" _p.close()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 4,
|
||
|
|
"id": "44338438",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import pickle\n",
|
||
|
|
"\n",
|
||
|
|
"def load_pickles(f) -> list:\n",
|
||
|
|
" _p = open(pickle_file, 'rb')\n",
|
||
|
|
" _d = pickle.load(_p)\n",
|
||
|
|
" _p.close()\n",
|
||
|
|
" \n",
|
||
|
|
" return _d"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 5,
|
||
|
|
"id": "2627c3c5",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Loading data...\n",
|
||
|
|
"data.pickle found...\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"import os\n",
|
||
|
|
"def load_data() -> list:\n",
|
||
|
|
" if os.path.isfile(pickle_file):\n",
|
||
|
|
" print(f'{pickle_file} found...')\n",
|
||
|
|
" return load_pickles(pickle_file)\n",
|
||
|
|
" print(f'Didn\\'t find {pickle_file}...')\n",
|
||
|
|
" all_data = dl_from_blob(glob_path)\n",
|
||
|
|
" print(f'Creating {pickle_file}...')\n",
|
||
|
|
" save_pickle(pickle_file, all_data)\n",
|
||
|
|
" return all_data\n",
|
||
|
|
"\n",
|
||
|
|
"print(\"Loading data...\")\n",
|
||
|
|
"data = load_data()\n",
|
||
|
|
"# plot_pd(data[0]['data'], False)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 6,
|
||
|
|
"id": "71e6d157",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import matplotlib.pyplot as plt\n",
|
||
|
|
"\n",
|
||
|
|
"def plot_pd(data, force=True):\n",
|
||
|
|
" fig, axs = plt.subplots(5, 3, figsize=(3*3, 3*5))\n",
|
||
|
|
" axs[0][0].plot(data['Acc1 X'])\n",
|
||
|
|
" axs[0][1].plot(data['Acc1 Y'])\n",
|
||
|
|
" axs[0][2].plot(data['Acc1 Z'])\n",
|
||
|
|
" axs[1][0].plot(data['Acc2 X'])\n",
|
||
|
|
" axs[1][1].plot(data['Acc2 Y'])\n",
|
||
|
|
" axs[1][2].plot(data['Acc2 Z'])\n",
|
||
|
|
" axs[2][0].plot(data['Gyro X'])\n",
|
||
|
|
" axs[2][1].plot(data['Gyro Y'])\n",
|
||
|
|
" axs[2][2].plot(data['Gyro Z'])\n",
|
||
|
|
" axs[3][0].plot(data['Mag X'])\n",
|
||
|
|
" axs[3][1].plot(data['Mag Y'])\n",
|
||
|
|
" axs[3][2].plot(data['Mag Z'])\n",
|
||
|
|
" axs[4][0].plot(data['Time'])\n",
|
||
|
|
"\n",
|
||
|
|
" if force:\n",
|
||
|
|
" for a in axs:\n",
|
||
|
|
" for b in a:\n",
|
||
|
|
" b.plot(data['Force'])\n",
|
||
|
|
" else:\n",
|
||
|
|
" axs[4][1].plot(data['Force'])\n",
|
||
|
|
"\n",
|
||
|
|
"def plot_np(data, force=True):\n",
|
||
|
|
" fig, axs = plt.subplots(5, 3, figsize=(3*3, 3*5))\n",
|
||
|
|
" axs[0][0].plot(data[0])\n",
|
||
|
|
" axs[0][1].plot(data[1])\n",
|
||
|
|
" axs[0][2].plot(data[2])\n",
|
||
|
|
" axs[1][0].plot(data[3])\n",
|
||
|
|
" axs[1][1].plot(data[4])\n",
|
||
|
|
" axs[1][2].plot(data[5])\n",
|
||
|
|
" axs[2][0].plot(data[6])\n",
|
||
|
|
" axs[2][1].plot(data[7])\n",
|
||
|
|
" axs[2][2].plot(data[8])\n",
|
||
|
|
" axs[3][0].plot(data[9])\n",
|
||
|
|
" axs[3][1].plot(data[10])\n",
|
||
|
|
" axs[3][2].plot(data[11])\n",
|
||
|
|
" axs[4][0].plot(data[13])\n",
|
||
|
|
"\n",
|
||
|
|
" if force:\n",
|
||
|
|
" for a in axs:\n",
|
||
|
|
" for b in a:\n",
|
||
|
|
" b.plot(data[12])\n",
|
||
|
|
" else:\n",
|
||
|
|
" axs[4][1].plot(data[12])\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 7,
|
||
|
|
"id": "19c4c56e",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def mill_drop(entry):\n",
|
||
|
|
" #drop millis on single\n",
|
||
|
|
" data_wo_mill = entry['data'].drop(labels='Millis', axis=1, inplace=False)\n",
|
||
|
|
" drop_entry = entry\n",
|
||
|
|
" drop_entry['data'] = data_wo_mill.reset_index(drop=True)\n",
|
||
|
|
" \n",
|
||
|
|
" return drop_entry"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 8,
|
||
|
|
"id": "ea509043",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import numpy as np\n",
|
||
|
|
"\n",
|
||
|
|
"def cut_force(drop_entry):\n",
|
||
|
|
" # force trans\n",
|
||
|
|
" shorten_entry = drop_entry\n",
|
||
|
|
" shorten_data = shorten_entry['data']\n",
|
||
|
|
" sf_entry = shorten_data['Force']\n",
|
||
|
|
" leeway = 10\n",
|
||
|
|
" \n",
|
||
|
|
" try:\n",
|
||
|
|
" thresh = 70\n",
|
||
|
|
" temps_over_T = np.where(sf_entry > thresh)[0]\n",
|
||
|
|
" shorten_data = shorten_data[max(temps_over_T.min()-leeway,0):min(len(sf_entry)-1,temps_over_T.max()+leeway)]\n",
|
||
|
|
" except:\n",
|
||
|
|
" thresold = 0.05\n",
|
||
|
|
" thresh = sf_entry.max()*thresold\n",
|
||
|
|
" temps_over_T = np.where(sf_entry > thresh)[0]\n",
|
||
|
|
" shorten_data = shorten_data[max(temps_over_T.min()-leeway,0):min(len(sf_entry)-1,temps_over_T.max()+leeway)]\n",
|
||
|
|
" \n",
|
||
|
|
" shorten_entry['data'] = shorten_data.reset_index(drop=True)\n",
|
||
|
|
" return shorten_entry"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 9,
|
||
|
|
"id": "7025983c",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def norm_force(shorten_entry, flist):\n",
|
||
|
|
" fnorm_entry = shorten_entry\n",
|
||
|
|
" u = fnorm_entry['user']\n",
|
||
|
|
" d = fnorm_entry['data']\n",
|
||
|
|
" \n",
|
||
|
|
" \n",
|
||
|
|
" d['Force'] = ((d['Force'] - flist[u].mean())/flist[u].std())\n",
|
||
|
|
" \n",
|
||
|
|
" fnorm_entry['data'] = fnorm_entry['data'].reset_index(drop=True)\n",
|
||
|
|
" return fnorm_entry"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 10,
|
||
|
|
"id": "64860f57",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def time_trans(fnorm_entry):\n",
|
||
|
|
" #timetrans\n",
|
||
|
|
" time_entry = fnorm_entry\n",
|
||
|
|
" \n",
|
||
|
|
" time_entry['data']['Time'] = fnorm_entry['data']['Time']-fnorm_entry['data']['Time'][0]\n",
|
||
|
|
" \n",
|
||
|
|
" time_entry['data'] = time_entry['data'].reset_index(drop=True)\n",
|
||
|
|
"\n",
|
||
|
|
" return time_entry"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 11,
|
||
|
|
"id": "0bb308a2",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def norm(time_entry):\n",
|
||
|
|
" # normalize\n",
|
||
|
|
" norm_entry = time_entry\n",
|
||
|
|
" \n",
|
||
|
|
" norm_entry['data']['Acc1 X'] = norm_entry['data']['Acc1 X'] / 32768\n",
|
||
|
|
" norm_entry['data']['Acc1 Y'] = norm_entry['data']['Acc1 Y'] / 32768\n",
|
||
|
|
" norm_entry['data']['Acc1 Z'] = norm_entry['data']['Acc1 Z'] / 32768\n",
|
||
|
|
" norm_entry['data']['Acc2 X'] = norm_entry['data']['Acc2 X'] / 8192\n",
|
||
|
|
" norm_entry['data']['Acc2 Y'] = norm_entry['data']['Acc2 Y'] / 8192\n",
|
||
|
|
" norm_entry['data']['Acc2 Z'] = norm_entry['data']['Acc2 Z'] / 8192\n",
|
||
|
|
" norm_entry['data']['Gyro X'] = norm_entry['data']['Gyro X'] / 32768\n",
|
||
|
|
" norm_entry['data']['Gyro Y'] = norm_entry['data']['Gyro Y'] / 32768\n",
|
||
|
|
" norm_entry['data']['Gyro Z'] = norm_entry['data']['Gyro Z'] / 32768\n",
|
||
|
|
" norm_entry['data']['Mag X'] = norm_entry['data']['Mag X'] / 8192\n",
|
||
|
|
" norm_entry['data']['Mag Y'] = norm_entry['data']['Mag Y'] / 8192\n",
|
||
|
|
" norm_entry['data']['Mag Z'] = norm_entry['data']['Mag Z'] / 8192\n",
|
||
|
|
" \n",
|
||
|
|
" norm_entry['data'] = norm_entry['data'].reset_index(drop=True)\n",
|
||
|
|
" \n",
|
||
|
|
" return norm_entry"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 12,
|
||
|
|
"id": "1171c8ef",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Preprocessing...\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"100%|██████████| 26179/26179 [01:29<00:00, 292.14it/s]\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"def preproc(d):\n",
|
||
|
|
" flist = {} \n",
|
||
|
|
" d_res = []\n",
|
||
|
|
" for e in data:\n",
|
||
|
|
" if e['user'] not in flist:\n",
|
||
|
|
" flist[e['user']] = e['data']['Force']\n",
|
||
|
|
" else:\n",
|
||
|
|
" flist[e['user']] = flist[e['user']].append(e['data']['Force'])\n",
|
||
|
|
" \n",
|
||
|
|
" for e in tqdm(data):\n",
|
||
|
|
" d_res.append(preproc_entry(e, flist))\n",
|
||
|
|
" return d_res\n",
|
||
|
|
" \n",
|
||
|
|
"def preproc_entry(entry, flist):\n",
|
||
|
|
" drop_entry = mill_drop(entry)\n",
|
||
|
|
"# plot_pd(drop_entry['data'])\n",
|
||
|
|
"# \n",
|
||
|
|
" shorten_entry = cut_force(drop_entry)\n",
|
||
|
|
"# plot_pd(shorten_entry['data'])\n",
|
||
|
|
"# \n",
|
||
|
|
" fnorm_entry = norm_force(shorten_entry, flist)\n",
|
||
|
|
"# plot_pd(fnorm_entry['data'])\n",
|
||
|
|
"# \n",
|
||
|
|
" time_entry = time_trans(shorten_entry)\n",
|
||
|
|
"# plot_pd(time_entry['data'])\n",
|
||
|
|
"# \n",
|
||
|
|
" norm_entry = norm(time_entry)\n",
|
||
|
|
"# plot_pd(norm_entry['data'], False)\n",
|
||
|
|
" return norm_entry\n",
|
||
|
|
"\n",
|
||
|
|
"print(\"Preprocessing...\")\n",
|
||
|
|
"pdata = preproc(data)\n",
|
||
|
|
"# plot_pd(pdata[0]['data'], False)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 13,
|
||
|
|
"id": "2d576b5d",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Truncating...\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"def throw(pdata):\n",
|
||
|
|
" llist = pd.Series([len(x['data']) for x in pdata])\n",
|
||
|
|
" threshold = int(llist.quantile(threshold_p))\n",
|
||
|
|
" longdex = np.where(llist <= threshold)[0]\n",
|
||
|
|
" return np.array(pdata)[longdex]\n",
|
||
|
|
"\n",
|
||
|
|
"llist = pd.Series([len(x['data']) for x in pdata])\n",
|
||
|
|
"threshold_p = 0.75\n",
|
||
|
|
"threshold = int(llist.quantile(threshold_p))\n",
|
||
|
|
"\n",
|
||
|
|
"print(\"Truncating...\")\n",
|
||
|
|
"tpdata = throw(pdata)\n",
|
||
|
|
"# plot_pd(tpdata[0]['data'], False)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 14,
|
||
|
|
"id": "b3eb709e",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" 9%|▉ | 1785/19640 [00:00<00:01, 17844.40it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Padding...\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"100%|██████████| 19640/19640 [00:01<00:00, 18711.98it/s]\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
|
||
|
|
"# ltpdata = []\n",
|
||
|
|
"def elong(tpdata):\n",
|
||
|
|
" for x in tqdm(tpdata):\n",
|
||
|
|
" y = x['data'].to_numpy().T\n",
|
||
|
|
" x['data'] = pad_sequences(y, dtype=float, padding='post', maxlen=threshold)\n",
|
||
|
|
" return tpdata\n",
|
||
|
|
"\n",
|
||
|
|
"print(\"Padding...\")\n",
|
||
|
|
"ltpdata = elong(tpdata)\n",
|
||
|
|
"# plot_np(ltpdata[0]['data'], False)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 15,
|
||
|
|
"id": "73a2a874",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"import tensorflow as tf\n",
|
||
|
|
"from tensorflow.keras.regularizers import l2\n",
|
||
|
|
"from tensorflow.keras.models import Sequential\n",
|
||
|
|
"from tensorflow.keras.layers import Dense, Flatten, BatchNormalization, Dropout\n",
|
||
|
|
"from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau\n",
|
||
|
|
"from tensorflow.keras.optimizers import Adam\n",
|
||
|
|
"\n",
|
||
|
|
"def build_model(shape, classes):\n",
|
||
|
|
" model = Sequential()\n",
|
||
|
|
" \n",
|
||
|
|
" ncount = shape[0]*shape[1]\n",
|
||
|
|
" \n",
|
||
|
|
" model.add(Flatten(input_shape=shape, name='flatten'))\n",
|
||
|
|
" \n",
|
||
|
|
" model.add(Dropout(drop_count, name=f'dropout_{drop_count*100}'))\n",
|
||
|
|
" model.add(BatchNormalization(name='batchNorm'))\n",
|
||
|
|
" \n",
|
||
|
|
" for i in range(1,layer_count+1):\n",
|
||
|
|
" neurons = int(ncount/pow(dense_steps,i))\n",
|
||
|
|
" if neurons <= classes:\n",
|
||
|
|
" break\n",
|
||
|
|
" model.add(Dropout(drop_count*i, name=f'HiddenDropout_{drop_count*i*100:.0f}'))\n",
|
||
|
|
" model.add(Dense(neurons, activation='relu', \n",
|
||
|
|
" kernel_regularizer=l2(0.001), name=f'Hidden_{i}')\n",
|
||
|
|
" )\n",
|
||
|
|
" \n",
|
||
|
|
" model.add(Dense(classes, activation='softmax', name='Output'))\n",
|
||
|
|
" \n",
|
||
|
|
" model.compile(\n",
|
||
|
|
" optimizer=Adam(),\n",
|
||
|
|
" loss=\"categorical_crossentropy\", \n",
|
||
|
|
" metrics=[\"acc\"],\n",
|
||
|
|
" )\n",
|
||
|
|
" \n",
|
||
|
|
" return model"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 16,
|
||
|
|
"id": "8ae93baa",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"checkpoint_file = './goat.weights'\n",
|
||
|
|
"\n",
|
||
|
|
"def train(X_train, y_train, X_test, y_test):\n",
|
||
|
|
" model = build_model(X_train[0].shape, 52)\n",
|
||
|
|
" \n",
|
||
|
|
" model.summary()\n",
|
||
|
|
" \n",
|
||
|
|
" # Create a callback that saves the model's weights\n",
|
||
|
|
" model_checkpoint = ModelCheckpoint(filepath=checkpoint_path, monitor='loss', \n",
|
||
|
|
"\t\t\tsave_best_only=True)\n",
|
||
|
|
" \n",
|
||
|
|
" history = model.fit(X_train, y_train, \n",
|
||
|
|
" epochs=30,\n",
|
||
|
|
" batch_size=256,\n",
|
||
|
|
" shuffle=True,\n",
|
||
|
|
" validation_data=(X_test, y_test),\n",
|
||
|
|
" verbose=2,\n",
|
||
|
|
" callbacks=[model_checkpoint]\n",
|
||
|
|
" )\n",
|
||
|
|
" \n",
|
||
|
|
" \n",
|
||
|
|
" model.load_weights(checkpoint_path)\n",
|
||
|
|
" print(\"Evaluate on test data\")\n",
|
||
|
|
" return model, history"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 17,
|
||
|
|
"id": "9668ef09",
|
||
|
|
"metadata": {
|
||
|
|
"tags": []
|
||
|
|
},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true' # this is required\n",
|
||
|
|
"os.environ['CUDA_VISIBLE_DEVICES'] = '0' # set to '0' for GPU0, '1' for GPU1 or '2' for GPU2. Check \"gpustat\" in a terminal."
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 18,
|
||
|
|
"id": "0bd41ed5",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"from sklearn.model_selection import train_test_split\n",
|
||
|
|
"from sklearn.preprocessing import LabelEncoder, LabelBinarizer\n",
|
||
|
|
"\n",
|
||
|
|
"X = np.array([x['data'] for x in ltpdata])\n",
|
||
|
|
"y = np.array([x['label'] for x in ltpdata])\n",
|
||
|
|
"\n",
|
||
|
|
"lb = LabelBinarizer()\n",
|
||
|
|
"y_tran = lb.fit_transform(y)\n",
|
||
|
|
"\n",
|
||
|
|
"X_train, X_test, y_train, y_test = train_test_split(X, y_tran, test_size=0.2, random_state=177013)\n",
|
||
|
|
"\n",
|
||
|
|
"X_train=X_train.reshape(X_train.shape[0],X_train.shape[1],X_train.shape[2])\n",
|
||
|
|
"X_test=X_test.reshape(X_test.shape[0],X_test.shape[1],X_test.shape[2])\n",
|
||
|
|
"\n",
|
||
|
|
"train_shape = X_train[0].shape\n",
|
||
|
|
"classes = y_train[0].shape[0]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 19,
|
||
|
|
"id": "2c25c41b",
|
||
|
|
"metadata": {
|
||
|
|
"tags": []
|
||
|
|
},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Model: \"sequential\"\n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"Layer (type) Output Shape Param # \n",
|
||
|
|
"=================================================================\n",
|
||
|
|
"flatten (Flatten) (None, 1050) 0 \n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"dropout_10.0 (Dropout) (None, 1050) 0 \n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"batchNorm (BatchNormalizatio (None, 1050) 4200 \n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"HiddenDropout_10 (Dropout) (None, 1050) 0 \n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"Hidden_1 (Dense) (None, 525) 551775 \n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"HiddenDropout_20 (Dropout) (None, 525) 0 \n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"Hidden_2 (Dense) (None, 262) 137812 \n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"HiddenDropout_30 (Dropout) (None, 262) 0 \n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"Hidden_3 (Dense) (None, 131) 34453 \n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"Output (Dense) (None, 52) 6864 \n",
|
||
|
|
"=================================================================\n",
|
||
|
|
"Total params: 735,104\n",
|
||
|
|
"Trainable params: 733,004\n",
|
||
|
|
"Non-trainable params: 2,100\n",
|
||
|
|
"_________________________________________________________________\n",
|
||
|
|
"Epoch 1/30\n",
|
||
|
|
"62/62 - 2s - loss: 4.8396 - acc: 0.0671 - val_loss: 4.7298 - val_acc: 0.0710\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 2/30\n",
|
||
|
|
"62/62 - 0s - loss: 4.0757 - acc: 0.1609 - val_loss: 4.2353 - val_acc: 0.1031\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 3/30\n",
|
||
|
|
"62/62 - 0s - loss: 3.5292 - acc: 0.2483 - val_loss: 3.9189 - val_acc: 0.1349\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 4/30\n",
|
||
|
|
"62/62 - 0s - loss: 3.1635 - acc: 0.3097 - val_loss: 3.5697 - val_acc: 0.2070\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 5/30\n",
|
||
|
|
"62/62 - 0s - loss: 2.8876 - acc: 0.3607 - val_loss: 3.3103 - val_acc: 0.2487\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 6/30\n",
|
||
|
|
"62/62 - 0s - loss: 2.6724 - acc: 0.4022 - val_loss: 3.0531 - val_acc: 0.3032\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 7/30\n",
|
||
|
|
"62/62 - 0s - loss: 2.5206 - acc: 0.4299 - val_loss: 2.8832 - val_acc: 0.3450\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 8/30\n",
|
||
|
|
"62/62 - 0s - loss: 2.3844 - acc: 0.4576 - val_loss: 2.5853 - val_acc: 0.4234\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 9/30\n",
|
||
|
|
"62/62 - 0s - loss: 2.2780 - acc: 0.4808 - val_loss: 2.3759 - val_acc: 0.4672\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 10/30\n",
|
||
|
|
"62/62 - 0s - loss: 2.2042 - acc: 0.4960 - val_loss: 2.2155 - val_acc: 0.5005\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 11/30\n",
|
||
|
|
"62/62 - 0s - loss: 2.1139 - acc: 0.5190 - val_loss: 2.0585 - val_acc: 0.5425\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 12/30\n",
|
||
|
|
"62/62 - 0s - loss: 2.0391 - acc: 0.5350 - val_loss: 1.9542 - val_acc: 0.5687\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 13/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.9897 - acc: 0.5411 - val_loss: 1.9089 - val_acc: 0.5759\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 14/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.9307 - acc: 0.5551 - val_loss: 1.8783 - val_acc: 0.5832\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 15/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.8869 - acc: 0.5673 - val_loss: 1.8283 - val_acc: 0.5942\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 16/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.8516 - acc: 0.5720 - val_loss: 1.7902 - val_acc: 0.5965\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 17/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.8156 - acc: 0.5860 - val_loss: 1.7896 - val_acc: 0.5894\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 18/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.7877 - acc: 0.5929 - val_loss: 1.7737 - val_acc: 0.6006\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 19/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.7562 - acc: 0.5984 - val_loss: 1.7304 - val_acc: 0.6212\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 20/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.7235 - acc: 0.6043 - val_loss: 1.7242 - val_acc: 0.6156\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 21/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.6954 - acc: 0.6149 - val_loss: 1.7041 - val_acc: 0.6263\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 22/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.6949 - acc: 0.6165 - val_loss: 1.7357 - val_acc: 0.6227\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 23/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.6688 - acc: 0.6208 - val_loss: 1.6868 - val_acc: 0.6354\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 24/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.6374 - acc: 0.6268 - val_loss: 1.6755 - val_acc: 0.6275\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 25/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.6202 - acc: 0.6383 - val_loss: 1.6566 - val_acc: 0.6393\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 26/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.5944 - acc: 0.6424 - val_loss: 1.6365 - val_acc: 0.6441\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 27/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.5963 - acc: 0.6435 - val_loss: 1.6578 - val_acc: 0.6334\n",
|
||
|
|
"Epoch 28/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.5958 - acc: 0.6412 - val_loss: 1.6364 - val_acc: 0.6357\n",
|
||
|
|
"Epoch 29/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.5655 - acc: 0.6501 - val_loss: 1.6174 - val_acc: 0.6510\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Epoch 30/30\n",
|
||
|
|
"62/62 - 0s - loss: 1.5553 - acc: 0.6498 - val_loss: 1.6273 - val_acc: 0.6410\n",
|
||
|
|
"INFO:tensorflow:Assets written to: training_1/cp.ckpt/assets\n",
|
||
|
|
"Evaluate on test data\n",
|
||
|
|
"CPU times: user 40.6 s, sys: 3.77 s, total: 44.3 s\n",
|
||
|
|
"Wall time: 36.3 s\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"%%time\n",
|
||
|
|
"if 'model' not in locals():\n",
|
||
|
|
" tf.keras.backend.clear_session()\n",
|
||
|
|
" model, history = train(np.array(X_train), np.array(y_train), np.array(X_test), np.array(y_test))\n",
|
||
|
|
"else:\n",
|
||
|
|
" print(\"Loaded weights...\")\n",
|
||
|
|
" model.load_weights(checkpoint_path)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 23,
|
||
|
|
"id": "adb16aa9",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": [
|
||
|
|
"(14, 75)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 23,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"X_test[0].shape"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"id": "0f26ada5",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def plot_keras_history(history, name='', acc='acc'):\n",
|
||
|
|
" \"\"\"Plots keras history.\"\"\"\n",
|
||
|
|
" import matplotlib.pyplot as plt\n",
|
||
|
|
"\n",
|
||
|
|
" training_acc = history.history[acc]\n",
|
||
|
|
" validation_acc = history.history['val_' + acc]\n",
|
||
|
|
" loss = history.history['loss']\n",
|
||
|
|
" val_loss = history.history['val_loss']\n",
|
||
|
|
"\n",
|
||
|
|
" epochs = range(len(training_acc))\n",
|
||
|
|
"\n",
|
||
|
|
" plt.ylim(0, 1)\n",
|
||
|
|
" plt.plot(epochs, training_acc, 'tab:blue', label='Training acc')\n",
|
||
|
|
" plt.plot(epochs, validation_acc, 'tab:orange', label='Validation acc')\n",
|
||
|
|
" plt.title('Training and validation accuracy ' + name)\n",
|
||
|
|
" plt.legend()\n",
|
||
|
|
"\n",
|
||
|
|
" plt.figure()\n",
|
||
|
|
"\n",
|
||
|
|
" plt.plot(epochs, loss, 'tab:green', label='Training loss')\n",
|
||
|
|
" plt.plot(epochs, val_loss, 'tab:red', label='Validation loss')\n",
|
||
|
|
" plt.title('Training and validation loss ' + name)\n",
|
||
|
|
" plt.legend()\n",
|
||
|
|
" plt.show()\n",
|
||
|
|
" plt.close()\n",
|
||
|
|
"plot_keras_history(history)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"id": "1d32900e",
|
||
|
|
"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": "3.8.10"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 5
|
||
|
|
}
|