From b69e3b60a55426dfefb4fae22ea1cba2013cae26 Mon Sep 17 00:00:00 2001
From: "Jean-Luc Parouty Jean-Luc.Parouty@simap.grenoble-inp.fr"
<paroutyj@f-dahu.u-ga.fr>
Date: Mon, 20 Jan 2020 23:38:16 +0100
Subject: [PATCH] Jupyter to Batch cooking
---
GTSRB/03-Tracking-and-visualizing.ipynb | 2 +-
GTSRB/04-Data-augmentation.ipynb | 5 +-
GTSRB/05-Full-convolutions.ipynb | 236 +++++++++++++--------
GTSRB/05.1-Full-convolutions-batch.ipynb | 42 ++--
GTSRB/05.2-Full-convolutions-reports.ipynb | 204 +++++++++---------
GTSRB/99 Scripts-Tensorboard.ipynb | 28 ++-
6 files changed, 290 insertions(+), 227 deletions(-)
diff --git a/GTSRB/03-Tracking-and-visualizing.ipynb b/GTSRB/03-Tracking-and-visualizing.ipynb
index b185c9c..1c93d55 100644
--- a/GTSRB/03-Tracking-and-visualizing.ipynb
+++ b/GTSRB/03-Tracking-and-visualizing.ipynb
@@ -270,7 +270,7 @@
" batch_size=batch_size,\n",
" epochs=epochs,\n",
" verbose=1,\n",
- " validation_data=(x_test[:200], y_test[:200]),\n",
+ " validation_data=(x_test, y_test),\n",
" callbacks=[tensorboard_callback, bestmodel_callback, savemodel_callback] )\n",
"\n",
"model.save('./run/models/last-model.h5')"
diff --git a/GTSRB/04-Data-augmentation.ipynb b/GTSRB/04-Data-augmentation.ipynb
index 6a8bfc9..2b87edc 100644
--- a/GTSRB/04-Data-augmentation.ipynb
+++ b/GTSRB/04-Data-augmentation.ipynb
@@ -203,7 +203,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "## 5/ Train the model\n",
+ "## 6/ Train the model\n",
"**Get the shape of my data :**"
]
},
@@ -265,6 +265,7 @@
"# ---- Train\n",
"#\n",
"history = model.fit( datagen.flow(x_train, y_train, batch_size=batch_size),\n",
+ " steps_per_epoch = int(x_train.shape[0]/batch_size),\n",
" epochs=epochs,\n",
" verbose=1,\n",
" validation_data=(x_test, y_test),\n",
@@ -306,7 +307,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "## 6/ History\n",
+ "## 7/ History\n",
"The return of model.fit() returns us the learning history"
]
},
diff --git a/GTSRB/05-Full-convolutions.ipynb b/GTSRB/05-Full-convolutions.ipynb
index 47bec69..364e330 100644
--- a/GTSRB/05-Full-convolutions.ipynb
+++ b/GTSRB/05-Full-convolutions.ipynb
@@ -31,10 +31,11 @@
"import numpy as np\n",
"import h5py\n",
"import os,time,json\n",
+ "import random\n",
"\n",
"from IPython.display import display\n",
"\n",
- "VERSION='1.2'"
+ "VERSION='1.6'"
]
},
{
@@ -50,11 +51,27 @@
"metadata": {},
"outputs": [],
"source": [
+ "# ---- Where I am ?\n",
+ "now = time.strftime(\"%A %d %B %Y - %Hh%Mm%Ss\")\n",
+ "here = os.getcwd()\n",
+ "random.seed(time.time())\n",
+ "tag_id = '{:06}'.format(random.randint(0,99999))\n",
+ "\n",
+ "# ---- Who I am ?\n",
+ "if 'OAR_JOB_ID' in os.environ:\n",
+ " oar_id=os.environ['OAR_JOB_ID']\n",
+ "else:\n",
+ " oar_id='???'\n",
+ "\n",
"print('\\nFull Convolutions Notebook')\n",
"print(' Version : {}'.format(VERSION))\n",
- "print(' Run time : {}'.format(time.strftime(\"%A %-d %B %Y, %H:%M:%S\")))\n",
+ "print(' Now is : {}'.format(now))\n",
+ "print(' OAR id : {}'.format(oar_id))\n",
+ "print(' Tag id : {}'.format(tag_id))\n",
+ "print(' Working directory : {}'.format(here))\n",
"print(' TensorFlow version :',tf.__version__)\n",
- "print(' Keras version :',tf.keras.__version__)"
+ "print(' Keras version :',tf.keras.__version__)\n",
+ "print(' for tensorboard : --logdir {}/run/logs_{}'.format(here,tag_id))"
]
},
{
@@ -77,7 +94,7 @@
" Returns: x_train,y_train,x_test,y_test data'''\n",
" # ---- Read dataset\n",
" filename='./data/'+name+'.h5'\n",
- " with h5py.File(filename) as f:\n",
+ " with h5py.File(filename,'r') as f:\n",
" x_train = f['x_train'][:]\n",
" y_train = f['y_train'][:]\n",
" x_test = f['x_test'][:]\n",
@@ -147,32 +164,27 @@
" model.add( keras.layers.Dense(43, activation='softmax'))\n",
" return model\n",
"\n",
- "# My sphisticated model, but small and fast\n",
- "#\n",
"def get_model_v3(lx,ly,lz):\n",
" model = keras.models.Sequential()\n",
- " model.add( keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(lx,ly,lz)))\n",
- " model.add( keras.layers.MaxPooling2D((2, 2)))\n",
- " model.add( keras.layers.Dropout(0.5))\n",
- "\n",
- " model.add( keras.layers.Conv2D(64, (3, 3), activation='relu'))\n",
- " model.add( keras.layers.MaxPooling2D((2, 2)))\n",
- " model.add( keras.layers.Dropout(0.5))\n",
- "\n",
- " model.add( keras.layers.Conv2D(128, (3, 3), activation='relu'))\n",
- " model.add( keras.layers.MaxPooling2D((2, 2)))\n",
- " model.add( keras.layers.Dropout(0.5))\n",
- "\n",
- " model.add( keras.layers.Conv2D(256, (3, 3), activation='relu'))\n",
- " model.add( keras.layers.MaxPooling2D((2, 2)))\n",
- " model.add( keras.layers.Dropout(0.5))\n",
- "\n",
- " model.add( keras.layers.Flatten()) \n",
- " model.add( keras.layers.Dense(1152, activation='relu'))\n",
- " model.add( keras.layers.Dropout(0.5))\n",
- "\n",
- " model.add( keras.layers.Dense(43, activation='softmax'))\n",
- " return model\n"
+ " model.add(tf.keras.layers.Conv2D(32, (5, 5), padding='same', activation='relu', input_shape=(lx,ly,lz)))\n",
+ " model.add(tf.keras.layers.BatchNormalization(axis=-1)) \n",
+ " model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))\n",
+ " model.add(tf.keras.layers.Dropout(0.2))\n",
+ "\n",
+ " model.add(tf.keras.layers.Conv2D(64, (5, 5), padding='same', activation='relu'))\n",
+ " model.add(tf.keras.layers.BatchNormalization(axis=-1))\n",
+ " model.add(tf.keras.layers.Conv2D(128, (5, 5), padding='same', activation='relu'))\n",
+ " model.add(tf.keras.layers.BatchNormalization(axis=-1))\n",
+ " model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))\n",
+ " model.add(tf.keras.layers.Dropout(0.2))\n",
+ "\n",
+ " model.add(tf.keras.layers.Flatten())\n",
+ " model.add(tf.keras.layers.Dense(512, activation='relu'))\n",
+ " model.add(tf.keras.layers.BatchNormalization())\n",
+ " model.add(tf.keras.layers.Dropout(0.4))\n",
+ "\n",
+ " model.add(tf.keras.layers.Dense(43, activation='softmax'))\n",
+ " return model"
]
},
{
@@ -188,16 +200,23 @@
"metadata": {},
"outputs": [],
"source": [
- "def multi_run(datasets, models, batch_size=64, epochs=16):\n",
+ "def multi_run(datasets, models, datagen=None,\n",
+ " train_size=1, test_size=1, batch_size=64, epochs=16, \n",
+ " verbose=0, extension_dir='last'):\n",
"\n",
- " # ---- Columns of report\n",
+ " # ---- Logs and models dir\n",
+ " #\n",
+ " os.makedirs('./run/logs_{}'.format(extension_dir), mode=0o750, exist_ok=True)\n",
+ " os.makedirs('./run/models_{}'.format(extension_dir), mode=0o750, exist_ok=True)\n",
+ " \n",
+ " # ---- Columns of output\n",
" #\n",
- " report={}\n",
- " report['Dataset']=[]\n",
- " report['Size'] =[]\n",
+ " output={}\n",
+ " output['Dataset']=[]\n",
+ " output['Size'] =[]\n",
" for m in models:\n",
- " report[m+' Accuracy'] = []\n",
- " report[m+' Duration'] = []\n",
+ " output[m+'_Accuracy'] = []\n",
+ " output[m+'_Duration'] = []\n",
"\n",
" # ---- Let's go\n",
" #\n",
@@ -207,11 +226,13 @@
" # ---- Read dataset\n",
" x_train,y_train,x_test,y_test = read_dataset(d_name)\n",
" d_size=os.path.getsize('./data/'+d_name+'.h5')/(1024*1024)\n",
- " report['Dataset'].append(d_name)\n",
- " report['Size'].append(d_size)\n",
+ " output['Dataset'].append(d_name)\n",
+ " output['Size'].append(d_size)\n",
" \n",
" # ---- Get the shape\n",
" (n,lx,ly,lz) = x_train.shape\n",
+ " n_train = int(x_train.shape[0]*train_size)\n",
+ " n_test = int(x_test.shape[0]*test_size)\n",
"\n",
" # ---- For each model\n",
" for m_name,m_function in models.items():\n",
@@ -222,62 +243,51 @@
" # ---- Compile it\n",
" model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
" # ---- Callbacks tensorboard\n",
- " log_dir = \"./run/logs/tb_{}_{}\".format(d_name,m_name)\n",
+ " log_dir = \"./run/logs_{}/tb_{}_{}\".format(extension_dir, d_name, m_name)\n",
" tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)\n",
" # ---- Callbacks bestmodel\n",
- " save_dir = \"./run/models/model_{}_{}.h5\".format(d_name,m_name)\n",
+ " save_dir = \"./run/models_{}/model_{}_{}.h5\".format(extension_dir, d_name, m_name)\n",
" bestmodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, monitor='accuracy', save_best_only=True)\n",
" # ---- Train\n",
" start_time = time.time()\n",
- " history = model.fit( x_train, y_train,\n",
- " batch_size = batch_size,\n",
- " epochs = epochs,\n",
- " verbose = 0,\n",
- " validation_data = (x_test, y_test),\n",
- " callbacks = [tensorboard_callback, bestmodel_callback])\n",
+ " if datagen==None:\n",
+ " # ---- No data augmentation (datagen=None) --------------------------------------\n",
+ " history = model.fit(x_train[:n_train], y_train[:n_train],\n",
+ " batch_size = batch_size,\n",
+ " epochs = epochs,\n",
+ " verbose = verbose,\n",
+ " validation_data = (x_test[:n_test], y_test[:n_test]),\n",
+ " callbacks = [tensorboard_callback, bestmodel_callback])\n",
+ " else:\n",
+ " # ---- Data augmentation (datagen given) ----------------------------------------\n",
+ " datagen.fit(x_train)\n",
+ " history = model.fit(datagen.flow(x_train, y_train, batch_size=batch_size),\n",
+ " steps_per_epoch = int(n_train/batch_size),\n",
+ " epochs = epochs,\n",
+ " verbose = verbose,\n",
+ " validation_data = (x_test[:n_test], y_test[:n_test]),\n",
+ " callbacks = [tensorboard_callback, bestmodel_callback])\n",
+ " \n",
" # ---- Result\n",
" end_time = time.time()\n",
" duration = end_time-start_time\n",
" accuracy = max(history.history[\"val_accuracy\"])*100\n",
" #\n",
- " report[m_name+' Accuracy'].append(accuracy)\n",
- " report[m_name+' Duration'].append(duration)\n",
+ " output[m_name+'_Accuracy'].append(accuracy)\n",
+ " output[m_name+'_Duration'].append(duration)\n",
" print(\"Accuracy={:.2f} and Duration={:.2f})\".format(accuracy,duration))\n",
" except:\n",
- " report[m_name+' Accuracy'].append('-')\n",
- " report[m_name+' Duration'].append('-')\n",
+ " output[m_name+'_Accuracy'].append('0')\n",
+ " output[m_name+'_Duration'].append('999')\n",
" print('-')\n",
- " return report"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 6/ Run\n",
- "### 6.1/ Clean"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "%%bash\n",
- "\n",
- "/bin/rm -r ./run/logs 2>/dev/null\n",
- "/bin/rm -r ./run/models 2>/dev/null\n",
- "/bin/mkdir -p -m 755 ./run/logs\n",
- "/bin/mkdir -p -m 755 ./run/models\n",
- "echo -e \"\\nReset directories : ./run/logs and ./run/models .\""
+ " return output"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
- "### 6.2/ run and save report"
+ "## 6/ Run !"
]
},
{
@@ -290,28 +300,72 @@
"\n",
"print('\\n---- Run','-'*50)\n",
"\n",
- "# ---- Datasets and models list\n",
- "\n",
- "# For tests\n",
- "# datasets = ['set-24x24-L', 'set-24x24-RGB']\n",
- "# models = {'v1':get_model_v1, 'v3':get_model_v3}\n",
- "\n",
- "# The real one\n",
- "datasets = ['set-24x24-L', 'set-24x24-RGB', 'set-48x48-L', 'set-48x48-RGB', 'set-24x24-L-LHE', 'set-24x24-RGB-HE', 'set-48x48-L-LHE', 'set-48x48-RGB-HE']\n",
- "models = {'v1':get_model_v1, 'v2':get_model_v2, 'v3':get_model_v3}\n",
- "\n",
- "# ---- Report name\n",
- "\n",
- "report_name='./run/report-{}.json'.format(time.strftime(\"%Y-%m-%d_%Hh%Mm%Ss\"))\n",
+ "# --------- Datasets, models, and more.. -----------------------------------\n",
+ "#\n",
+ "# ---- For tests\n",
+ "# datasets = ['set-24x24-L', 'set-24x24-RGB']\n",
+ "# models = {'v1':get_model_v1, 'v4':get_model_v2}\n",
+ "# batch_size = 64\n",
+ "# epochs = 2\n",
+ "# train_size = 0.1\n",
+ "# test_size = 0.1\n",
+ "# with_datagen = False\n",
+ "# verbose = 0\n",
+ "#\n",
+ "# ---- All possibilities -> Run A\n",
+ "datasets = ['set-24x24-L', 'set-24x24-RGB', 'set-48x48-L', 'set-48x48-RGB', 'set-24x24-L-LHE', 'set-24x24-RGB-HE', 'set-48x48-L-LHE', 'set-48x48-RGB-HE']\n",
+ "models = {'v1':get_model_v1, 'v2':get_model_v2, 'v3':get_model_v3}\n",
+ "batch_size = 64\n",
+ "epochs = 16\n",
+ "train_size = 1\n",
+ "test_size = 1\n",
+ "with_datagen = False\n",
+ "verbose = 0\n",
+ "#\n",
+ "# ---- Data augmentation -> Run B\n",
+ "# datasets = ['set-48x48-RGB']\n",
+ "# models = {'v2':get_model_v2}\n",
+ "# batch_size = 64\n",
+ "# epochs = 20\n",
+ "# train_size = 1\n",
+ "# test_size = 1\n",
+ "# with_datagen = True\n",
+ "# verbose = 0\n",
+ "#\n",
+ "# ---------------------------------------------------------------------------\n",
"\n",
+ "# ---- Data augmentation\n",
+ "#\n",
+ "if with_datagen :\n",
+ " datagen = keras.preprocessing.image.ImageDataGenerator(featurewise_center=False,\n",
+ " featurewise_std_normalization=False,\n",
+ " width_shift_range=0.1,\n",
+ " height_shift_range=0.1,\n",
+ " zoom_range=0.2,\n",
+ " shear_range=0.1,\n",
+ " rotation_range=10.)\n",
+ "else:\n",
+ " datagen=None\n",
+ " \n",
"# ---- Run\n",
- "\n",
- "out = multi_run(datasets, models, batch_size=64, epochs=2)\n",
+ "#\n",
+ "output = multi_run(datasets, models,\n",
+ " datagen=datagen,\n",
+ " train_size=train_size, test_size=test_size,\n",
+ " batch_size=batch_size, epochs=epochs,\n",
+ " verbose=verbose,\n",
+ " extension_dir=tag_id)\n",
"\n",
"# ---- Save report\n",
+ "#\n",
+ "report={}\n",
+ "report['output']=output\n",
+ "report['description']='train_size={} test_size={} batch_size={} epochs={} data_aug={}'.format(train_size,test_size,batch_size,epochs,with_datagen)\n",
+ "\n",
+ "report_name='./run/report_{}.json'.format(tag_id)\n",
"\n",
- "with open(report_name, 'w') as outfile:\n",
- " json.dump(out, outfile)\n",
+ "with open(report_name, 'w') as file:\n",
+ " json.dump(report, file)\n",
"\n",
"print('\\nReport saved as ',report_name)\n",
"print('-'*59)\n"
diff --git a/GTSRB/05.1-Full-convolutions-batch.ipynb b/GTSRB/05.1-Full-convolutions-batch.ipynb
index cd78bdb..da29279 100644
--- a/GTSRB/05.1-Full-convolutions-batch.ipynb
+++ b/GTSRB/05.1-Full-convolutions-batch.ipynb
@@ -23,18 +23,8 @@
]
},
{
- "cell_type": "code",
- "execution_count": 22,
+ "cell_type": "raw",
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Done.\n"
- ]
- }
- ],
"source": [
"%%bash\n",
"\n",
@@ -56,7 +46,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 1,
"metadata": {},
"outputs": [
{
@@ -64,7 +54,7 @@
"output_type": "stream",
"text": [
"[NbConvertApp] Converting notebook 05-Full-convolutions.ipynb to script\n",
- "[NbConvertApp] Writing 8155 bytes to ./run/full_convolutions.py\n"
+ "[NbConvertApp] Writing 11301 bytes to ./run/full_convolutions_A.py\n"
]
}
],
@@ -73,19 +63,19 @@
"\n",
"# ---- This will convert a notebook to a notebook.py script\n",
"#\n",
- "jupyter nbconvert --to script --output='./run/full_convolutions' '05-Full-convolutions.ipynb'"
+ "jupyter nbconvert --to script --output='./run/full_convolutions_A' '05-Full-convolutions.ipynb'"
]
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "-rwxr-xr-x 1 paroutyj l-simap 8155 Jan 19 22:24 ./run/full_convolutions.py\n"
+ "-rwxr-xr-x 1 paroutyj l-simap 11301 Jan 20 22:11 ./run/full_convolutions_A.py\n"
]
}
],
@@ -110,18 +100,18 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Overwriting ./run/batch_full_convolutions.sh\n"
+ "Overwriting ./run/batch_full_convolutions_A.sh\n"
]
}
],
"source": [
- "%%writefile \"./run/batch_full_convolutions.sh\"\n",
+ "%%writefile \"./run/batch_full_convolutions_A.sh\"\n",
"#!/bin/bash\n",
"#OAR -n Full convolutions\n",
"#OAR -t gpu\n",
"#OAR -l /nodes=1/gpudevice=1,walltime=01:00:00\n",
- "#OAR --stdout full_convolutions.out\n",
- "#OAR --stderr full_convolutions.err\n",
+ "#OAR --stdout _batch/full_convolutions_%jobid%.out\n",
+ "#OAR --stderr _batch/full_convolutions_%jobid%.err\n",
"#OAR --project deeplearningshs\n",
"\n",
"#---- For cpu\n",
@@ -141,7 +131,7 @@
"\n",
"CONDA_ENV=deeplearning2\n",
"RUN_DIR=~/fidle/GTSRB\n",
- "RUN_SCRIPT=./run/full_convolutions.py\n",
+ "RUN_SCRIPT=./run/full_convolutions_A.py\n",
"\n",
"# ---- Cuda Conda initialization\n",
"#\n",
@@ -162,22 +152,22 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "-rwxr-xr-x 1 paroutyj l-simap 955 Jan 19 22:13 ./run/batch_full_convolutions.sh\n",
- "-rwxr-xr-x 1 paroutyj l-simap 8155 Jan 19 22:24 ./run/full_convolutions.py\n"
+ "-rwxr-xr-x 1 paroutyj l-simap 1045 Jan 20 22:12 ./run/batch_full_convolutions_A.sh\n",
+ "-rwxr-xr-x 1 paroutyj l-simap 11301 Jan 20 22:11 ./run/full_convolutions_A.py\n"
]
}
],
"source": [
"%%bash\n",
- "chmod 755 \"./run/batch_full_convolutions.sh\"\n",
- "chmod 755 \"./run/full_convolutions.py\"\n",
+ "chmod 755 ./run/*.sh\n",
+ "chmod 755 ./run/*.py\n",
"ls -l ./run/*full_convolutions*"
]
},
diff --git a/GTSRB/05.2-Full-convolutions-reports.ipynb b/GTSRB/05.2-Full-convolutions-reports.ipynb
index 61e5387..ed87da1 100644
--- a/GTSRB/05.2-Full-convolutions-reports.ipynb
+++ b/GTSRB/05.2-Full-convolutions-reports.ipynb
@@ -19,7 +19,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@@ -38,24 +38,36 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
- "def show_report(report_name):\n",
+ "def highlight_max(s):\n",
+ " is_max = (s == s.max())\n",
+ " return ['background-color: yellow' if v else '' for v in is_max]\n",
+ "\n",
+ "def show_report(file):\n",
" # ---- Read json file\n",
- " with open(report_name) as infile:\n",
+ " with open(file) as infile:\n",
" dict_report = json.load( infile )\n",
+ " output = dict_report['output']\n",
+ " description = dict_report['description']\n",
+ " # ---- about\n",
+ " print(\"\\n\\n\\nReport : \",Path(file).stem)\n",
+ " print( \"Desc. : \",description,'\\n')\n",
" # ---- Create a pandas\n",
- " report = pd.DataFrame (dict_report)\n",
- " models = list(dict_report.keys())[2:]\n",
+ " report = pd.DataFrame (output)\n",
+ " col_accuracy = [ c for c in output.keys() if c.endswith('Accuracy')]\n",
+ " col_duration = [ c for c in output.keys() if c.endswith('Duration')]\n",
" # ---- Build formats\n",
" lambda_acc = lambda x : '{:.2f} %'.format(x) if (isinstance(x, float)) else '{:}'.format(x)\n",
" lambda_dur = lambda x : '{:.1f} s'.format(x) if (isinstance(x, float)) else '{:}'.format(x)\n",
" formats = {'Size':'{:.2f} Mo'}\n",
- " for m in models:\n",
- " formats[m]=lambda_acc if (m.endswith('Accuracy')) else lambda_dur\n",
- " t=report.style.format(formats).hide_index()\n",
+ " for c in col_accuracy: \n",
+ " formats[c]=lambda_acc\n",
+ " for c in col_duration:\n",
+ " formats[c]=lambda_dur\n",
+ " t=report.style.highlight_max(subset=col_accuracy).format(formats).hide_index()\n",
" display(t)"
]
},
@@ -68,7 +80,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 8,
"metadata": {},
"outputs": [
{
@@ -77,7 +89,9 @@
"text": [
"\n",
"\n",
- "Report : report-2020-01-19_22h14m29s \n",
+ "\n",
+ "Report : report_2020_01_20_17h22m23s\n",
+ "Desc. : train_size=1 test_size=1 batch_size=64 epochs=16 data_aug=False \n",
"\n"
]
},
@@ -85,91 +99,97 @@
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
- "</style><table id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7\" ><thead> <tr> <th class=\"col_heading level0 col0\" >Dataset</th> <th class=\"col_heading level0 col1\" >Size</th> <th class=\"col_heading level0 col2\" >v1 Accuracy</th> <th class=\"col_heading level0 col3\" >v1 Duration</th> <th class=\"col_heading level0 col4\" >v2 Accuracy</th> <th class=\"col_heading level0 col5\" >v2 Duration</th> <th class=\"col_heading level0 col6\" >v3 Accuracy</th> <th class=\"col_heading level0 col7\" >v3 Duration</th> </tr></thead><tbody>\n",
+ " #T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col4 {\n",
+ " background-color: yellow;\n",
+ " } #T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col6 {\n",
+ " background-color: yellow;\n",
+ " } #T_24e98e70_3ba8_11ea_9561_9b700250c302row6_col2 {\n",
+ " background-color: yellow;\n",
+ " }</style><table id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302\" ><thead> <tr> <th class=\"col_heading level0 col0\" >Dataset</th> <th class=\"col_heading level0 col1\" >Size</th> <th class=\"col_heading level0 col2\" >v1_Accuracy</th> <th class=\"col_heading level0 col3\" >v1_Duration</th> <th class=\"col_heading level0 col4\" >v2_Accuracy</th> <th class=\"col_heading level0 col5\" >v2_Duration</th> <th class=\"col_heading level0 col6\" >v3_Accuracy</th> <th class=\"col_heading level0 col7\" >v3_Duration</th> </tr></thead><tbody>\n",
" <tr>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row0_col0\" class=\"data row0 col0\" >set-24x24-L</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row0_col1\" class=\"data row0 col1\" >228.77 Mo</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row0_col2\" class=\"data row0 col2\" >5.72 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row0_col3\" class=\"data row0 col3\" >5.0 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row0_col4\" class=\"data row0 col4\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row0_col5\" class=\"data row0 col5\" >2.4 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row0_col6\" class=\"data row0 col6\" >-</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row0_col7\" class=\"data row0 col7\" >-</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row0_col0\" class=\"data row0 col0\" >set-24x24-L</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row0_col1\" class=\"data row0 col1\" >228.77 Mo</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row0_col2\" class=\"data row0 col2\" >95.39 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row0_col3\" class=\"data row0 col3\" >58.2 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row0_col4\" class=\"data row0 col4\" >97.32 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row0_col5\" class=\"data row0 col5\" >52.6 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row0_col6\" class=\"data row0 col6\" >95.16 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row0_col7\" class=\"data row0 col7\" >50.3 s</td>\n",
" </tr>\n",
" <tr>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row1_col0\" class=\"data row1 col0\" >set-24x24-RGB</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row1_col1\" class=\"data row1 col1\" >684.39 Mo</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row1_col2\" class=\"data row1 col2\" >16.62 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row1_col3\" class=\"data row1 col3\" >2.9 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row1_col4\" class=\"data row1 col4\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row1_col5\" class=\"data row1 col5\" >2.5 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row1_col6\" class=\"data row1 col6\" >-</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row1_col7\" class=\"data row1 col7\" >-</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row1_col0\" class=\"data row1 col0\" >set-24x24-RGB</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row1_col1\" class=\"data row1 col1\" >684.39 Mo</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row1_col2\" class=\"data row1 col2\" >96.11 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row1_col3\" class=\"data row1 col3\" >47.2 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row1_col4\" class=\"data row1 col4\" >97.77 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row1_col5\" class=\"data row1 col5\" >55.2 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row1_col6\" class=\"data row1 col6\" >96.52 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row1_col7\" class=\"data row1 col7\" >52.3 s</td>\n",
" </tr>\n",
" <tr>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row2_col0\" class=\"data row2 col0\" >set-48x48-L</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row2_col1\" class=\"data row2 col1\" >913.90 Mo</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row2_col2\" class=\"data row2 col2\" >6.99 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row2_col3\" class=\"data row2 col3\" >8.0 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row2_col4\" class=\"data row2 col4\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row2_col5\" class=\"data row2 col5\" >3.7 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row2_col6\" class=\"data row2 col6\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row2_col7\" class=\"data row2 col7\" >2.0 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row2_col0\" class=\"data row2 col0\" >set-48x48-L</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row2_col1\" class=\"data row2 col1\" >913.90 Mo</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row2_col2\" class=\"data row2 col2\" >95.98 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row2_col3\" class=\"data row2 col3\" >135.2 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row2_col4\" class=\"data row2 col4\" >97.88 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row2_col5\" class=\"data row2 col5\" >118.3 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row2_col6\" class=\"data row2 col6\" >97.38 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row2_col7\" class=\"data row2 col7\" >92.0 s</td>\n",
" </tr>\n",
" <tr>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row3_col0\" class=\"data row3 col0\" >set-48x48-RGB</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row3_col1\" class=\"data row3 col1\" >2736.36 Mo</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row3_col2\" class=\"data row3 col2\" >14.96 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row3_col3\" class=\"data row3 col3\" >8.5 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row3_col4\" class=\"data row3 col4\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row3_col5\" class=\"data row3 col5\" >3.7 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row3_col6\" class=\"data row3 col6\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row3_col7\" class=\"data row3 col7\" >2.1 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col0\" class=\"data row3 col0\" >set-48x48-RGB</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col1\" class=\"data row3 col1\" >2736.36 Mo</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col2\" class=\"data row3 col2\" >96.29 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col3\" class=\"data row3 col3\" >138.7 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col4\" class=\"data row3 col4\" >97.95 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col5\" class=\"data row3 col5\" >124.7 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col6\" class=\"data row3 col6\" >97.53 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row3_col7\" class=\"data row3 col7\" >98.5 s</td>\n",
" </tr>\n",
" <tr>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row4_col0\" class=\"data row4 col0\" >set-24x24-L-LHE</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row4_col1\" class=\"data row4 col1\" >228.77 Mo</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row4_col2\" class=\"data row4 col2\" >8.14 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row4_col3\" class=\"data row4 col3\" >2.7 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row4_col4\" class=\"data row4 col4\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row4_col5\" class=\"data row4 col5\" >2.5 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row4_col6\" class=\"data row4 col6\" >-</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row4_col7\" class=\"data row4 col7\" >-</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row4_col0\" class=\"data row4 col0\" >set-24x24-L-LHE</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row4_col1\" class=\"data row4 col1\" >228.77 Mo</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row4_col2\" class=\"data row4 col2\" >95.79 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row4_col3\" class=\"data row4 col3\" >44.3 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row4_col4\" class=\"data row4 col4\" >96.41 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row4_col5\" class=\"data row4 col5\" >53.1 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row4_col6\" class=\"data row4 col6\" >95.72 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row4_col7\" class=\"data row4 col7\" >50.9 s</td>\n",
" </tr>\n",
" <tr>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row5_col0\" class=\"data row5 col0\" >set-24x24-RGB-HE</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row5_col1\" class=\"data row5 col1\" >684.39 Mo</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row5_col2\" class=\"data row5 col2\" >19.96 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row5_col3\" class=\"data row5 col3\" >2.5 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row5_col4\" class=\"data row5 col4\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row5_col5\" class=\"data row5 col5\" >2.7 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row5_col6\" class=\"data row5 col6\" >-</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row5_col7\" class=\"data row5 col7\" >-</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row5_col0\" class=\"data row5 col0\" >set-24x24-RGB-HE</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row5_col1\" class=\"data row5 col1\" >684.39 Mo</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row5_col2\" class=\"data row5 col2\" >95.35 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row5_col3\" class=\"data row5 col3\" >46.0 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row5_col4\" class=\"data row5 col4\" >96.80 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row5_col5\" class=\"data row5 col5\" >54.5 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row5_col6\" class=\"data row5 col6\" >94.29 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row5_col7\" class=\"data row5 col7\" >52.5 s</td>\n",
" </tr>\n",
" <tr>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row6_col0\" class=\"data row6 col0\" >set-48x48-L-LHE</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row6_col1\" class=\"data row6 col1\" >913.90 Mo</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row6_col2\" class=\"data row6 col2\" >12.69 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row6_col3\" class=\"data row6 col3\" >7.6 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row6_col4\" class=\"data row6 col4\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row6_col5\" class=\"data row6 col5\" >4.0 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row6_col6\" class=\"data row6 col6\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row6_col7\" class=\"data row6 col7\" >2.0 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row6_col0\" class=\"data row6 col0\" >set-48x48-L-LHE</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row6_col1\" class=\"data row6 col1\" >913.90 Mo</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row6_col2\" class=\"data row6 col2\" >96.72 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row6_col3\" class=\"data row6 col3\" >131.8 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row6_col4\" class=\"data row6 col4\" >97.80 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row6_col5\" class=\"data row6 col5\" >117.9 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row6_col6\" class=\"data row6 col6\" >97.16 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row6_col7\" class=\"data row6 col7\" >92.8 s</td>\n",
" </tr>\n",
" <tr>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row7_col0\" class=\"data row7 col0\" >set-48x48-RGB-HE</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row7_col1\" class=\"data row7 col1\" >2736.36 Mo</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row7_col2\" class=\"data row7 col2\" >20.77 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row7_col3\" class=\"data row7 col3\" >9.5 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row7_col4\" class=\"data row7 col4\" >5.56 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row7_col5\" class=\"data row7 col5\" >3.8 s</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row7_col6\" class=\"data row7 col6\" >5.94 %</td>\n",
- " <td id=\"T_deb0ddec_3b01_11ea_a4ca_350a472bdab7row7_col7\" class=\"data row7 col7\" >2.4 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row7_col0\" class=\"data row7 col0\" >set-48x48-RGB-HE</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row7_col1\" class=\"data row7 col1\" >2736.36 Mo</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row7_col2\" class=\"data row7 col2\" >94.58 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row7_col3\" class=\"data row7 col3\" >140.0 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row7_col4\" class=\"data row7 col4\" >97.77 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row7_col5\" class=\"data row7 col5\" >124.6 s</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row7_col6\" class=\"data row7 col6\" >97.11 %</td>\n",
+ " <td id=\"T_24e98e70_3ba8_11ea_9561_9b700250c302row7_col7\" class=\"data row7 col7\" >100.1 s</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
- "<pandas.io.formats.style.Styler at 0x7f5585503390>"
+ "<pandas.io.formats.style.Styler at 0x7f1cc3519dd0>"
]
},
"metadata": {},
@@ -178,36 +198,22 @@
],
"source": [
"for file in glob.glob(\"./run/*.json\"):\n",
- " print(\"\\n\\nReport : \",Path(file).stem,'\\n') \n",
" show_report(file)\n"
]
},
{
- "cell_type": "markdown",
+ "cell_type": "code",
+ "execution_count": null,
"metadata": {},
- "source": [
- "---\n",
- "\n",
- "\n",
- "### Some old results : \n",
- "\n"
- ]
+ "outputs": [],
+ "source": []
},
{
- "cell_type": "markdown",
+ "cell_type": "code",
+ "execution_count": null,
"metadata": {},
- "source": [
- "| Datasets | Size | Model : v1 | Model : v2 | Model : v3 |\n",
- "|:------------------------:|:---------------:|:------------------:|:------------------:|:------------------:|\n",
- "| set-24x24-L | 229 Mo | 95.91% 75.04s | 96.86% 102.28s | - - |\n",
- "| set-24x24-RGB | 684 Mo | 96.60% 77.24s | 97.32% 103.93s | - - |\n",
- "| set-48x48-L | 914 Mo | **96.71%** 123.94s | 97.68% 149.57s | 97.60% 91.53s |\n",
- "| set-48x48-RGB | 2736 Mo | 96.36% 117.74s | **98.20%** 142.63s | 97.28% 91.29s |\n",
- "| set-24x24-L-LHE | 229 Mo | 95.95% 66.12s | 96.75% 89.45s | - - |\n",
- "| set-24x24-RGB-HE | 684 Mo | 95.30% 68.89s | 96.28% 92.15s | - - |\n",
- "| set-48x48-L-LHE | 914 Mo | 96.69% 109.28s | 97.94% 135.17s | **97.97%** 83.80s |\n",
- "| set-48x48-RGB-HE | 2736 Mo | 95.29% 117.70s | **98.13%** 141.56s | 97.00% 89.38s |"
- ]
+ "outputs": [],
+ "source": []
}
],
"metadata": {
diff --git a/GTSRB/99 Scripts-Tensorboard.ipynb b/GTSRB/99 Scripts-Tensorboard.ipynb
index daba57f..2db0f8b 100644
--- a/GTSRB/99 Scripts-Tensorboard.ipynb
+++ b/GTSRB/99 Scripts-Tensorboard.ipynb
@@ -21,14 +21,15 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Tensorbord started - pid is 49306\n"
+ "Tensorbord started - pid is 9934\n",
+ "12399\n"
]
}
],
@@ -39,7 +40,7 @@
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -57,14 +58,14 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Tensorboard process not found...\n"
+ "Tensorbord stopped - pid was 9934\n"
]
}
],
@@ -82,7 +83,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 2,
"metadata": {},
"outputs": [
{
@@ -112,6 +113,7 @@
"\n",
"VERSION='1.2'\n",
"CONDA_ENV='GPU'\n",
+ "HOST_FRONT='f-dahu'\n",
"\n",
"# ---- Usage\n",
"#\n",
@@ -145,16 +147,26 @@
"# ---- Start it\n",
"#\n",
"tensorboard --port $PORT_TSB --host 0.0.0.0 $@ &>/dev/null &\n",
- "\n",
+ " \n",
"# ---- Where is it ?\n",
"#\n",
"sleep 5\n",
"p=\"$(/bin/ps ax | /bin/grep \"tensorboard --port $PORT_TSB\" | /bin/grep -v grep | awk '{print $1}')\"\n",
"if [ -z \"$p\" ]; then\n",
" echo \"Tensorboard didn't start... check your parameters !\"\n",
+ " exit\n",
"else\n",
" echo \"Tensorbord started - pid is $p\"\n",
- "fi"
+ "fi\n",
+ " \n",
+ "# ---- Not on a node ? we give the tunnel\n",
+ "#\n",
+ "if [ \"$(hostname)\" == $HOST_FRONT ]\n",
+ "then\n",
+ " SSH_CMD=\"/usr/bin/ssh -NL 6006:$HOST_FRONT:$PORT_TSB dahu.ciment\"\n",
+ " echo -e \"SSH Tunnel : \\e[93m$SSH_CMD \\e[0m\\n\"\n",
+ "fi\n",
+ " "
]
},
{
--
GitLab