Skip to content
Snippets Groups Projects
Commit 969a596c authored by Jean-Luc Parouty Jean-Luc.Parouty@simap.grenoble-inp.fr's avatar Jean-Luc Parouty Jean-Luc.Parouty@simap.grenoble-inp.fr
Browse files

Add data augmentation

parent d5434aea
No related branches found
No related tags found
No related merge requests found
Expand all Hide whitespace changes
Inline Side-by-side
GTSRB/03-Tracking-and-visualizing.ipynb
+ 0
− 1
View file @ 969a596c
%% Cell type:markdown id: tags:
German Traffic Sign Recognition Benchmark (GTSRB)
=================================================
---
Introduction au Deep Learning (IDLE) - S. Aria, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020
## Episode 3 : Tracking, visualizing and save models
Our main steps:
- Monitoring and understanding our model training
- Add recovery points
- Analyze the results
- Restore and run recovery pont
## 1/ Import and init
%% Cell type:code id: tags:
``` python
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.callbacks import TensorBoard
import numpy as np
import h5py
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sn
import os, time, random
import idle.pwk as ooo
from importlib import reload
ooo.init()
```
%% Cell type:markdown id: tags:
## 2/ Load dataset
Dataset is one of the saved dataset: RGB25, RGB35, L25, L35, etc.
First of all, we're going to use a smart dataset : **set-24x24-L**
(with a GPU, it only takes 35'' compared to more than 5' with a CPU !)
%% Cell type:code id: tags:
``` python
%%time
def read_dataset(name):
'''Reads h5 dataset from ./data
Arguments: dataset name, without .h5
Returns: x_train,y_train,x_test,y_test data'''
# ---- Read dataset
filename='./data/'+name+'.h5'
with h5py.File(filename) as f:
x_train = f['x_train'][:]
y_train = f['y_train'][:]
x_test = f['x_test'][:]
y_test = f['y_test'][:]
# ---- done
print('Dataset "{}" is loaded. ({:.1f} Mo)\n'.format(name,os.path.getsize(filename)/(1024*1024)))
return x_train,y_train,x_test,y_test
x_train,y_train,x_test,y_test = read_dataset('set-24x24-L')
```
%% Cell type:markdown id: tags:
## 3/ Have a look to the dataset
Note: Data must be reshape for matplotlib
%% Cell type:code id: tags:
``` python
print("x_train : ", x_train.shape)
print("y_train : ", y_train.shape)
print("x_test : ", x_test.shape)
print("y_test : ", y_test.shape)
ooo.plot_images(x_train, y_train, range(12), columns=6, x_size=2, y_size=2)
ooo.plot_images(x_train, y_train, range(36), columns=12, x_size=1, y_size=1)
```
%% Cell type:markdown id: tags:
## 4/ Create model
We will now build a model and train it...
Some models...
%% Cell type:code id: tags:
``` python
# A basic model
#
def get_model_v1(lx,ly,lz):
model = keras.models.Sequential()
model.add( keras.layers.Conv2D(96, (3,3), activation='relu', input_shape=(lx,ly,lz)))
model.add( keras.layers.MaxPooling2D((2, 2)))
model.add( keras.layers.Dropout(0.2))
model.add( keras.layers.Conv2D(192, (3, 3), activation='relu'))
model.add( keras.layers.MaxPooling2D((2, 2)))
model.add( keras.layers.Dropout(0.2))
model.add( keras.layers.Flatten())
model.add( keras.layers.Dense(1500, activation='relu'))
model.add( keras.layers.Dropout(0.5))
model.add( keras.layers.Dense(43, activation='softmax'))
return model
```
%% Cell type:markdown id: tags:
## 5/ Prepare callbacks
We will add 2 callbacks :
- **TensorBoard**
Training logs, which can be visualised with Tensorboard.
`#tensorboard --logdir ./run/logs`
IMPORTANT : Relancer tensorboard à chaque run
- **Model backup**
It is possible to save the model each xx epoch or at each improvement.
The model can be saved completely or partially (weight).
For full format, we can use HDF5 format.
%% Cell type:code id: tags:
``` python
%%bash
# To clean old logs and saved model, run this cell
#
#/bin/rm -r ./run/logs 2>/dev/null
#/bin/rm -r ./run/models 2>/dev/null
/bin/ls -l ./run 2>/dev/null
```
%% Cell type:code id: tags:
``` python
ooo.mkdir('./run/models')
ooo.mkdir('./run/logs')
# ---- Callback tensorboard
log_dir = "./run/logs/tb_" + ooo.tag_now()
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)
# ---- Callback ModelCheckpoint - Save best model
save_dir = "./run/models/best-model.h5"
bestmodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, monitor='accuracy', save_best_only=True)
# ---- Callback ModelCheckpoint - Save model each epochs
save_dir = "./run/models/model-{epoch:04d}.h5"
savemodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, save_freq=2000*5)
```
%% Cell type:markdown id: tags:
## 5/ Train the model
**Get the shape of my data :**
%% Cell type:code id: tags:
``` python
(n,lx,ly,lz) = x_train.shape
print("Images of the dataset have this folowing shape : ",(lx,ly,lz))
```
%% Cell type:markdown id: tags:
**Get and compile a model, with the data shape :**
%% Cell type:code id: tags:
``` python
model = get_model_v1(lx,ly,lz)
# model.summary()
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
```
%% Cell type:markdown id: tags:
**Train it :**
Note : La courbe d'apprentissage est visible en temps réel avec Tensorboard :
`#tensorboard --logdir ./run/logs`
%% Cell type:code id: tags:
``` python
%%time
batch_size = 64
epochs = 30
# ---- Shuffle train data
x_train,y_train=ooo.shuffle_np_dataset(x_train,y_train)
# ---- Train
# Note: To be faster in our example, we can take only 2000 values
#
history = model.fit( x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test[:200], y_test[:200]),
callbacks=[tensorboard_callback, bestmodel_callback, savemodel_callback] )
model.save('./run/models/last-model.h5')
```
%% Cell type:markdown id: tags:
**Evaluate it :**
%% Cell type:code id: tags:
``` python
max_val_accuracy = max(history.history["val_accuracy"])
print("Max validation accuracy is : {:.4f}".format(max_val_accuracy))
```
%% Cell type:code id: tags:
``` python
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss : {:5.4f}'.format(score[0]))
print('Test accuracy : {:5.4f}'.format(score[1]))
```
%% Cell type:markdown id: tags:
## 6/ History
The return of model.fit() returns us the learning history
%% Cell type:code id: tags:
``` python
ooo.plot_history(history)
```
%% Cell type:markdown id: tags:
## 7/ Evaluation and confusion
%% Cell type:code id: tags:
``` python
reload(ooo)
y_pred = model.predict_classes(x_test)
conf_mat = confusion_matrix(y_test,y_pred, normalize="true", labels=range(43))
ooo.plot_confusion_matrix(conf_mat)
```
%% Cell type:markdown id: tags:
## 8/ Restore and evaluate
### 8.1/ List saved models :
%% Cell type:code id: tags:
``` python
!find ./run/models/
```
%% Cell type:markdown id: tags:
### 8.2/ Restore a model :
%% Cell type:code id: tags:
``` python
loaded_model = tf.keras.models.load_model('./run/models/best-model.h5')
# best_model.summary()
print("Loaded.")
```
%% Cell type:markdown id: tags:
### 8.3/ Evaluate it :
%% Cell type:code id: tags:
``` python
score = loaded_model.evaluate(x_test, y_test, verbose=0)
print('Test loss : {:5.4f}'.format(score[0]))
print('Test accuracy : {:5.4f}'.format(score[1]))
```
%% Cell type:markdown id: tags:
### 8.4/ Make a prediction :
%% Cell type:code id: tags:
``` python
# ---- Get a random image
#
i = random.randint(1,len(x_test))
x,y = x_test[i], y_test[i]
# ---- Do prediction
#
predictions = loaded_model.predict( np.array([x]) )
# ---- A prediction is just the output layer
#
print("\nOutput layer from model is (x100) :\n")
with np.printoptions(precision=2, suppress=True, linewidth=95):
print(predictions*100)
# ---- Graphic visualisation
#
print("\nGraphically :\n")
plt.figure(figsize=(12,2))
plt.bar(range(43), predictions[0], align='center', alpha=0.5)
plt.ylabel('Probability')
plt.ylim((0,1))
plt.xlabel('Class')
plt.title('Trafic Sign prediction')
plt.show()
# ---- Predict class
#
p = np.argmax(predictions)
# ---- Show result
#
print("\nPrediction on the left, real stuff on the right :\n")
ooo.plot_images([x,x_meta[y]], [p,y], range(2), columns=3, x_size=3, y_size=2)
if p==y:
print("YEEES ! that's right!")
else:
print("oups, that's wrong ;-(")
```
%% Cell type:markdown id: tags:
---
That's all folks !
%% Cell type:code id: tags:
``` python
```
......
GTSRB/04-Data-augmentation.ipynb
+ 461
− 141
View file @ 969a596c
Source diff could not be displayed: it is too large. Options to address this: view the blob.
GTSRB/04.1-Data-augmentation.ipynb 0 → 100644
+ 353
− 0
View file @ 969a596c
This diff is collapsed.
GTSRB/99 Run-Tensorboard.ipynb
+ 75
− 7
View file @ 969a596c
%% Cell type:markdown id: tags:
Running Tensorboard from Jupyter lab
====================================
---
Introduction au Deep Learning (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020
Vesion : 1.0
%% Cell type:markdown id: tags:
## Méthode 1 : Shell execute
**Start**
%% Cell type:code id: tags:
``` python
%%bash
tensorboard_start --logdir ./run/logs
```
%% Output
Tensorbord started with pid 84593
Tensorbord started with pid 80451
%% Cell type:code id: tags:
``` python
%%bash
tensorboard_stop
```
%% Output
Tensorboard process not found...
%% Cell type:code id: tags:
``` python
%%bash
# ---- Port number,
PORT_JPY="$(id -u)"
PORT_TSB="$(( $PORT_J + 10000 ))"
HOST_G="$(hostname)"
SSH_CMD="/usr/bin/ssh -NL 8888:$HOST_G:$PORT_J -L 6006:$HOST_G:$PORT_T dahu.ciment"
tensorboard --port 21277 --host 0.0.0.0 --logdir ./run/logs &>/dev/null &
# tensorboard --port 21277 --host 0.0.0.0 --logdir ./run/logs &>/dev/null &
tensorboard --port 21277 --host 0.0.0.0 --logdir ./run/logs 2>&1
```
%% Output
W0113 22:02:28.498013 140212267140864 plugin_event_accumulator.py:294] Found more than one graph event per run, or there was a metagraph containing a graph_def, as well as one or more graph events. Overwriting the graph with the newest event.
TensorBoard 2.0.0 at http://0.0.0.0:21277/ (Press CTRL+C to quit)
Traceback (most recent call last):
File "/home/paroutyj/.conda/envs/deeplearning2/bin/tensorboard", line 10, in <module>
sys.exit(run_main())
File "/home/paroutyj/.conda/envs/deeplearning2/lib/python3.7/site-packages/tensorboard/main.py", line 64, in run_main
app.run(tensorboard.main, flags_parser=tensorboard.configure)
File "/home/paroutyj/.conda/envs/deeplearning2/lib/python3.7/site-packages/absl/app.py", line 299, in run
_run_main(main, args)
File "/home/paroutyj/.conda/envs/deeplearning2/lib/python3.7/site-packages/absl/app.py", line 250, in _run_main
sys.exit(main(argv))
File "/home/paroutyj/.conda/envs/deeplearning2/lib/python3.7/site-packages/tensorboard/program.py", line 222, in main
self._register_info(server)
File "/home/paroutyj/.conda/envs/deeplearning2/lib/python3.7/site-packages/tensorboard/program.py", line 268, in _register_info
manager.write_info_file(info)
File "/home/paroutyj/.conda/envs/deeplearning2/lib/python3.7/site-packages/tensorboard/manager.py", line 268, in write_info_file
with open(_get_info_file_path(), "w") as outfile:
PermissionError: [Errno 13] Permission denied: '/tmp/.tensorboard-info/pid-94212.info'
---------------------------------------------------------------------------
CalledProcessError Traceback (most recent call last)
<ipython-input-19-d5c18c938787> in <module>
----> 1 get_ipython().run_cell_magic('bash', '', '\n# ---- Port number, \nPORT_JPY="$(id -u)"\nPORT_TSB="$(( $PORT_J + 10000 ))"\nHOST_G="$(hostname)"\nSSH_CMD="/usr/bin/ssh -NL 8888:$HOST_G:$PORT_J -L 6006:$HOST_G:$PORT_T dahu.ciment"\n\n# tensorboard --port 21277 --host 0.0.0.0 --logdir ./run/logs &>/dev/null &\ntensorboard --port 21277 --host 0.0.0.0 --logdir ./run/logs 2>&1\n')
~/.conda/envs/deeplearning2/lib/python3.7/site-packages/IPython/core/interactiveshell.py in run_cell_magic(self, magic_name, line, cell)
2350 with self.builtin_trap:
2351 args = (magic_arg_s, cell)
-> 2352 result = fn(*args, **kwargs)
2353 return result
2354
~/.conda/envs/deeplearning2/lib/python3.7/site-packages/IPython/core/magics/script.py in named_script_magic(line, cell)
140 else:
141 line = script
--> 142 return self.shebang(line, cell)
143
144 # write a basic docstring:
</home/paroutyj/.conda/envs/deeplearning2/lib/python3.7/site-packages/decorator.py:decorator-gen-110> in shebang(self, line, cell)
~/.conda/envs/deeplearning2/lib/python3.7/site-packages/IPython/core/magic.py in <lambda>(f, *a, **k)
185 # but it's overkill for just that one bit of state.
186 def magic_deco(arg):
--> 187 call = lambda f, *a, **k: f(*a, **k)
188
189 if callable(arg):
~/.conda/envs/deeplearning2/lib/python3.7/site-packages/IPython/core/magics/script.py in shebang(self, line, cell)
243 sys.stderr.flush()
244 if args.raise_error and p.returncode!=0:
--> 245 raise CalledProcessError(p.returncode, cell, output=out, stderr=err)
246
247 def _run_script(self, p, cell, to_close):
CalledProcessError: Command 'b'\n# ---- Port number, \nPORT_JPY="$(id -u)"\nPORT_TSB="$(( $PORT_J + 10000 ))"\nHOST_G="$(hostname)"\nSSH_CMD="/usr/bin/ssh -NL 8888:$HOST_G:$PORT_J -L 6006:$HOST_G:$PORT_T dahu.ciment"\n\n# tensorboard --port 21277 --host 0.0.0.0 --logdir ./run/logs &>/dev/null &\ntensorboard --port 21277 --host 0.0.0.0 --logdir ./run/logs 2>&1\n'' returned non-zero exit status 1.
%% Cell type:code id: tags:
``` python
!echo "This a test">/tmp/.tensorboard-info/foobar-655465.txt
#!cat /tmp/foobar-655465.txt
#!rm /tmp/foobar-655465.txt
!ls -ld /tmp/.tensorboard-info
!ls -ld /tmp/.tensorboard-info/*
See : https://github.com/tensorflow/tensorboard/issues/2010
```
%% Output
/bin/sh: 1: cannot create /tmp/.tensorboard-info/foobar-655465.txt: Permission denied
drwxr-xr-x 2 juanbaldonado l-inria 60 Jan 13 21:00 /tmp/.tensorboard-info
-rw-r--r-- 1 juanbaldonado l-inria 346 Jan 13 21:00 /tmp/.tensorboard-info/pid-74153.info
%% Cell type:markdown id: tags:
**Check**
%% Cell type:code id: tags:
``` python
!echo $(ps ax | grep 'tensorboard --port 21277' | grep -v grep | awk '{print $1}')
```
%% Output
84593
%% Cell type:code id: tags:
``` python
!ps ax | grep tensorboard
!pwd
```
%% Output
83294 pts/0 Ss+ 0:00 /bin/sh -c ps ax | grep tensorboard
83296 pts/0 S+ 0:00 grep tensorboard
/home/paroutyj/fidle/GTSRB
%% Cell type:markdown id: tags:
**Stop**
%% Cell type:code id: tags:
``` python
%%bash
p="$(ps ax | grep 'tensorboard --port 21277' | grep -v grep | awk '{print $1}')"
if [ -z ${p} ]; then echo "No process"; else kill $p; echo "Ended ($p)" ; fi
```
%% Output
Ended (82555)
%% Cell type:markdown id: tags:
## Méthode 2 : Magic command
**Start**
%% Cell type:code id: tags:
``` python
%load_ext tensorboard
```
%% Cell type:code id: tags:
``` python
%tensorboard --port 21277 --host 0.0.0.0 --logdir ./run/logs
```
%% Cell type:markdown id: tags:
**Stop**
No way... use bash method
## Methode 3 : Tensorboard module
**Start**
%% Cell type:code id: tags:
``` python
import tensorboard.notebook as tsb
```
%% Cell type:code id: tags:
``` python
tsb.start('--port 21277 --host 0.0.0.0 --logdir ./run/logs')
```
%% Output
%% Cell type:markdown id: tags:
**Check**
%% Cell type:code id: tags:
``` python
a=tsb.list()
```
%% Cell type:markdown id: tags:
**Stop**
No way... use bash method
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment