Skip to content
Snippets Groups Projects
Commit b32677bc authored by Soraya Arias's avatar Soraya Arias
Browse files

Add run directory creation

parent 79f354d1
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
GTSRB/02-First-convolutions.ipynb
+ 2
− 1
View file @ b32677bc
%% Cell type:markdown id: tags:
<img width="800px" src="../fidle/img/00-Fidle-header-01.svg"></img>
# <!-- TITLE --> [GTS2] - CNN with GTSRB dataset - First convolutions
<!-- DESC --> Episode 2 : First convolutions and first results
<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->
## Objectives :
- Recognizing traffic signs
- Understand the **principles** and **architecture** of a **convolutional neural network** for image classification
The German Traffic Sign Recognition Benchmark (GTSRB) is a dataset with more than 50,000 photos of road signs from about 40 classes.
The final aim is to recognise them !
Description is available there : http://benchmark.ini.rub.de/?section=gtsrb&subsection=dataset
## What we're going to do :
- Read H5 dataset
- Build a model
- Train the model
- Evaluate the model
## Step 1 - Import and init
### 1.1 - Python
%% 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 matplotlib.pyplot as plt
import h5py
import os,time,sys
from importlib import reload
sys.path.append('..')
import fidle.pwk as ooo
ooo.init()
os.makedirs('./run/', mode=0o750, exist_ok=True)
```
%% Output
FIDLE 2020 - Practical Work Module
Version : 0.4.3
Run time : Friday 28 February 2020, 10:25:11
TensorFlow version : 2.0.0
Keras version : 2.2.4-tf
%% Cell type:markdown id: tags:
### 1.2 - Where are we ?
%% Cell type:code id: tags:
``` python
place, dataset_dir = ooo.good_place( { 'GRICAD' : f'{os.getenv("SCRATCH_DIR","")}/PROJECTS/pr-fidle/datasets/GTSRB',
'IDRIS' : f'{os.getenv("WORK","")}/datasets/GTSRB',
'HOME' : f'{os.getenv("HOME","")}/datasets/GTSRB'} )
```
%% Output
Well, we should be at GRICAD !
We are going to use: /bettik/PROJECTS/pr-fidle/datasets/GTSRB
%% Cell type:markdown id: tags:
## Step 2 - Load dataset
We're going to retrieve a previously recorded dataset.
For example: set-24x24-L
%% Cell type:code id: tags:
``` python
%%time
def read_dataset(dataset_dir, name):
'''Reads h5 dataset from dataset_dir
Args:
dataset_dir : datasets dir
name : dataset name, without .h5
Returns: x_train,y_train,x_test,y_test data'''
# ---- Read dataset
filename=f'{dataset_dir}/{name}.h5'
with h5py.File(filename,'r') 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(dataset_dir, 'set-24x24-L')
```
%% Output
Dataset "set-24x24-L" is loaded. (228.8 Mo)
CPU times: user 16 ms, sys: 128 ms, total: 144 ms
Wall time: 239 ms
%% Cell type:markdown id: tags:
## Step 3 - Have a look to the dataset
We take a quick look as we go by...
%% 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)
```
%% Output
x_train : (39209, 24, 24, 1)
y_train : (39209,)
x_test : (12630, 24, 24, 1)
y_test : (12630,)
%% Cell type:markdown id: tags:
## Step 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
# A more sophisticated model
#
def get_model_v2(lx,ly,lz):
model = keras.models.Sequential()
model.add( keras.layers.Conv2D(64, (3, 3), padding='same', input_shape=(lx,ly,lz), activation='relu'))
model.add( keras.layers.Conv2D(64, (3, 3), activation='relu'))
model.add( keras.layers.MaxPooling2D(pool_size=(2, 2)))
model.add( keras.layers.Dropout(0.2))
model.add( keras.layers.Conv2D(128, (3, 3), padding='same', activation='relu'))
model.add( keras.layers.Conv2D(128, (3, 3), activation='relu'))
model.add( keras.layers.MaxPooling2D(pool_size=(2, 2)))
model.add( keras.layers.Dropout(0.2))
model.add( keras.layers.Conv2D(256, (3, 3), padding='same',activation='relu'))
model.add( keras.layers.Conv2D(256, (3, 3), activation='relu'))
model.add( keras.layers.MaxPooling2D(pool_size=(2, 2)))
model.add( keras.layers.Dropout(0.2))
model.add( keras.layers.Flatten())
model.add( keras.layers.Dense(512, activation='relu'))
model.add( keras.layers.Dropout(0.5))
model.add( keras.layers.Dense(43, activation='softmax'))
return model
# My sphisticated model, but small and fast
#
def get_model_v3(lx,ly,lz):
model = keras.models.Sequential()
model.add( keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(lx,ly,lz)))
model.add( keras.layers.MaxPooling2D((2, 2)))
model.add( keras.layers.Dropout(0.5))
model.add( keras.layers.Conv2D(64, (3, 3), activation='relu'))
model.add( keras.layers.MaxPooling2D((2, 2)))
model.add( keras.layers.Dropout(0.5))
model.add( keras.layers.Conv2D(128, (3, 3), activation='relu'))
model.add( keras.layers.MaxPooling2D((2, 2)))
model.add( keras.layers.Dropout(0.5))
model.add( keras.layers.Conv2D(256, (3, 3), activation='relu'))
model.add( keras.layers.MaxPooling2D((2, 2)))
model.add( keras.layers.Dropout(0.5))
model.add( keras.layers.Flatten())
model.add( keras.layers.Dense(1152, activation='relu'))
model.add( keras.layers.Dropout(0.5))
model.add( keras.layers.Dense(43, activation='softmax'))
return model
```
%% Cell type:markdown id: tags:
## Step 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))
```
%% Output
Images of the dataset have this folowing shape : (24, 24, 1)
%% 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()
img=keras.utils.plot_model( model, to_file='./run/model.png', show_shapes=True, show_layer_names=True, dpi=72)
display(img)
model.compile(optimizer = 'adam',
loss = 'sparse_categorical_crossentropy',
metrics = ['accuracy'])
```
%% Output
Model: "sequential_2"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_4 (Conv2D) (None, 22, 22, 96) 960
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 11, 11, 96) 0
_________________________________________________________________
dropout_6 (Dropout) (None, 11, 11, 96) 0
_________________________________________________________________
conv2d_5 (Conv2D) (None, 9, 9, 192) 166080
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 4, 4, 192) 0
_________________________________________________________________
dropout_7 (Dropout) (None, 4, 4, 192) 0
_________________________________________________________________
flatten_2 (Flatten) (None, 3072) 0
_________________________________________________________________
dense_4 (Dense) (None, 1500) 4609500
_________________________________________________________________
dropout_8 (Dropout) (None, 1500) 0
_________________________________________________________________
dense_5 (Dense) (None, 43) 64543
=================================================================
Total params: 4,841,083
Trainable params: 4,841,083
Non-trainable params: 0
_________________________________________________________________
%% Cell type:markdown id: tags:
**Train it :**
%% Cell type:code id: tags:
``` python
%%time
batch_size = 64
epochs = 5
# ---- Shuffle train data
x_train,y_train=ooo.shuffle_np_dataset(x_train,y_train)
# ---- Train
history = model.fit( x_train, y_train,
batch_size = batch_size,
epochs = epochs,
verbose = 1,
validation_data = (x_test, y_test))
```
%% Output
Train on 39209 samples, validate on 12630 samples
Epoch 1/5
39209/39209 [==============================] - 9s 225us/sample - loss: 1.2385 - accuracy: 0.6579 - val_loss: 0.4697 - val_accuracy: 0.8898
Epoch 2/5
39209/39209 [==============================] - 2s 61us/sample - loss: 0.2207 - accuracy: 0.9373 - val_loss: 0.3298 - val_accuracy: 0.9228
Epoch 3/5
39209/39209 [==============================] - 2s 61us/sample - loss: 0.1194 - accuracy: 0.9659 - val_loss: 0.2805 - val_accuracy: 0.9370
Epoch 4/5
39209/39209 [==============================] - 2s 61us/sample - loss: 0.0849 - accuracy: 0.9756 - val_loss: 0.2571 - val_accuracy: 0.9390
Epoch 5/5
39209/39209 [==============================] - 2s 61us/sample - loss: 0.0637 - accuracy: 0.9809 - val_loss: 0.2219 - val_accuracy: 0.9497
CPU times: user 16 s, sys: 2.3 s, total: 18.4 s
Wall time: 18.7 s
%% 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))
```
%% Output
Max validation accuracy is : 0.9497
%% 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]))
```
%% Output
Test loss : 0.2219
Test accuracy : 0.9497
%% Cell type:markdown id: tags:
<div class="todo">
What you can do:
<ul>
<li>Try the different models</li>
<li>Try with different datasets</li>
<li>Test different hyperparameters (epochs, batch size, optimization, etc.)</li>
<li>Create your own model</li>
</ul>
</div>
%% Cell type:markdown id: tags:
---
<img width="80px" src="../fidle/img/00-Fidle-logo-01.svg"></img>
......
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