CNN output regression in tflearn

Question

I'm working on a self driving car. I want to predict steering angle from pictures using a CNN in tflearn. The problem is that it only outputs 0.1. What do you think is the problem? The pictures is 128x128 but I have tried to resize them to 28x28 so I can use the code from the mnist example. The lables is steering angles between 0 and 180. I can also say that the loss is not getting any smaller when training.

Training.py

import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
import tflearn.datasets.mnist as mnist
import numpy
from scipy import misc
import csv

nrOfFiles = 0
csv_list = []

with open('/Users/gustavoskarsson/Desktop/car/csvfile.csv', 'r') as f:
    reader = csv.reader(f)
    csv_list = list(reader)

nrOfFiles = len(csv_list)

pics = []
face = misc.face()
for i in range(0, nrOfFiles):
    face = misc.imread('/Users/gustavoskarsson/Desktop/car/pics/' + str(i) + '.jpg')
    face = misc.imresize(face[:,:,0], (28, 28))
    pics.append(face)

X = numpy.array(pics)


steer = []
throt = []
for i in range(0, nrOfFiles):
    steer.append(csv_list[i][1])
    throt.append(csv_list[i][2])

#y__ = numpy.array([steer, throt])
Y = numpy.array(steer)
Y = Y.reshape(-1, 1)
#Strunta i gasen till att börja med.


convnet = input_data(shape=[None, 28, 28, 1], name='input')

convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)

convnet = fully_connected(convnet, 1, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=0.01, loss='mean_square', name='targets')

model = tflearn.DNN(convnet)
model.fit(X, Y, n_epoch=6, batch_size=10, show_metric=True)
model.save('mod.model')

Predict.py

import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
import tflearn.datasets.mnist as mnist
import numpy
from scipy import misc


convnet = input_data(shape=[None, 28, 28, 1], name='input')
                           #[none, 28,  28, 1]

convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)

convnet = fully_connected(convnet, 1, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=0.01, loss='mean_square', name='targets')

model = tflearn.DNN(convnet)
model.load('mod.model')

#load test image
face = misc.face()
pics = []
for i in range(0, 3):
    face = misc.imread('/Users/gustavoskarsson/Desktop/car/pics/' + str(i) + '.jpg')
    face = misc.imresize(face[:,:,0], (28, 28))
    pics.append(face) 

test_x = numpy.array(pics)
test_x = test_x.reshape([-1, 28, 28, 1])
print(model.predict([test_x[0]]))

Michail N Michail N · Accepted Answer · 2017-09-22T13:43:19

You overwrite convent variable which has the convolution network for each layer. Also you should down sample in each layer. Your code should be like:

    x = tf.reshape(x, shape=[-1, 28, 28, 1])

    # Convolution Layer with 32 filters and a kernel size of 5
    conv1 = tf.layers.conv2d(x, 32, 5, activation=tf.nn.relu)

    # Max Pooling (down-sampling) with strides of 2 and kernel size of 2
    conv1 = tf.layers.max_pooling2d(conv1, 2, 2)

    # Convolution Layer with 64 filters and a kernel size of 3
    conv2 = tf.layers.conv2d(conv1, 64, 3, activation=tf.nn.relu)

    # Max Pooling (down-sampling) with strides of 2 and kernel size of 2
    conv2 = tf.layers.max_pooling2d(conv2, 2, 2)

You can see a here also

CNN output regression in tflearn

2 Answers