CODEWITHSUNDEEP
tensorflowconv-neural-network
Ahmed Mohamed
Ahmed Mohamed

Reputation: 231

Tensorflow error when using placeholder

I'm beginner in tensorflow and i use it in implementing CNN on images and when i use palceholder with feed_dir it gives me error say

You must Feed a value for placeholder

Grey_images = []
def Read_images(): 
    for filename in glob.glob(r'Path*.jpg'):
        img = Image.open(filename)
        img = img.convert('L')  # convert to gray scale
        img = np.asanyarray(img) 
        img_shape = img.shape
        img_reshaped = img.reshape(224,224,1 channels)
        Grey_images.append(img_reshaped)#[#imgs,224,224,1]

Read_images()
img = tf.placeholder(dtype=tf.float32,shape=[None,224,224,1])

def RunAll():
    layer = Layer(img,1,3,3,64,2,'Relu')

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    Prediction = sess.run(RunAll(),feed_dict={img:Grey_images})

And this is class layer

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

def Conv2d(inp, W ,Stride):

    return tf.nn.conv2d(inp, W, strides=[1, Stride ,Stride, 1], padding='SAME')

class Layer:
    def __init__(self, inp,inp_channels_num,filter_width_size,filter_height_size,outp_channels_num,stride,activation_func):
        sess = tf.Session()
        self.W_conv = weight_variable([filter_width_size, filter_height_size, inp_channels_num, outp_channels_num])
        self.b_conv = bias_variable([outp_channels_num])    
        if (activation_func=='Sigmoid'):
            self.h_conv = tf.nn.sigmoid(Conv2d(inp, self.W_conv, stride) + self.b_conv)
        else:
            self.h_conv = tf.nn.relu(Conv2d(inp, self.W_conv, stride) + self.b_conv)
        sess.run(tf.global_variables_initializer())            
        self.h_conv = sess.run(self.h_conv)
        sess.close()

It gives me the error in this line however i use feed_dir in sess.run(Runall()) so what am i missing ?

self.h_conv = sess.run(self.h_conv)

Upvotes: 0

Views: 166

Answers (2)

Alexandre Passos
Alexandre Passos

Reputation: 5206

The line where you run self.h_conv also needs a feed_dict provided.

Upvotes: 1

Raady
Raady

Reputation: 1726

your whole program run on the same line, you haven't mentioned what the error is ?

update

in function Read_images() you created have no return any value, so last line in function you should add return Grey_images

and you are not saving the values after you read images. in the program line Read_lines() change to Grey_images = Read_lines()

Upvotes: 0

Related Questions