Kernel Restarting The kernel appears to have died & dst tensor is not initialized - windows

Question

I'm using Tensorflow (GPU) to fit a CNN model (the total input datasize is only 9.8MB(np array form) and I'm on Windows 10 (Kaby Lake), Tensorflow GPU mode, Geforce GTX 1050, RAM 32GB.
Each time I try running this below piece of code, it either ends the kernel or throws up the error "dst tensor is not initialized". This code seems to be executable by others with relatively lower computing power than mine but I'm not sure how to get it to work.
I am able to run the below code on Tensorflow CPU mode without any problem (but it takes almost 12 hours to finish running it, especially with the epoch is set to more than just 3). That's why I need to run it using my GPU for faster execution.
import tensorflow as tf
import numpy as np
IMG_PX_SIZE = 50
HM_SLICES = 20
n_classes = 2
x = tf.placeholder('float')
y = tf.placeholder('float')
keep_rate = 0.8
keep_prob = tf.placeholder(tf.float32)
def conv3d(x, W):
return tf.nn.conv3d(x, W, strides=[1,1,1,1,1], padding='SAME')
def maxpool3d(x):
return tf.nn.max_pool3d(x, ksize=[1,2,2,2,1], strides=[1,2,2,2,1],
padding='SAME')
def convolutional_neural_network(x):
weights = {'W_conv1':tf.Variable(tf.random_normal([3,3,3,1,32])),
'W_conv2':tf.Variable(tf.random_normal([3,3,3,32,64])),
'W_fc':tf.Variable(tf.random_normal([62720 ,1024])),
'out':tf.Variable(tf.random_normal([1024, n_classes]))}
biases = {'b_conv1':tf.Variable(tf.random_normal([32])),
'b_conv2':tf.Variable(tf.random_normal([64])),
'b_fc':tf.Variable(tf.random_normal([1024])),
'out':tf.Variable(tf.random_normal([n_classes]))}
x = tf.reshape(x, shape=[-1, IMG_PX_SIZE, IMG_PX_SIZE, HM_SLICES, 1])
conv1 = tf.nn.relu(conv3d(x, weights['W_conv1']) + biases['b_conv1'])
conv1 = maxpool3d(conv1)
conv2 = tf.nn.relu(conv3d(conv1, weights['W_conv2']) + biases['b_conv2'])
conv2 = maxpool3d(conv2)
fc = tf.reshape(conv2,[-1, 62720 ])
fc = tf.nn.relu(tf.matmul(fc, weights['W_fc'])+biases['b_fc'])
fc = tf.nn.dropout(fc, keep_rate)
output = tf.matmul(fc, weights['out']) + biases['out']
return output
def train_neural_network(x):
much_data = np.load('muchdata_sampled-50-50-20.npy')
train_data = much_data[:100]
validation_data = much_data[-100:]
prediction = convolutional_neural_network(x)
cost = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y) )
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 3
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
epoch_loss = 0
for data in train_data:
X = data[0]
Y = data[1]
_, c = sess.run([optimizer, cost], feed_dict={x: X, y: Y})
epoch_loss += c
print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Accuracy:',accuracy.eval({x:[i[0] for i in validation_data], y:[i[1]
for i in validation_data]}))
train_neural_network(x)
Please kindly provide some help as I'm stuck with this for sometime now. My only tip is to feed the data in batches instead of the whole thing into CNN, but I'm not successful with that technique yet. Could someone please point out a way ?