Actuellement je le code suivant:Mise à jour de l'état initial d'un réseau de neurones récurrent dans tensorflow
init_state = tf.Variable(tf.zeros([batch_partition_length, state_size])) # -> [16, 1024].
final_state = tf.Variable(tf.zeros([batch_partition_length, state_size]))
And inside my inference method that is responsible producing the output, I have the following:
def inference(frames):
# Note that I write the final_state as a global valriable to avoid the shadowing issue, since it is referenced at the dynamic_rnn line.
global final_state
# .... Here we have some conv layers and so on...
# Now the RNN cell
with tf.variable_scope('local1') as scope:
# Move everything into depth so we can perform a single matrix multiply.
shape_d = pool3.get_shape()
shape = shape_d[1] * shape_d[2] * shape_d[3]
# tf_shape = tf.stack(shape)
tf_shape = 1024
print("shape:", shape, shape_d[1], shape_d[2], shape_d[3])
# So note that tf_shape = 1024, this means that we have 1024 features are fed into the network. And
# the batch size = 1024. Therefore, the aim is to divide the batch_size into num_steps so that
reshape = tf.reshape(pool3, [-1, tf_shape])
# Now we need to reshape/divide the batch_size into num_steps so that we would be feeding a sequence
rnn_inputs = tf.reshape(reshape, [batch_partition_length, step_size, tf_shape])
print('RNN inputs shape: ', rnn_inputs.get_shape()) # -> (16, 64, 1024).
cell = tf.contrib.rnn.BasicRNNCell(state_size)
# note that rnn_outputs are the outputs but not multiplied by W.
rnn_outputs, final_state = tf.nn.dynamic_rnn(cell, rnn_inputs, initial_state=init_state)
# linear Wx + b
with tf.variable_scope('softmax_linear') as scope:
weight_softmax = \
tf.Variable(
tf.truncated_normal([state_size, n_classes], stddev=1/state_size, dtype=tf.float32, name='weight_softmax'))
bias_softmax = tf.constant(0.0, tf.float32, [n_classes], name='bias_softmax')
softmax_linear = tf.reshape(
tf.matmul(tf.reshape(rnn_outputs, [-1, state_size]), weight_softmax) + bias_softmax,
[batch_size, n_classes])
print('Output shape:', softmax_linear.get_shape())
return softmax_linear
# Here we define the loss, accuracy and the optimzer.
# now run the graph:
with tf.Session() as sess:
_, accuracy_train, loss_train, summary = \
sess.run([optimizer, accuracy, cost_scalar, merged], feed_dict={x: image_batch,
y_valence: valences,
confidence_holder: confidences})
....
Problème: Comment je serais en mesure d'attribuer initial_state la valeur stockée dans final_state? Autrement dit, comment mettre à jour une valeur Variable plus l'autre?
Je l'ai utilisé comme suit:
tf.assign(init_state, final_state.eval())
en séance après l'exécution de la commande sess.run. Mais, cela jette une erreur: Vous devez nourrir une valeur pour « entrées » tenseur d'espace réservé avec DTYPE flotteur Où tf.Variable: « entrée » est déclarée comme suit:
x = tf.placeholder(tf.float32, [None, 112, 112, 3], name='inputs')
Et l'alimentation se fait après lire les images des tfRecords par la commande suivante:
example = tf.train.Example()
example.ParseFromString(string_record)
height = int(example.features.feature['height']
.int64_list
.value[0])
width = int(example.features.feature['width']
.int64_list
.value[0])
img_string = (example.features.feature['image_raw']
.bytes_list
.value[0])
img_1d = np.fromstring(img_string, dtype=np.uint8)
reconstructed_img = img_1d.reshape((height, width, -1)) # Where this is added to the image_batch list, which is fed into the placeholder.
Et si essayé ce qui suit:
img_1d = np.fromstring(img_string, dtype=np.float32)
Cette produira l'erreur suivante:
ValueError: ne peut pas remodeler tableau de taille 9408 en forme (112112, newaxis)
Toute aide est très appréciée !!