img_batch, label_batch = tf.train.shuffle_batch([img, label],
batch_size=128,capacity=2000,
min_after_dequeue=1000)
logits = cifar10.inference(img_batch)
saver = tf.train.Saver()
sess = tf.Session()
init = tf.initialize_all_variables()
sess.run(init)
saver.restore(sess,"/Tensorflow/cata.tfmodel")
tf.train.start_queue_runners(sess=sess)
I have trained the model "cata.tfmodel" in another program and restored the sess in this program, but I don't know how to use this model to classify one picture and output the classification.
The type of my dataset is tfrecords and read it by queue.
I'm confused that if I covert one picture into tfrecords, it will contain image and label, what to do next?
logits = cifar10.inference(img_batch)
saver = tf.train.Saver(tf.all_variables())
Besides, If I delete logits , saver will throw ValueError: No variables to save
Related
I have used the retrain.py script provided at the tensorflow github to finetune a pretrained inceptionV3 model on my own dataset. I have the model saved to disk and now I want to use it as the starting point for another round of training in which I retrain all of the convolutional layers. Below is the code I am attempting to use to create the new graph. I thought that once I have the graph loaded into the default graph I could access the variables in it with tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES) and set them all to trainable. However, there doesn't appear to be anything in any of the tf.GraphKeys variables (GLOBAL_VARIABLES, TRAINABLE_VARIABLES, MODEL_VARIABLES etc.). So when I try to create the optimizer I get an error "ValueError: No variables to optimize." What am I doing wrong?
def create_graph(model_path, class_count):
"""Creates a graph from saved GraphDef file and returns a saver."""
with tf.Graph().as_default() as graph:
# Creates graph from saved graph_def.pb.
with tf.gfile.FastGFile(model_path, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')
#import logits from saved graph
logits_tensor = graph.get_tensor_by_name("final_training_ops/biases/final_biases:0")
ground_truth_input = tf.placeholder(tf.float32,
[None, class_count],
name='GroundTruthInput')
print(tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES)
#connect logits to the training ops
with tf.name_scope('cross_entropy'):
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(
labels=ground_truth_input, logits=logits_tensor)
with tf.name_scope('total'):
cross_entropy_mean = tf.reduce_mean(cross_entropy)
tf.summary.scalar('cross_entropy', cross_entropy_mean)
with tf.name_scope('train'):
optimizer = tf.train.GradientDescentOptimizer(0.001)
train_step = optimizer.minimize(cross_entropy_mean)
return graph, ground_truth_input, cross_entropy_mean, train_step
I faced a problem with properly restoring the saved model in tensorflow. I created the Bidirectional RNN model in tensorflow with following code:
batchX_placeholder = tf.placeholder(tf.float32, [None, timesteps, 1],
name="batchX_placeholder")])
batchY_placeholder = tf.placeholder(tf.float32, [None, num_classes],
name="batchY_placeholder")
weights = tf.Variable(np.random.rand(2*STATE_SIZE, num_classes),
dtype=tf.float32, name="weights")
biases = tf.Variable(np.zeros((1, num_classes)), dtype=tf.float32,
name="biases")
logits = BiRNN(batchX_placeholder, weights, biases)
with tf.name_scope("prediction"):
prediction = tf.nn.softmax(logits)
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=logits, labels=batchY_placeholder))
lr = tf.Variable(learning_rate, trainable=False, dtype=tf.float32,
name='lr')
optimizer = tf.train.AdamOptimizer(learning_rate=lr)
train_op = optimizer.minimize(loss_op)
init_op = tf.initialize_all_variables()
saver = tf.train.Saver()
The architecture of BiRNN created with the following function:
def BiRNN(x, weights, biases):
# Unstack to get a list of 'time_steps' tensors of shape (batch_size,
# num_input)
x = tf.unstack(x, time_steps, 1)
# Forward and Backward direction cells
lstm_fw_cell = rnn.BasicLSTMCell(STATE_SIZE, forget_bias=1.0)
lstm_bw_cell = rnn.BasicLSTMCell(STATE_SIZE, forget_bias=1.0)
outputs, _, _ = rnn.static_bidirectional_rnn(lstm_fw_cell,
lstm_bw_cell, x, dtype=tf.float32)
# Linear activation, using rnn inner loop last output
return tf.matmul(outputs[-1], weights) + biases
Then I train a model and save it after each 200 steps:
with tf.Session() as sess:
sess.run(init_op)
current_step = 0
for batch_x, batch_y in get_minibatch():
sess.run(train_op, feed_dict={batchX_placeholder: batch_x,
batchY_placeholder: batch_y})
current_step += 1
if current_step % 200 == 0:
saver.save(sess, os.path.join(model_dir, "model")
To run the saved model in inference mode I use saved tensorflow graph in "model.meta" file:
graph = tf.get_default_graph()
saver = tf.train.import_meta_graph(os.path.join(model_dir, "model.meta"))
sess = tf.Session()
saver.restore(sess, tf.train.latest_checkpoint(model_dir)
weights = graph.get_tensor_by_name("weights:0")
biases = graph.get_tensor_by_name("biases:0")
batchX_placeholder = graph.get_tensor_by_name("batchX_placeholder:0")
batchY_placeholder = graph.get_tensor_by_name("batchY_placeholder:0")
logits = BiRNN(batchX_placeholder, weights, biases)
prediction = graph.get_operation_by_name("prediction/Softmax")
argmax_pred = tf.argmax(prediction, 1)
init = tf.global_variables_initializer()
sess.run(init)
for x_seq, y_gt in get_sequence():
_, y_pred = sess.run([prediction, argmax_pred],
feed_dict={batchX_placeholder: [x_seq]],
batchY_placeholder: [[0.0, 0.0]]})
print("Y ground true: " + str(y_gt) + ", Y pred: " + str(y_pred[0]))
And when I run the code in inference mode, I get different results each time I launch it. It seems that output neurons from the softmax layer randomly bundled with different output classes.
So, my question is: How can I save and then correctly restore the model in tensorflow, so that all neurons properly bundled with corresponding output classes?
There is no need to call tf.global_variables_initializer(), I think that is your problem.
I removed some operations: logits, weights and biases since you don't need them, all those are already loaded, use graph.get_tensor_by_name to get them.
For the prediction, get the tensor instead of the operation. (see this answer):
This is the code:
graph = tf.get_default_graph()
saver = tf.train.import_meta_graph(os.path.join(model_dir, "model.meta"))
sess = tf.Session()
saver.restore(sess, tf.train.latest_checkpoint(model_dir))
batchX_placeholder = graph.get_tensor_by_name("batchX_placeholder:0")
batchY_placeholder = graph.get_tensor_by_name("batchY_placeholder:0")
prediction = graph.get_tensor_by_name("prediction/Softmax:0")
argmax_pred = tf.argmax(prediction, 1)
Edit 1: I notice that I wasn't clear on why you got different results.
And when I run the code in inference mode, I get different results
each time I launch it.
Notice that although you used the weights from the loaded model, you are creating the BiRNN again, and the BasicLSTMCell also have weights and other variables that you don't set from your loaded model, hence they need to be initialized (with new random values) resulting in an untrained model again.
I am restoring a pre-trained model in TensorFlow and would like to know if my code works as desired. Here is the code below. It looks like it does not make use of the pre-trained model because the loss from the code below is way higher than training error, e.g., 200 something. Please let me know how I can modify it. Thank you in advance.
def main(_):
with tf.Graph().as_default() as g:
x, img, rows, cols = load_image(FLAGS.input, FLAGS.image_size)
with slim.arg_scope(resnet_v2.resnet_arg_scope(weight_decay=0.0005)):
logits, endpoints = resnet_v2.resnet_v2_152(x, nb_classes, is_training=False)
predictions = tf.argmax(logits, 1)
saver = tf.train.Saver()
with tf.Session(graph=g) as sess:
sess.run(tf.global_variables_initializer())
# Load a pretrained model.
print("\nLoading a model...")
saver.restore(sess, checkpoint_path)
print("\nFeedforwarding...")
pred, loss_out, output, grads_val = sess.run([predictions, loss, conv_layer, norm_grads])
I would really appreciate it if I could get some help in saving and restoring LSTMs.
I have this LSTM layer -
# LSTM cell
cell = tf.contrib.rnn.LSTMCell(n_hidden)
output, current_state = tf.nn.dynamic_rnn(cell, word_vectors, dtype=tf.float32)
outputs = tf.transpose(output, [1, 0, 2])
last = tf.gather(outputs, int(outputs.get_shape()[0]) - 1)
# Saver function
saver = tf.train.Saver()
saver.save(sess, 'test-model')
The saver saves the model and allows me to save and restore the weights and biases of the LSTM. However, I need to restore this LSTM layer and feed it a new set of inputs.
To restore the entire model, I'm doing:
with tf.Session() as sess:
saver = tf.train.import_meta_graph('test-model.meta')
saver.restore(sess, tf.train.latest_checkpoint('./'))
Is it possible for me to initialize an LSTM cell with the pre-trained weights and biases?
If not, how do I restore this LSTM layer?
Thank you very much!
You are already loading the model, and so the weights of the model. All you need to do is use get_tensor_by_name to get any tensor from the graph and use it for inference.
Example:
with tf.Session() as sess:
saver = tf.train.import_meta_graph('test-model.meta')
saver.restore(sess, tf.train.latest_checkpoint('./'))
# Get the tensors by their variable name
word_vec = = detection_graph.get_tensor_by_name('word_vec:0')
output_tensor = detection_graph.get_tensor_by_name('outputs:0')
sess.run(output_tensor, feed_dict={word_vec: ...})
In the above example word_vec and outputs are names assigned to the tensors during creation of the graph. Make sure you assign names, so that they can be called by their name.
I am new to TensorFlow. I have trained the inception_v3 model successfully with my training data; now I want to predict the output of several images, but the number of them is different from the batch_size in training. I did it as follows:
from tensorflow.contrib.slim.nets import inception_v3 as inception
checkpoint_dir =os.path.join('runs', configure_name, 'checkpoints')
checkpoint_file = tf.train.latest_checkpoint(checkpoint_dir)
graph = tf.Graph()
with graph.as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=True,
log_device_placement=False)
sess = tf.Session(config=session_conf)
with sess.as_default():
# Load the saved meta graph and restore variables
saver = tf.train.import_meta_graph("{}.meta".format(checkpoint_file))
saver.restore(sess, checkpoint_file)
x = tf.placeholder(tf.float32, [batch_size,input_size,input_size,num_channels], name='images')
_, end_points = inception.inception_v3(x,num_classes=num_classes, is_training=False)
outputs = end_points['Predictions']
scores = sess.run(outputs, feed_dict={x: x_eval})
predictions = np.argmax(scores,axis=1)
It gave me the errors as follows:
FailedPreconditionError: Attempting to use uninitialized value InceptionV3/Conv2d_1a_3x3/weights_1
It seems that the model parameters in "outputs" are not fed in successfully, but I do not know how to do it. Any ideas? Thanks.
Here you explicitly set the first dim of input placeholder x batch_size, so each time you need to feed a numpy.array type tensor with the same dim or your program will go wrong.
A solution can be setting the first dim of any placeholder(input and label) None so that this dim can be any int or different during training and validation
UPDATE:
if you have already trained your model with a fixed first dim placeholder input(and label), you can change it when restore this graph with tf.train.import_meta_graph(grapg_def=your_graph_def, input_map={'your_train_input_placedholer_name':new_placeholder})
here new_placeholder is a placeholder you newly create with unfixed first dim.