I have downloaded checkpoints along with model for Mobilenet v3. After extraction of rar file, I get two folders and two other files. Directory looks like following
Main Folder
ema (folder)
checkpoint
model-x.data-00000-of-00001
model-x.index
model-x.meta
pristine (folder)
model.ckpt-y.data-00000-of-00001
model.ckpt-y.index
model.ckpt-y.meta
.pb
.tflite
I have tried many codes among which few are below.
import tensorflow as tf
from tensorflow.python.platform import gfile
model_path = "./weights/v3-large-minimalistic_224_1.0_uint8/model.ckpt-3868848"
detection_graph = tf.Graph()
with tf.Session(graph=detection_graph) as sess:
# Load the graph with the trained states
loader = tf.train.import_meta_graph(model_path+'.meta')
loader.restore(sess, model_path)
The above code results in following error
Node {{node batch_processing/distort_image/switch_case/indexed_case}} of type Case has '_lower_using_switch_merge' attr set but it does not support lowering.
I tried following code:
import tensorflow as tf
import sys
sys.path.insert(0, 'models/research/slim')
from nets.mobilenet import mobilenet_v3
tf.reset_default_graph()
file_input = tf.placeholder(tf.string, ())
image = tf.image.decode_jpeg(tf.read_file('test.jpg'))
images = tf.expand_dims(image, 0)
images = tf.cast(images, tf.float32) / 128. - 1
images.set_shape((None, None, None, 3))
images = tf.image.resize_images(images, (224, 224))
model = mobilenet_v3.wrapped_partial(mobilenet_v3.mobilenet,
new_defaults={'scope': 'MobilenetEdgeTPU'},
conv_defs=mobilenet_v3.V3_LARGE_MINIMALISTIC,
depth_multiplier=1.0)
with tf.contrib.slim.arg_scope(mobilenet_v3.training_scope(is_training=False)):
logits, endpoints = model(images)
ema = tf.train.ExponentialMovingAverage(0.999)
vars = ema.variables_to_restore()
print(vars)
with tf.Session() as sess:
tf.train.Saver(vars).restore(sess, './weights/v3-large-minimalistic_224_1.0_uint8/saved_model.pb')
tf.train.Saver().save(sess, './weights/v3-large-minimalistic_224_1.0_uint8/pristine/model.ckpt')
The above code generates following error:
Unable to open table file ./weights/v3-large-minimalistic_224_1.0_uint8/saved_model.pb: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
[[node save/RestoreV2 (defined at <ipython-input-11-1531bbfd84bb>:29) ]]
How can I load Mobilenet v3 model along with the checkpoints and use it for my data?
try this
with tf.contrib.slim.arg_scope(mobilenet_v3.training_scope(is_training=False)):
logits, endpoints = mobilenet_v3.large_minimalistic(images)
instead of
model = mobilenet_v3.wrapped_partial(mobilenet_v3.mobilenet,
new_defaults={'scope': 'MobilenetEdgeTPU'},
conv_defs=mobilenet_v3.V3_LARGE_MINIMALISTIC,
depth_multiplier=1.0)
with tf.contrib.slim.arg_scope(mobilenet_v3.training_scope(is_training=False)):
logits, endpoints = model(images)
Related
I followed the website: https://leimao.github.io/blog/Save-Load-Inference-From-TF2-Frozen-Graph/
However, I still do not know how to run inference with frozen_func(see my code below).
Please advise how to run inference using pb file in TensorFlow 2.2. Thanks.
import tensorflow as tf
def wrap_frozen_graph(graph_def, inputs, outputs, print_graph=False):
def _imports_graph_def():
tf.compat.v1.import_graph_def(graph_def, name="")
wrapped_import = tf.compat.v1.wrap_function(_imports_graph_def, [])
import_graph = wrapped_import.graph
print("-" * 50)
print("Frozen model layers: ")
layers = [op.name for op in import_graph.get_operations()]
if print_graph == True:
for layer in layers:
print(layer)
print("-" * 50)
return wrapped_import.prune(
tf.nest.map_structure(import_graph.as_graph_element, inputs),
tf.nest.map_structure(import_graph.as_graph_element, outputs))
# Load frozen graph using TensorFlow 1.x functions
with tf.io.gfile.GFile("/content/drive/My Drive/Model_file/froze_graph.pb", "rb") as f:
graph_def = tf.compat.v1.GraphDef()
loaded = graph_def.ParseFromString(f.read())
# Wrap frozen graph to ConcreteFunctions
frozen_func = wrap_frozen_graph(graph_def=graph_def,
inputs=["wav_data:0"],
outputs=["labels_softmax:0"],
print_graph=True)
You can use tf.graph_util.import_graph_def inside a tf.function to do that. For example, suppose you make a test GraphDef file my_func.pb like this:
import tensorflow as tf
# Test function to make into a GraphDef file
#tf.function
def my_func(x):
return tf.square(x, name='y')
# Get graph
g = my_func.get_concrete_function(tf.TensorSpec(None, tf.float32)).graph
# Write to file
tf.io.write_graph(g, '.', 'my_func.pb', as_text=False)
You can then load it and use it like this:
import tensorflow as tf
from tensorflow.core.framework.graph_pb2 import GraphDef
# Load GraphDef
with open('my_func.pb', 'rb') as f:
gd = GraphDef()
gd.ParseFromString(f.read())
#tf.function
def my_func2(x):
# Ensure the input is a tensor of the right type
x = tf.convert_to_tensor(x, tf.float32)
# Import the graph giving x as input and getting the output y
y = tf.graph_util.import_graph_def(
gd, input_map={'x:0': x}, return_elements=['y:0'])[0]
return y
tf.print(my_func2(2))
# 4
I have exported my model from Google AutoML image classification. I only have a saved_model.pb and no checkpoint or metafiles. Is there a way to convert this saved_model.pb to frozen_inferenc_graph
You can achieve this by the following method with only .pb file.
import tensorflow as tf
from tensorflow.python.platform import gfile
GRAPH_PB_PATH = './model/model_file.pb' #path to your .pb file
with tf.Session(config=config) as sess:
print("load graph")
with gfile.FastGFile(GRAPH_PB_PATH,'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
sess.graph.as_default()
tf.import_graph_def(graph_def, name='')
graph_nodes=[n for n in graph_def.node]
Now when you freeze a graph to .pb file your variables are converted to Const type and the weights which were trainable variables would also be stored as Const in .pb file. graph_nodes contains all the nodes in the graph. But we are interested in all the Const type nodes.
wts = [n for n in graph_nodes if n.op=='Const']
Each element of wts is of NodeDef type. It has several attributes such as name, op etc. The values can be extracted as follows -
from tensorflow.python.framework import tensor_util
for n in wts:
print "Name of the node - %s" % n.name
print "Value - "
print tensor_util.MakeNdarray(n.attr['value'].tensor)
Hope this solves your concern.
I'm trying to benchmark the performance in the inference phase of my Keras model build with the TensorFlow backend. I was thinking that the the Tensorflow Benchmark tool was the proper way to go.
I've managed to build and run the example on Desktop with the tensorflow_inception_graph.pb and everything seems to work fine.
What I can't seem to figure out is how to save the Keras model as a proper .pbmodel. I'm able to get the TensorFlow Graph from the Keras model as follows:
import keras.backend as K
K.set_learning_phase(0)
trained_model = function_that_returns_compiled_model()
sess = K.get_session()
sess.graph # This works
# Get the input tensor name for TF Benchmark
trained_model.input
> <tf.Tensor 'input_1:0' shape=(?, 360, 480, 3) dtype=float32>
# Get the output tensor name for TF Benchmark
trained_model.output
> <tf.Tensor 'reshape_2/Reshape:0' shape=(?, 360, 480, 12) dtype=float32>
I've now been trying to save the model in a couple of different ways.
import tensorflow as tf
from tensorflow.contrib.session_bundle import exporter
model = trained_model
export_path = "path/to/folder" # where to save the exported graph
export_version = 1 # version number (integer)
saver = tf.train.Saver(sharded=True)
model_exporter = exporter.Exporter(saver)
signature = exporter.classification_signature(input_tensor=model.input, scores_tensor=model.output)
model_exporter.init(sess.graph.as_graph_def(), default_graph_signature=signature)
model_exporter.export(export_path, tf.constant(export_version), sess)
Which produces a folder with some files I don't know what to do with.
I would now run the Benchmark tool with something like this
bazel-bin/tensorflow/tools/benchmark/benchmark_model \
--graph=tensorflow/tools/benchmark/what_file.pb \
--input_layer="input_1:0" \
--input_layer_shape="1,360,480,3" \
--input_layer_type="float" \
--output_layer="reshape_2/Reshape:0"
But no matter which file I'm trying to use as the what_file.pb I'm getting a Error during inference: Invalid argument: Session was not created with a graph before Run()!
So I got this to work. Just needed to convert all variables in the tensorflow graph to constants and then save graph definition.
Here's a small example:
import tensorflow as tf
from keras import backend as K
from tensorflow.python.framework import graph_util
K.set_learning_phase(0)
model = function_that_returns_your_keras_model()
sess = K.get_session()
output_node_name = "my_output_node" # Name of your output node
with sess as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
graph_def = sess.graph.as_graph_def()
output_graph_def = graph_util.convert_variables_to_constants(
sess,
sess.graph.as_graph_def(),
output_node_name.split(","))
tf.train.write_graph(output_graph_def,
logdir="my_dir",
name="my_model.pb",
as_text=False)
Now just call the TensorFlow Benchmark tool with my_model.pb as the graph.
You're saving the parameters of this model and not the graph definition; to save that use tf.get_default_graph().as_graph_def().SerializeToString() and then save that to a file.
That said I don't think the benchmark tool will work since it has no way to initialize the variables your model depends on.
(1) I'm trying to fine-tune a VGG-16 network using TFSlim by loading pretrained weights into all layers except thefc8 layer. I achieved this by using the TF-SLIm function as follows:
import tensorflow as tf
import tensorflow.contrib.slim as slim
import tensorflow.contrib.slim.nets as nets
vgg = nets.vgg
# Specify where the Model, trained on ImageNet, was saved.
model_path = 'path/to/vgg_16.ckpt'
# Specify where the new model will live:
log_dir = 'path/to/log/'
images = tf.placeholder(tf.float32, [None, 224, 224, 3])
predictions = vgg.vgg_16(images)
variables_to_restore = slim.get_variables_to_restore(exclude=['fc8'])
restorer = tf.train.Saver(variables_to_restore)
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
restorer.restore(sess,model_path)
print "model restored"
This works fine as long as I do not change the num_classes for the VGG16 model. What I would like to do is to change the num_classes from 1000 to 200. I was under the impression that if I did this modification by defining a new vgg16-modified class that replaces the fc8 to produce 200 outputs, (along with a variables_to_restore = slim.get_variables_to_restore(exclude=['fc8']) that everything will be fine and dandy. However, tensorflow complains of a dimensions mismatch:
InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [1,1,4096,200] rhs shape= [1,1,4096,1000]
So, how does one really go about doing this ? The documentation for TFSlim is really patchy and there are several versions scattered on Github - so not getting much help there.
You can try using slim's way of restoring — slim.assign_from_checkpoint.
There is related documentation in the slim sources:
https://github.com/tensorflow/tensorflow/blob/129665119ea60640f7ed921f36db9b5c23455224/tensorflow/contrib/slim/python/slim/learning.py
Corresponding part:
*************************************************
* Fine-Tuning Part of a model from a checkpoint *
*************************************************
Rather than initializing all of the weights of a given model, we sometimes
only want to restore some of the weights from a checkpoint. To do this, one
need only filter those variables to initialize as follows:
...
# Create the train_op
train_op = slim.learning.create_train_op(total_loss, optimizer)
checkpoint_path = '/path/to/old_model_checkpoint'
# Specify the variables to restore via a list of inclusion or exclusion
# patterns:
variables_to_restore = slim.get_variables_to_restore(
include=["conv"], exclude=["fc8", "fc9])
# or
variables_to_restore = slim.get_variables_to_restore(exclude=["conv"])
init_assign_op, init_feed_dict = slim.assign_from_checkpoint(
checkpoint_path, variables_to_restore)
# Create an initial assignment function.
def InitAssignFn(sess):
sess.run(init_assign_op, init_feed_dict)
# Run training.
slim.learning.train(train_op, my_log_dir, init_fn=InitAssignFn)
Update
I tried the following:
import tensorflow as tf
import tensorflow.contrib.slim as slim
import tensorflow.contrib.slim.nets as nets
images = tf.placeholder(tf.float32, [None, 224, 224, 3])
predictions = nets.vgg.vgg_16(images)
print [v.name for v in slim.get_variables_to_restore(exclude=['fc8']) ]
And got this output (shortened):
[u'vgg_16/conv1/conv1_1/weights:0',
u'vgg_16/conv1/conv1_1/biases:0',
…
u'vgg_16/fc6/weights:0',
u'vgg_16/fc6/biases:0',
u'vgg_16/fc7/weights:0',
u'vgg_16/fc7/biases:0',
u'vgg_16/fc8/weights:0',
u'vgg_16/fc8/biases:0']
So it looks like you should prefix scope with vgg_16:
print [v.name for v in slim.get_variables_to_restore(exclude=['vgg_16/fc8']) ]
gives (shortened):
[u'vgg_16/conv1/conv1_1/weights:0',
u'vgg_16/conv1/conv1_1/biases:0',
…
u'vgg_16/fc6/weights:0',
u'vgg_16/fc6/biases:0',
u'vgg_16/fc7/weights:0',
u'vgg_16/fc7/biases:0']
Update 2
Complete example that executes without errors (at my system).
import tensorflow as tf
import tensorflow.contrib.slim as slim
import tensorflow.contrib.slim.nets as nets
s = tf.Session(config=tf.ConfigProto(gpu_options={'allow_growth':True}))
images = tf.placeholder(tf.float32, [None, 224, 224, 3])
predictions = nets.vgg.vgg_16(images, 200)
variables_to_restore = slim.get_variables_to_restore(exclude=['vgg_16/fc8'])
init_assign_op, init_feed_dict = slim.assign_from_checkpoint('./vgg16.ckpt', variables_to_restore)
s.run(init_assign_op, init_feed_dict)
In the example above vgg16.ckpt is a checkpoint saved by tf.train.Saver for 1000 classes VGG16 model.
Using this checkpoint with all variables of 200 classes model (including fc8) gives the following error:
init_assign_op, init_feed_dict = slim.assign_from_checkpoint('./vgg16.ckpt', slim.get_variables_to_restore())
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
1 init_assign_op, init_feed_dict = slim.assign_from_checkpoint(
----> 2 './vgg16.ckpt', slim.get_variables_to_restore())
/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/framework/python/ops/variables.pyc in assign_from_checkpoint(model_path, var_list)
527 assign_ops.append(var.assign(placeholder_value))
528
--> 529 feed_dict[placeholder_value] = var_value.reshape(var.get_shape())
530
531 assign_op = control_flow_ops.group(*assign_ops)
ValueError: total size of new array must be unchanged
Trying to run the Inceptionv3 Tensorflow model with the architecture and the checkpoint provided by Google here.
My issue is that my script crashes on saver.restore(sess, "./inception_v3.ckpt") with the following error:
tensorflow.python.framework.errors.NotFoundError: Tensor name "InceptionV3/Mixed_5b/Branch_1/Conv2d_0b_5x5/biases" not found in checkpoint files ./inception_v3.ckpt
Here is my code:
import tensorflow as tf
import inception_v3
with tf.Session() as sess:
image = tf.read_file('./file.jpg')
# code to decode, crop, convert jpeg
eval_inputs = tf.pack([image])
logits, _ = inception_v3.inception_v3(eval_inputs, num_classes=1001, is_training=False)
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver()
saver.restore(sess, "./inception_v3.ckpt")
I get the same errors with the other checkpoint/model combinations so this must be an issue with my code. Not sure what I am doing wrong though.
Thank you
Indeed the checkpoint file does not contain this tensor. Can you file a bug on github?
You need to call inception_v3() within the arg_scope() returned by inception_v3_arg_scope() like this:
import tensorflow as tf
import tensorflow.contrib.slim as slim
from nets.inception_v3 import inception_v3, inception_v3_arg_scope
height = 299
width = 299
channels = 3
# Create graph
X = tf.placeholder(tf.float32, shape=[None, height, width, channels])
with slim.arg_scope(inception_v3_arg_scope()):
logits, end_points = inception_v3(X, num_classes=1001,
is_training=False)
predictions = end_points["Predictions"]
saver = tf.train.Saver()
X_test = ... # your images, shape [batch_size, 299, 299, 3]
# Execute graph
with tf.Session() as sess:
saver.restore(sess, "./inception_v3.ckpt")
predictions_val = predictions.eval(feed_dict={X: X_test})
predicted_classes = np.argmax(predictions_val, axis=1)
I recommend clearly separating the construction phase and the execution phase. Just tested on a random photo on the web, and it worked fine. :)