This question follows from my earlier question . I had converted this keras model to .pb. The I also successfully converted this .pb to intermediate representation of Open VINO. The model is available in the attachment of last answer of this post at intel developer forum.
If you got this model. Now you can load the model like this .
model_path = 'jester_freezed/IR/model/tf_model.xml'
from openvino.inference_engine import IENetwork, IECore
import os
def load_to_IE(model_xml, cpu_extension=None):
#Load the Inference Engine API
plugin = IECore()
# Load IR files into their related class
model_bin = os.path.splitext(model_xml)[0] + ".bin"
net = IENetwork(model=model_xml, weights=model_bin)
return net
net = load_to_IE(model_path)
Here is the full error.
RuntimeError: Check 'PartialShape::broadcast_merge_into(pshape, get_input_partial_shape(i), autob)' failed at /teamcity/work/scoring_engine_build/releases_2020_1/ngraph/src/ngraph/node.cpp:890:
While validating node 'Add[Add_43](Convolution_41: float{1,40,12,12}, Constant_42: float{40}) -> (??)':
Argument shapes are inconsistent.
My open vino version is 2020.1.
There are no resources available to debug this error. Please help. Thanks.
Related
I am trying to convert a Tensorflow Object Detection model(ssd-mobilenet-v2-fpnlite, from TensorFlow 2 Detection Model Zoo) to TFLite. First of all, I train the model using the model_main_tf2.py and then I use the export_tflite_graph_tf2.py to export a saved model(.pb). However, when it comes to convert the .pb file to .tflite it throws this error:
OSError: SavedModel file does not exist at: /content/gdrive/My Drive/models/research/object_detection/fine_tuned_model/saved_model/saved_model.pb/{saved_model.pbtxt|saved_model.pb}
To convert the .pb file I used:
import tensorflow as tf
SAVED_MODEL_PATH = os.path.join(os.getcwd(),'object_detection', 'fine_tuned_model', 'saved_model', 'saved_model.pb')
# SAVED_MODEL_PATH: '/content/gdrive/My Drive/models/research/object_detection/exported_model/saved_model/saved_model.pb'
converter = tf.lite.TFLiteConverter.from_saved_model(SAVED_MODEL_PATH)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.experimental_new_converter = True
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]
tflite_model = converter.convert()
open("detect.tflite", "wb").write(tflite_model)
or "tflite_convert" from command line, but with the same error. I also tried to run it with the latest tf-nightly version as it suggests here, but the outcome is the same. I tried to pass the path with various ways, it seems like the .pd is not well written (not the right file). Is there a way to manage to convert the model to tflite so as to implement it to android? Thank you!
Your saved_model path should be "/content/gdrive/My Drive/models/research/object_detection/fine_tuned_model/saved_model/". It is the folder instead of files in that folder
For quick test, try to type in terminal
tflite_convert \
--saved_model_dir="path to saved_folder" \
--output_file="path to tflite file u want to save"
I don't have enough reputation to just comment but the problem here seems to be your SAVED_MODEL_PATH.
You could try to hardcode the path and remove the .pb file. I don't remember exactly what's the trick here but it's definitively due to the path
I am looking into using MXNet LSTM modelling for time-series analysis for a problem i am currently working on.
As a way of understanding how to implement this, I am following the example code given by xnNet from the link: https://mxnet.incubator.apache.org/tutorials/r/MultidimLstm.html
When running this script after downloading the necessary data to my local source, i am able to execute the code fine until i get to the following section to train the model:
## train the network
system.time(model <- mx.model.buckets(symbol = symbol,
train.data = train.data,
eval.data = eval.data,
num.round = 100,
ctx = ctx,
verbose = TRUE,
metric = mx.metric.mse.seq,
initializer = initializer,
optimizer = optimizer,
batch.end.callback = NULL,
epoch.end.callback = epoch.end.callback))
When running this section, the following error occurs once gaining connection to the API.
Error in mx.nd.internal.as.array(nd) :
[14:22:53] c:\jenkins\workspace\mxnet\mxnet\src\operator\./rnn-inl.h:359:
Check failed: param_.p == 0 (0.2 vs. 0) Dropout is not supported at the moment.
Is there currently a problem internally within the XNNet R package which is unable to run this code? I can't imagine they would provide a tutorial example for the package that is not executable.
My other thought is that it is something to do with my local device execution and connection to the API. I haven't been able to find any information about this being a problem for other users though.
Any inputs or suggestions would be greatly appreciated thanks.
Looks like you're running an old version of R package. I think following instructions on this page to build a recent R-package should resolve this issue.
I am trying to access to the derivatives. Looking at the manual, the recorder should have it. However, running the below code i receive the error :
Any idea?
deriv_case = cr.driver_derivative_cases.get_case('rank0:SLSQP|1')
AttributeError: 'SqliteCaseReader' object has no attribute 'driver_derivative_cases'**
from openmdao.drivers.scipy_optimizer import ScipyOptimizeDriver
from openmdao.test_suite.components.sellar import SellarDerivativesGrouped
from openmdao.test_suite.components.sellar import SellarProblem
from openmdao.recorders.case_reader import CaseReader
from openmdao.recorders.sqlite_recorder import SqliteRecorder
prob = SellarProblem(SellarDerivativesGrouped)
driver = prob.driver = ScipyOptimizeDriver(optimizer='SLSQP')
driver.recording_options['record_derivatives'] = True
fname = "record.sql"
recorder = SqliteRecorder(fname)
prob.driver.add_recorder(recorder)
#driver.add_recorder('recorder')
prob.setup()
prob.run_driver()
prob.cleanup()
cr = CaseReader(fname)
# Get derivatives associated with the first iteration.
deriv_case = cr.driver_derivative_cases.get_case('rank0:SLSQP|1')
# Get all derivatives from that case.
derivs = deriv_case.get_derivatives()
# See what derivatives have been recorded.
print(set(derivs.keys))
That example comes from the latest beta docs, which are associated with the current code on the github master branch. I gather you are probably running the most recent release, which is 2.3.1, which doesn't have that feature yet. You could either clone our repo on Github to get the most recent commits to the code, or you could wait until we release 2.4.
I've trained a model with Azure Custom Vision and downloaded the TensorFlow files for Android
(see: https://learn.microsoft.com/en-au/azure/cognitive-services/custom-vision-service/export-your-model). How can I use this with tensorflow.js?
I need a model (pb file) and weights (json file). However Azure gives me a .pb and a textfile with tags.
From my research I also understand that there are also different pb files, but I can't find which type Azure Custom Vision exports.
I found the tfjs converter. This is to convert a TensorFlow SavedModel (is the *.pb file from Azure a SavedModel?) or Keras model to a web-friendly format. However I need to fill in "output_node_names" (how do I get these?). I'm also not 100% sure if my pb file for Android is equal to a "tf_saved_model".
I hope someone has a tip or a starting point.
Just parroting what I said here to save you a click. I do hope that the option to export directly to tfjs is available soon.
These are the steps I did to get an exported TensorFlow model working for me:
Replace PadV2 operations with Pad. This python function should do it. input_filepath is the path to the .pb model file and output_filepath is the full path of the updated .pb file that will be created.
import tensorflow as tf
def ReplacePadV2(input_filepath, output_filepath):
graph_def = tf.GraphDef()
with open(input_filepath, 'rb') as f:
graph_def.ParseFromString(f.read())
for node in graph_def.node:
if node.op == 'PadV2':
node.op = 'Pad'
del node.input[-1]
print("Replaced PadV2 node: {}".format(node.name))
with open(output_filepath, 'wb') as f:
f.write(graph_def.SerializeToString())
Install tensorflowjs 0.8.6 or earlier. Converting frozen models is deprecated in later versions.
When calling the convertor, set --input_format as tf_frozen_model and set output_node_names as model_outputs. This is the command I used.
tensorflowjs_converter --input_format=tf_frozen_model --output_json=true --output_node_names='model_outputs' --saved_model_tags=serve path\to\modified\model.pb folder\to\save\converted\output
Ideally, tf.loadGraphModel('path/to/converted/model.json') should now work (tested for tfjs 1.0.0 and above).
Partial answer:
Trying to achieve the same thing - here is the start of an answer - to make use of the output_node_names:
tensorflowjs_converter --input_format=tf_frozen_model --output_node_names='model_outputs' model.pb web_model
I am not yet sure how to incorporate this into same code - do you have anything #Kasper Kamperman?
I created a model using Apache OpenNLP's command line tool to recognize named entities. The below code created the model using the file sentences4OpenNLP.txt as a training set.
opennlp TokenNameFinderTrainer -type maxent -model C:\Users\Documents\en-ner-org.bin -lang en -data C:\Users\Documents\apache-opennlp-1.6.0\sentences4OpenNLP.txt -encoding UTF-8
I tested the model from the command line by passing it sentences to tag, and the model seemed to be working well. However, I am unable to successfully use the model from R. I am using the below lines in attempts to create an organization annotating function. Using the same code to load a model downloaded from OpenNLP works fine.
modelNER <- "C:/Users/Documents/en-ner-org.bin"
oa <- openNLP::Maxent_Entity_Annotator(language = "en",
kind = "organization",
probs = TRUE,
model = modelNER)
When the above code is run I get an error saying:
Could not instantiate the opennlp.tools.namefind.TokenNameFinderFactory. The initialization throw an exception.
opennlp.tools.util.ext.ExtensionNotLoadedException: Unable to find implementation for opennlp.tools.util.BaseToolFactory, the class or service opennlp.tools.namefind.TokenNameFinderFactory could not be located!
at opennlp.tools.util.ext.ExtensionLoader.instantiateExtension(ExtensionLoader.java:97)
at opennlp.tools.util.BaseToolFactory.create(BaseToolFactory.java:106)
at opennlp.tools.util.model.BaseModel.initializeFactory(BaseModel.java:254)
Error in .jnew("opennlp.tools.namefind.TokenNameFinderModel", .jcast(.jnew("java.io.FileInputStream", :
java.lang.IllegalArgumentException: opennlp.tools.util.InvalidFormatException: Could not instantiate the opennlp.tools.namefind.TokenNameFinderFactory. The initialization throw an exception.
at opennlp.tools.util.model.BaseModel.loadModel(BaseModel.java:237)
at opennlp.tools.util.model.BaseModel.<init>(BaseModel.java:181)
at opennlp.tools.namefind.TokenNameFinderModel.<init>(TokenNameFinderModel.java:110)
Any advice on how to fix the error would be a big help. Thanks in advance.
Resolved the error. The R function openNLP::Maxent_Entity_Annotator was not compatible with the named entity recognition (NER) model being produced by OpenNLP 1.6.0. Building the NER model using OpenNLP 1.5.3 resulted in openNLP::Maxent_Entity_Annotator running without error.