I'm having trouble trying to list the operations of a TFLite model. I know operations can be listed given a frozen graph, but what about a TFLite .tflite model? Can operations be listed?
You can get a list of all used Tensorflow Lite Operations with the visualization script.
wget -O tflite_visualize.py https://raw.githubusercontent.com/tensorflow/tensorflow/master/tensorflow/lite/tools/visualize.py
Assuming your model is saved in model.tflite create the html file using the downloaded script.
python tflite_visualize.py model.tflite model_visualization.html
Right in the section labled Ops.
As mentioned in the TensorFlow Lite docs, you need to use a tf.lite.Interpreter to parse a .tflite model.
# Load TFLite model and allocate tensors.
interpreter = tf.lite.Interpreter(model_path="converted_model.tflite")
interpreter.allocate_tensors()
Then use the get_tensor_details method to get the list of Tensors.
interpreter.get_tensor_details()
As per the docs,
Gets tensor details for every tensor with valid tensor details.
Tensors where required information about the tensor is not found are not added to the list. This includes temporary tensors without a name.
Returns: A list of dictionaries containing tensor information.
Related
I'm trying to create a .tflite model from a CycleGAN taken from GitHub (https://github.com/vanhuyz/CycleGAN-TensorFlow).
I am very new in this field and I do not understand how to expose the .pb model (which I have already created from the checkpoints) in a .tflite model.
I tried with tflite_convert but without any result, also because I don't know the parameters to insert as --input_arrays and --output_arrays.
Some idea?
I would recommend using the TFLiteConverter python api here: https://www.tensorflow.org/lite/convert/python_api and use SavedModel as your model input format. Otherwise, you can provide the input and output tensor names or your pb model as input_arrays and output_arrays.
I want to use MMdnn to convert a tensorflow ResNet model to other frameworks. It seems that I can only use mmconvert to read from a .pb frozen graph file.
However, when using tf.estimator.Estimator, the .pb file that it creates is a SavedModelDef. I understand this to be a wrapper around the tf GraphDef. Thus the GraphDef .pb file can be extracted from the SavedModel using freeze_graph.py.
From there, I will need the name of the input node in the tf GraphDef. But I'm unsure how to identify the name from looking at the .pbtxt. The tf.Estimator inputs with a tf.Dataset object, according to the framework.
I'm guessing there should be a tf.Placeholder somewhere that accepts the input. But I'm not sure how to find what the input node actually is.
Answering my own question here. The freeze_graph utility that comes with tensorflow is useful for extracting the graphdef from the tf SavedModel format.
To find the name of the input node, make sure to saved the tf SavedModel in pbtxt format. Open it up and look for the first node of your compute graph, e.g. if using tf resnet, the first nodes will be named resnet_model/*. Find the node that feeds this node, and you will have the name of the input node to specify to MMdnn tools. I expected this to be a tf.Placeholder that the Estimator adds for inputs. This node was just named Placeholder, so that's what I specified as the input node.
First extract the compute graph.
freeze_graph --input_saved_model_dir <path/to/saved_model_dir> --output_node_names softmax --output_graph ./graph_def.pb
Then use MMdnn to convert it to caffe.
mmconvert -sf tensorflow -iw ./graph_def.pb --inNodeName Placeholder --inputShape 224,224,3 --dstNodeName softmax -df caffe -om tf_resnet
I am aiming to inference tensorflow slim model with Intel OpenVINO optimizer. Using open vino docs and slides for inference and tf slim docs for training model.
It's a multi-class classification problem. I have trained tf slim mobilnet_v2 model from scratch (using sript train_image_classifier.py). Evaluation of trained model on test set gives relatively good results to begin with (using script eval_image_classifier.py):
eval/Accuracy[0.8017]eval/Recall_5[0.9993]
However, single .ckpt file is not saved (even though at the end of train_image_classifier.py run there is a message like "model.ckpt is saved to checkpoint_dir"), there are 3 files (.ckpt-180000.data-00000-of-00001, .ckpt-180000.index, .ckpt-180000.meta) instead.
OpenVINO model optimizer requires a single checkpoint file.
According to docs I call mo_tf.py with following params:
python mo_tf.py --input_model D:/model/mobilenet_v2_224.pb --input_checkpoint D:/model/model.ckpt-180000 -b 1
It gives the error (same if pass --input_checkpoint D:/model/model.ckpt):
[ ERROR ] The value for command line parameter "input_checkpoint" must be existing file/directory, but "D:/model/model.ckpt-180000" does not exist.
Error message is clear, there are not such files on disk. But as I know most tf utilities convert .ckpt-????.meta to .ckpt under the hood.
Trying to call:
python mo_tf.py --input_model D:/model/mobilenet_v2_224.pb --input_meta_graph D:/model/model.ckpt-180000.meta -b 1
Causes:
[ ERROR ] Unknown configuration of input model parameters
It doesn't matter for me in which way I will transfer graph to OpenVINO intermediate representation, just need to reach that result.
Thanks a lot.
EDIT
I managed to run OpenVINO model optimizer on frozen graph of tf slim model. However I still have no idea why had my previous attempts (based on docs) failed.
you can try converting the model to frozen format (.pb) and then convert the model using OpenVINO.
.ckpt-meta has the metagraph. The computation graph structure without variable values.
the one you can observe in tensorboard.
.ckpt-data has the variable values,without the skeleton or structure. to restore a model we need both meta and data files.
.pb file saves the whole graph (meta+data)
As per the documentation of OpenVINO:
When a network is defined in Python* code, you have to create an inference graph file. Usually, graphs are built in a form that allows model training. That means that all trainable parameters are represented as variables in the graph. To use the graph with the Model Optimizer, it should be frozen.
https://software.intel.com/en-us/articles/OpenVINO-Using-TensorFlow
the OpenVINO optimizes the model by converting the weighted graph passed in frozen form.
I retrained inceptionV3 model on my own data using Tensorflow slim. Below files are generated after training :-
graph.pbtxt, model.ckpt, model.meta, model.index, checkpoint,
events.out.tfevents
I want to freeze the graph files and create a .pb file. I don't know what is input node and output node in inception v3. And using Tensorboard is complex for me.
What are the input/output nodes in inceptionV3?(in slim/nets) OR how can I find the input/output nodes ?
OS : window 7
(A). If you will make it to bottom of this link. You would find this somewhere(specific to inceptionV3) :
input_layer=input
output_layer=InceptionV3/Predictions/Reshape_1
(B). Another way is to print all tensors of the model and get input/output tensor
from tensorflow.python.tools.inspect_checkpoint import print_tensors_in_checkpoint_file
ckpt_path="model.ckpt"
print_tensors_in_checkpoint_file(file_name=ckpt_path, tensor_name='', all_tensors=True, all_tensor_names=True)
(C). If you need to print tensor names of .pb file. You can use this simple code.
Check what would work for you.
I want to use transfer learning with Google's Inception network for an image recognition problem. I am using retrain.py from the TensorFlow example source for inspiration.
In retrain.py, the Inception graph is loaded and a feed dict is used to feed the new images into the model's input layer. However, I have my data serialized in TFRecord files and have been using an input pipeline to feed in my inputs, as demonstrated here.
So I have a tensor images which returns my input data in batches when run. But how can I feed these images into Inception? I can't use a feed dict since my inputs are tensors, not NumPy arrays. My two ideas are
1) simply call sess.run() on each batch to convert it to a NumPy array, and then use a feed dict to pass it to Inception.
2) replace the input node in the Inception graph with my own batch input tensor
I think (1) would work, but it seems a little inelegant. (2) seems more natural to me, but I can't do exactly that because TensorFlow graphs can only be appended to and not otherwise modified.
Is there a better approach?
You can implement option (2), replacing the input node, but you will need to modify retrain.py to do so. The tf.import_graph_def() function supports a limited form of modification to the imported graph, by remapping tensors in the imported graph to existing tensors in the target graph.
This line in retrain.py calls tf.import_graph_def() to import the Inception model, where jpeg_data_tensor becomes the tensor that you feed with input data:
bottleneck_tensor, jpeg_data_tensor, resized_input_tensor = (
tf.import_graph_def(graph_def, name='', return_elements=[
BOTTLENECK_TENSOR_NAME, JPEG_DATA_TENSOR_NAME,
RESIZED_INPUT_TENSOR_NAME]))
Instead of retrieving jpeg_data_tensor from the imported graph, you can remap it to an input pipeline that you construct yourself:
# Output of a training pipeline, returning a `tf.string` tensor containing
# a JPEG-encoded image.
jpeg_data_tensor = ...
bottleneck_tensor, resized_input_tensor = (
tf.import_graph_def(
graph_def,
input_map={JPEG_DATA_TENSOR_NAME: jpeg_data_tensor},
return_elements=[BOTTLENECK_TENSOR_NAME, RESIZED_INPUT_TENSOR_NAME]))
Wherever you previously fed jpeg_data_tensor, you no longer need to need it, because the inputs will be read from the input pipeline you constructed. (Note that you might need to handle resized_input_tensor as well... I'm not intimately familiar with retrain.py, so some restructuring might be necessary.)