I have an tensorflow .pb file which I would like to load into python DNN, restore the graph and get the predictions. I am doing this to test out whether the .pb file created can make the predictions similar to the normal Saver.save() model.
My basic problem is am getting a very different value of predictions when I make them on Android using the above mentioned .pb file
My .pb file creation code:
frozen_graph = tf.graph_util.convert_variables_to_constants(
session,
session.graph_def,
['outputLayer/Softmax']
)
with open('frozen_model.pb', 'wb') as f:
f.write(frozen_graph.SerializeToString())
So I have two major concerns:
How can I load the above mentioned .pb file to python Tensorflow model ?
Why am I getting completely different values of prediction in python and android ?
The following code will read the model and print out the names of the nodes in the graph.
import tensorflow as tf
from tensorflow.python.platform import gfile
GRAPH_PB_PATH = './frozen_model.pb'
with tf.Session() 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]
names = []
for t in graph_nodes:
names.append(t.name)
print(names)
You are freezing the graph properly that is why you are getting different results basically weights are not getting stored in your model. You can use the freeze_graph.py (link) for getting a correctly stored graph.
Here is the updated code for tensorflow 2.
import tensorflow as tf
GRAPH_PB_PATH = './frozen_model.pb'
with tf.compat.v1.Session() as sess:
print("load graph")
with tf.io.gfile.GFile(GRAPH_PB_PATH,'rb') as f:
graph_def = tf.compat.v1.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]
names = []
for t in graph_nodes:
names.append(t.name)
print(names)
Related
I have a convolutional LSTM model that I am hoping to use on an android app to do real time prediction, however facing some issue converting it to tflite.
model = Sequential()
model.add(ConvLSTM2D(filters=64, kernel_size=(1,3), activation='relu', input_shape=(n_steps, 1, n_length, n_features)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(n_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
Everything works fine, however when I try to convert to tflite, I get the following error:
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()
# Save the model.
with open('model_conv_lstm.tflite', 'wb') as f:
f.write(tflite_model)
from google.colab import files
files.download('model_conv_lstm.tflite')
/usr/local/lib/python3.7/dist-packages/tensorflow/lite/python/convert.py in toco_convert_protos(model_flags_str, toco_flags_str, input_data_str, debug_info_str, enable_mlir_converter)
313 for error_data in _metrics_wrapper.retrieve_collected_errors():
314 converter_error.append_error(error_data)
--> 315 raise converter_error
316
317 return _run_toco_binary(model_flags_str, toco_flags_str, input_data_str,
ConverterError: /usr/local/lib/python3.7/dist-packages/tensorflow/python/saved_model/save.py:1315:0: error: 'tf.TensorListReserve' op requires element_shape to be static during TF Lite transformation pass
<unknown>:0: note: loc("StatefulPartitionedCall"): called from
/usr/local/lib/python3.7/dist-packages/tensorflow/python/saved_model/save.py:1315:0: error: failed to legalize operation 'tf.TensorListReserve' that was explicitly marked illegal
<unknown>:0: note: loc("StatefulPartitionedCall"): called from
<unknown>:0: error: Lowering tensor list ops is failed. Please consider using Select TF ops and disabling `_experimental_lower_tensor_list_ops` flag in the TFLite converter object. For example, converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]\n converter._experimental_lower_tensor_list_ops = False
I manage to fix the error if I convert the model to tflite using this:
# Convert the model.
converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]
converter._experimental_lower_tensor_list_ops = False
tflite_model = converter.convert()
# Save the model.
with open('model_conv_lstm.tflite', 'wb') as f:
f.write(tflite_model)
from google.colab import files
files.download('model_conv_lstm.tflite')
However, when I import the tflite model into my android app, it doesn't work anymore and the app crashes each time I load the model. Any ideas what might be the problem?
I am attempting to use a new NLP model within the PyTorch android demo app Demo App Git however I am struggling to serialize the model so that it works with Android.
The demonstration given by PyTorch is as follows for a Resnet model:
model = torchvision.models.resnet18(pretrained=True)
model.eval()
example = torch.rand(1, 3, 224, 224)
traced_script_module = torch.jit.trace(model, example)
traced_script_module.save("app/src/main/assets/model.pt")
However I am not sure what to use for the 'example' input with my NLP model.
The model that I am using from a fastai tutorial and the python is linked here: model
Here is the Python used to create my model (using the Fastai library). It is the same as in the model link above, but in a simplified form.
from fastai.text import *
path = untar_data('http://files.fast.ai/data/examples/imdb_sample')
path.ls()
#: [PosixPath('/storage/imdb_sample/texts.csv')]
data_lm = TextDataBunch.from_csv(path, 'texts.csv')
data = (TextList.from_csv(path, 'texts.csv', cols='text')
.split_from_df(col=2)
.label_from_df(cols=0)
.databunch())
bs=48
path = untar_data('https://s3.amazonaws.com/fast-ai-nlp/imdb')
data_lm = (TextList.from_folder(path)
.filter_by_folder(include=['train', 'test', 'unsup'])
.split_by_rand_pct(0.1)
.label_for_lm()
.databunch(bs=bs))
learn = language_model_learner(data_lm, AWD_LSTM, drop_mult=0.3)
learn.fit_one_cycle(1, 1e-2, moms=(0.8,0.7))
learn.unfreeze()
learn.fit_one_cycle(10, 1e-3, moms=(0.8,0.7))
learn.save_encoder('fine_tuned_enc')
path = untar_data('https://s3.amazonaws.com/fast-ai-nlp/imdb')
data_clas = (TextList.from_folder(path, vocab=data_lm.vocab)
.split_by_folder(valid='test')
.label_from_folder(classes=['neg', 'pos'])
.databunch(bs=bs))
learn = text_classifier_learner(data_clas, AWD_LSTM, drop_mult=0.5)
learn.load_encoder('fine_tuned_enc')
learn.fit_one_cycle(1, 2e-2, moms=(0.8,0.7))
learn.freeze_to(-2)
learn.fit_one_cycle(1, slice(1e-2/(2.6**4),1e-2), moms=(0.8,0.7))
learn.freeze_to(-3)
learn.fit_one_cycle(1, slice(5e-3/(2.6**4),5e-3), moms=(0.8,0.7))
learn.unfreeze()
learn.fit_one_cycle(2, slice(1e-3/(2.6**4),1e-3), moms=(0.8,0.7))
I worked out how to do this after a while. The issue was that the Fastai model wasn't tracing correctly no matter what shape of input I was using.
In the end, I used another text classification model and got it to work. I wrote a tutorial about how I did it, in case it can help anyone else.
NLP PyTorch Tracing Tutorial
Begin by opening a new Jupyter Python Notebook using your preferred cloud machine provider (I use Paperspace).
Next, copy and run the code in the PyTorch Text Classification tutorial. But replace the line…
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
With…
device = torch.device("cpu")
NOTE: It caused issues tracing when the device was set to CUDA so I forced it on to the CPU. (this will slow training, but inference on the mobile will run at the same speed as it is cpu anyway)
Lastly, run the code below to correctly trace the model to allow it to be run on Android:
data = DataLoader(test_dataset, batch_size=1, collate_fn=generate_batch)
for text, offsets, cls in data:
text, offsets, cls = text.to(device), offsets.to(device), cls.to(device)
example = text, offsets
traced_script_module = torch.jit.trace(model, example)
traced_script_module.save("model.pt")
In addition, if you would like a CSV copy of the vocab list for use on Android when you are making predictions, run the following code afterwards:
import pandas as pd
vocab = train_dataset.get_vocab()
df = pd.DataFrame.from_dict(vocab.stoi, orient='index', columns=['token'])
df[:30]
df.to_csv('out.csv')
This model should work fine on Android using the PyTorch API.
I'm developing a real-time object classification app for android. First I created a deep learning model using "keras" and I already have trained model saved as "model.h5" file. I would like to know how can I use that model in android for image classification.
You cant export Keras directly to Android but you have to save the model
Configure Tensorflow as your Keras backend.
Save model wights using model.save(filepath) (you already done this)
Then load it with one of the following solutions:
Solution 1: Import model in Tensflow
1- Build Tensorflow model
Build tensorflow model from keras model use this code (link updated)
2- Build Android app and call Tensorflow. check this tutorial and this official demo from google to learn how to do it.
Solution 2: Import model in java
1- deeplearning4j a java library allow to import keras model: tutorial link
2- Use deeplearning4j in Android: it is easy since you are in java world. check this tutorial
First you need to export the Keras model to a Tensorflow model :
def export_model_for_mobile(model_name, input_node_names, output_node_name):
tf.train.write_graph(K.get_session().graph_def, 'out', \
model_name + '_graph.pbtxt')
tf.train.Saver().save(K.get_session(), 'out/' + model_name + '.chkp')
freeze_graph.freeze_graph('out/' + model_name + '_graph.pbtxt', None, \
False, 'out/' + model_name + '.chkp', output_node_name, \
"save/restore_all", "save/Const:0", \
'out/frozen_' + model_name + '.pb', True, "")
input_graph_def = tf.GraphDef()
with tf.gfile.Open('out/frozen_' + model_name + '.pb', "rb") as f:
input_graph_def.ParseFromString(f.read())
output_graph_def = optimize_for_inference_lib.optimize_for_inference(
input_graph_def, input_node_names, [output_node_name],
tf.float32.as_datatype_enum)
with tf.gfile.FastGFile('out/tensorflow_lite_' + model_name + '.pb', "wb") as f:
f.write(output_graph_def.SerializeToString())
You just need to know the input_nodes_names and output_node_names of your graph. This will create a new folder with several files. Among them, one starts with tensorflow_lite_. This is the file you shall move to your Android device.
Then import Tensorflow library on Android and use TensorFlowInferenceInterface to run your model.
implementation 'org.tensorflow:tensorflow-android:1.5.0'
You can check my simple XOR example on Github :
https://github.com/OmarAflak/Keras-Android-XOR
If you want optimize way to do classification then i will suggest you to run inference of your model using armnn android libraries.
You have to follow few steps.
1. Install and setup arm nn libraries in ubuntu. You can take help from below url
https://github.com/ARM-software/armnn/blob/branches/armnn_19_08/BuildGuideAndroidNDK.md
Just import your model and do inference. You can take help from below url
https://developer.arm.com/solutions/machine-learning-on-arm/developer-material/how-to-guides/deploying-a-tensorflow-mnist-model-on-arm-nn/deploying-a-tensorflow-mnist-model-on-arm-nn-single-page
After compilation you will get binary which will take input and give you output
You can run that binary inside any andriod appication
It is optimize way.
I use custom model for classification in Tensor flow Camera Demo.
I generated a .pb file (serialized protobuf file) and I could display the huge graph it contains.
To convert this graph to a optimized graph, as given in [https://www.oreilly.com/learning/tensorflow-on-android], the following procedure could be used:
$ bazel-bin/tensorflow/python/tools/optimize_for_inference \
--input=tf_files/retrained_graph.pb \
--output=tensorflow/examples/android/assets/retrained_graph.pb
--input_names=Mul \
--output_names=final_result
Here how to find the input_names and output_names from the graph display.
When I dont use proper names, I get device crash:
E/TensorFlowInferenceInterface(16821): Failed to run TensorFlow inference
with inputs:[AvgPool], outputs:[predictions]
E/AndroidRuntime(16821): FATAL EXCEPTION: inference
E/AndroidRuntime(16821): java.lang.IllegalArgumentException: Incompatible
shapes: [1,224,224,3] vs. [32,1,1,2048]
E/AndroidRuntime(16821): [[Node: dropout/dropout/mul = Mul[T=DT_FLOAT,
_device="/job:localhost/replica:0/task:0/cpu:0"](dropout/dropout/div,
dropout/dropout/Floor)]]
Try this:
run python
>>> import tensorflow as tf
>>> gf = tf.GraphDef()
>>> gf.ParseFromString(open('/your/path/to/graphname.pb','rb').read())
and then
>>> [n.name + '=>' + n.op for n in gf.node if n.op in ( 'Softmax','Placeholder')]
Then, you can get result similar to this:
['Mul=>Placeholder', 'final_result=>Softmax']
But I'm not sure it's the problem of node names regarding the error messages.
I guess you provided wrong arguements when loading the graph file or your generated graph file is something wrong?
Check this part:
E/AndroidRuntime(16821): java.lang.IllegalArgumentException: Incompatible
shapes: [1,224,224,3] vs. [32,1,1,2048]
UPDATE:
Sorry,
if you're using (re)trained graph , then try this:
[n.name + '=>' + n.op for n in gf.node if n.op in ( 'Softmax','Mul')]
It seems that (re)trained graph saves input/output op name as "Mul" and "Softmax", while optimized and/or quantized graph saves them as "Placeholder" and "Softmax".
BTW, using retrained graph in mobile environment is not recommended according to Peter Warden's post: https://petewarden.com/2016/09/27/tensorflow-for-mobile-poets/ . It's better to use quantized or memmapped graph due to performance and file size issue, I couldn't find out how to load memmapped graph in android though...:(
(no problem loading optimized / quantized graph in android)
Recently I came across this option directly from tensorflow:
bazel build tensorflow/tools/graph_transforms:summarize_graph
bazel-bin/tensorflow/tools/graph_transforms/summarize_graph
--in_graph=custom_graph_name.pb
I wrote a simple script to analyze the dependency relations in a computational graph (usually a DAG, directly acyclic graph). It's so obvious that the inputs are the nodes that lack a input. However, outputs can be defined as any nodes in a graph because, in the weirdest but still valid case, outputs can be inputs while the other nodes are all dummy. I still define the output operations as nodes without output in the code. You could neglect it at your willing.
import tensorflow as tf
def load_graph(frozen_graph_filename):
with tf.io.gfile.GFile(frozen_graph_filename, "rb") as f:
graph_def = tf.compat.v1.GraphDef()
graph_def.ParseFromString(f.read())
with tf.Graph().as_default() as graph:
tf.import_graph_def(graph_def)
return graph
def analyze_inputs_outputs(graph):
ops = graph.get_operations()
outputs_set = set(ops)
inputs = []
for op in ops:
if len(op.inputs) == 0 and op.type != 'Const':
inputs.append(op)
else:
for input_tensor in op.inputs:
if input_tensor.op in outputs_set:
outputs_set.remove(input_tensor.op)
outputs = list(outputs_set)
return (inputs, outputs)
I am writing an android app using python for android (sl4a) and what I want it to do is search a joke website and extract a joke. Then tell me that joke to wake me up. So far it saves the raw html source to a list but I need it to make a new list by saving the data between html tags then reading that data to me. Its the parser I can't get to work. Here's the code:
import android
droid = android.Android()
import urllib
current = 0
newlist = []
sock = urllib.urlopen("http://m.funtweets.com/random")
htmlSource = sock.read()
sock.close()
rawhtml = []
rawhtml.append (htmlSource)
while current < len(rawhtml):
while current != "<div class=":
if [current] == "</b></a>":
newlist.append (current)
current += 1
print newlist
use this LIB for parsing HTML in android http://jsoup.org/ its reach and widely accepted lib among developers its also available for python :)
This is how to do this:
[Code]
import re
import urllib2
page = urllib2.urlopen("http://www.m.funtweets.com/random").read()
user = re.compile(r'<span>#</span>(\w+)')
text = re.compile(r"</b></a> (\w.*)")
user_lst =[match.group(1) for match in re.finditer(user, page)]
text_lst =[match.group(1) for match in re.finditer(text, page)]
for _user, _text in zip(user_lst, text_lst):
print '#{0}\n{1}\n'.format(_user,_text)
[/code]