I have trained my model as QNN with brevitas. Basically my input shape is:
torch.Size([1, 3, 1024])
I have exported the .pt extended file. As I try my model and generate a confusion matrix I was able to observe everything that I want.
So I believe that there is no problem about the model.
On the other hand as I try to export the .onnx file to implement this brevitas trained model on FINN, I wrote the code given below:
from brevitas.export import FINNManager
FINNManager.export(my_model, input_shape=(1, 3, 1024), export_path='myfinnmodel.onnx')
But as I do that I get the error as:
torch.onnx.export(module, input_t, export_target, **kwargs)
TypeError: export() got an unexpected keyword argument
'enable_onnx_checker'
I do not think this is related with the version. But if you want me to be sure about the version, I can check these too.
If you can help me I will be really appreciated.
Sincerely;
The problem is related to pytorch version > 1.10. Where "enable_onnx_checker" is no more a parameter of torch.onnx.export function.
This is the official solution from the repository.
https://github.com/Xilinx/brevitas/pull/408/files
The fix is not yet release. Is in dev branch.
You need to compile brevitas by yourself or simply change the code in brevitas/export/onnx/manager.py following official solution.
After that i am able to get onnx converted model.
Related
I read several discussions about this and still cannot make it work for my case
Have a classification model trained using Google Tables.
Exported the model and download the directory with cli.
My goal is to get a better understanding of the model trained by google, study it, understand its decisions. And later try to prune it to improve performance.
I'm using this code, just to start:
import tensorflow as tf
from tensorflow import keras
import struct2tensor
location = "model_dir"
model = tf.saved_model.load(location)
model.summary()
I get this error:
AttributeError: 'AutoTrackable' object has no attribute 'summary'
the variable model is of type:
<tensorflow.python.training.tracking.tracking.AutoTrackable at 0x7fa8eaa7ed30>
And I stuck there, don't know how to continue. Using Python 3.8 and the last version of those libraries. Any idea of how can I proceed?
Thanks!
The proper method to load your model depends on your file formatting.
You can see in the Tensorflow documentation that "The object returned by tf.saved_model.load is not a Keras object (i.e. doesn't have .fit, .predict, etc. methods)" and "Use tf.keras.models.load_model to restore the Keras model".
I'm not sure if you want to use the keras module or not, but since you have imported it I assume you do. In that case I would recommend checking this other Stackoverflow thread where it is explained how to use the tf.keras.models.load_model method depending if your model is saved as .pb or .h5.
If the model is saved as .pb you should use it with the string pointing to the directory where the model is saved, as you did in your code snippet but in this case using the keras method:
model = tf.keras.models.load_model('model_dir')
If instead it's saved as .h5 you should use it specifying it:
model = tf.keras.models.load_model('my_model_in_h5.h5')
Totally new to Tensorflow,
I have created one object detection model (.pb and .pbtxt) using 'faster_rcnn_inception_v2_coco_2018_01_28' model I found from TensorFlow zoo. It works fine on windows but I want to use this model on google coral edge TPU. How can I convert my frozen model into edgetpu.tflite quantized model?
There are 2 more steps to this pipeline:
1) Convert the .pb -> tflite:
I won't go through details since there are documentation on this on tensorflow official page and it changes very often, but I'll still try to answer specifically to your question. There are 2 ways of doing this:
Quantization Aware Training: this happens during training of the model. I don't think this applies to you since your question seems to indicates that you were not aware of this process. But please correct me if I'm wrong.
Post Training Quantization: Basically loading your model where all tensors are of type float and convert it to a tflite form with int8 tensors. Again, I won't go into too much details, but I'll give you 2 actual examples of doing so :) a) with code
b) with tflite_convert tools
2) Compile the model from tflite -> edgetpu.tflite:
Once you have produced a fully quantized tflite model, congrats your model is now much more efficient for arm platform and the size is much smaller. However it will still be ran on the CPU unless you compile it for the edgetpu. You can review this doc for installation and usage. But compiling it is as easy as:
$ edgetpu_compiler -s your_quantized_model.tflite
Hope this helps!
I am trying to check if my .onnx model is correct, and need to run inference to verify the output for the same.
I know we can run validation on .mlmodel using coremltools in Python - basically load the model and input and get the prediction. I am trying to do a similar thing for the .onnx model.
I found the MXNet framework but I can't seem to understand how to import the model - I just have the .onnx file and MXNet requires some extra input besides the onnx model.
Is there any other simple way to do this in Python? I am guessing this is a common problem but can't seem to find any relevant libraries/frameworks to do this as easily as coremltools for .mlmodel.
I do not wish to convert .onnx to another type of model (like say PyTorch) as I want to check the .onnx model as is, not worrying if the conversion was correct. Just need a way to load the model and input, run inference and print the output.
This is my first time encountering these formats, so any help or insight would be appreciated.
Thanks!
I figured out a way to do this using Caffe2 - just posting in case someone in the future tries to do the same thing.
The main code snippet is:
import onnx
import caffe2.python.onnx.backend
from caffe2.python import core, workspace
import numpy as np
# make input Numpy array of correct dimensions and type as required by the model
modelFile = onnx.load('model.onnx')
output = caffe2.python.onnx.backend.run_model(modelFile, inputArray.astype(np.float32))
Also it is important to note that the input to run_model can only be a numpy array or a string. The output will be an object of the Backend.Outputs type. I was able to extract the output numpy array from it.
I was able to execute inference on the CPU, and hence did not need the Caffe2 installation with GPU (requiring CUDA and CDNN).
This is probably a very basic question...
But how do I convert checkpoint files into a single .pb file.
My goal is to serve the model using probably C++
These are the files that I'm trying to convert.
As a side note I'm using tflearn with tensorflow.
Edit 1:
I found an article that explains how to do this: https://blog.metaflow.fr/tensorflow-how-to-freeze-a-model-and-serve-it-with-a-python-api-d4f3596b3adc
The problem is that I'm stuck with the following error
KeyError: "The name 'Adam' refers to an Operation not in the graph."
How do I fix this?
Edit 2:
Maybe this will shed some light on the problem.
The error that I get comes from the regression layer, if I use: sgd.
I'll get
KeyError: "The name 'SGD' refers to an Operation not in the graph."
The tutorial on https://blog.metaflow.fr/tensorflow-how-to-freeze-a-model-and-serve-it-with-a-python-api-d4f3596b3adc works just fine.
The problem was that I was loading the model using tensorflow instead of using tflearn.
So... instead of:
tf.train.import_meta_graph(...)
We do:
model.load(...)
TFLearn knows how to parse the graph properly.
I'm having an issue i can't manage to solve.
I'm just approaching the Super Resolution Images on Python and i found this on github: https://github.com/titu1994/Image-Super-Resolution
I think this is exactly what i need for my project.
So i just install everything i need to run it and i run it with this:
python main.py (path)t1.bmp
t1.bmp is an image stored in the "input-images" directory so my command is this:
python main.py C:\Users\cecilia....\t1.bmp
The error i get is this:
http://imgur.com/X3ssj08
http://imgur.com/rRSdyUb
Can you please help me solving this? (The code i'm using is the one on the github i linked)
Thanks in advance
The very first line on the Readme in the github link that you give says that the code is designed for theano only. Yet in your traceback it shows that you are using tensorflow as backend...
The error that you are having is typical of having the wrong image format for the used backend. You have to know that for convolutional networks, Theano and tensorflow have different conventions. Theano expects the following order for the dimensions (batch, channels, nb_rows , nb_cols) and tensorflow (batch, nb_rows, nb_cols, channels). The first is known as "channels_first" and the other "channels_last". So what happens is that the code you are trying to run (which is explicitly said to be designed for Theano) organises the data to match the channels_first format, which causes tensorflow to crash because the dimensions don't match what it expects.
Bottom line: use theano, or change the code appropriately to make it work on tensorflow.