I train a model by tensorflow 2 to detecting vehicles, but I want to Convert tensorflow saved_model to frozen inference graph.
Can any one help?
It is not the recommended way to save your model and i would suggest you use saved model.
People around here can help if you explain why you want to use frozen graph specifically and saved model won't help.
If you still want to try freezing you can use this internal method to do so.
Related
I would like to train a MLP(Multi Layer Perceptron) with MNIST dataset. I use a validation set so I can save the weights of the best model. Then I want to load these weights back into the same architecture and use them to initialize and train with another dataset. I would like to know if this is possible with Tensorflow 1.x or 2.x. Right now I am trying to write a custom function to do it but it is getting complicated. I am using tf 1.x.
I suggest you take a look at tensorflow's documentation, here a link of a tutorial to save your weights and load them afterwards:
https://www.tensorflow.org/tutorials/keras/save_and_load
How do I find more info on how the ssd_mobilenet_v1 tflite model on TFHub was trained?
Was it trained in such a way that made it easy to convert it to tflite by avoiding certain ops not supported by tflite? Or was it trained normally, and then converted using the tflite converter with TF Select and the tips on this github issue?
Also, does anyone know if there's an equivalent mobilenet tflite model trained on OpenImagesV6? If not, what's the best starting point for training one?
I am not sure about about the exact origin of the model, but looks like it does have TFLite-compatible ops. From my experience, the best place to start for TFLite-compatible SSD models is with the TF2 Detection Zoo. You can convert any of the SSD models using these instructions.
To train your own model, you can follow these instructions that leverage Google Cloud.
I have trained an image classification model using pytorch.
Now, I want to move it from research to production pipeline.
I am thinking of using TensorFlow extended. I have a very noob doubt that will I'll be able to use my PyTorch trained model in the TensorFlow extended pipeline(I can convert the trained model to ONNX and then to Tensorflow compatible format).
I don't want to rewrite and retrain the training part to TensorFlow as it'll be a great overhead.
Is it possible or Is there any better way to productionize the PyTorch trained models?
You should be able to convert your PyTorch image classification model to Tensorflow format using ONNX, as long as you are using standard layers. I would recommend doing the conversion and then look at both model summaries to make sure they are relatively similar. Also, do some tests to make sure your converted model handles any particular edge cases you have. Once you have confirmed that the converted model works, save your model as a TF SavedModel format and then you should be able to use it in Tensorflow Extended (TFX).
For more info on the conversion process, see this tutorial: https://learnopencv.com/pytorch-to-tensorflow-model-conversion/
You could considering using the torchX library. I haven't use it yet, but it seems to make it easier to deploy models by creating and running model pipelines. I don't think it has the same data validation functionality that Tensorflow Extended has, but maybe that will be added in the future.
I'm having a really hard time converting this model to s h5 model so I can then convert it to Tensorflow lite Someone managed to do that. I shared the colab here:
I really appreciate any help that I can get.
here is my colab:
https://colab.research.google.com/drive/1ZON8lvha8sI9ZCJEF0Ad8au2NNc9sUkU
I used this approach:
from docproduct.models import MedicalQAModelwithBert
medical_qa_model = MedicalQAModelwithBert(
config_file=os.path.join(
pretrained_path, 'bert_config.json'),
checkpoint_file=os.path.join(pretrained_path, 'biobert_model.ckpt'))
medical_qa_model.save("model.h5")
The error that I get is
NotImplementedError: The save method requires the model to be a Functional model or a Sequential model. It does not work for subclassed models, because such models are defined via the body of a Python method, which isn't safely serializable. Consider using save_weights, in order to save the weights of the model.
I can save_weights but then I will have issue with converting with tflite because that requires the whole model. Any one have any suggestions how to solve this issue ?
My ultimate goal is to convert the model to tflite.
Thanks
Update:
It seems the issue is that they make their own subclass of Model and do not implement save().
https://github.com/re-search/DocProduct/blob/master/docproduct/models.py#L62
Is there any workaround to be able to convert the model without training it from scratch?
Basically I am trying to use google's pre trained Speaker-id model for speaker detection. But this being a TensorFlow Lite model, I can't use it on my Linux pc. For that, I am trying to find a converter back to its frozen graph model.
Any help on this converter or any direct way to use tensorflow Lite pretrained models on desktop itself, will be appreciated.
You can use the converter which generates tflite models to convert it back to a .pb file if that is what you're searching for.
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/lite/toco/g3doc/cmdline_examples.md