google-cloud-ml

I manage to retrain my specific classification model using the generic inception model following this tutorial . I would like now to deploy it on the google cloud machine learning following this steps . I already managed to export it as MetaGraph but I can't manage to get the proper inputs and outputs. Using it locally, my entry point to the graph is DecodeJpeg/contents:0 which is fed with a jpeg image in binary format. The output are my predictions. The code I use locally (which is working) is: softmax_tensor = sess.graph.get_tensor_by_name('final_result:0') predictions = sess.run(softmax

I am trying to use Google Cloud ML to host a Tensorflow model and get predictions. I have a pretrained model that I have uploaded to the cloud and I have created a model and version in my Cloud ML console. I followed the instructions from here to prepare my data for requesting online predictions. For both the Python method and the glcoud method I get the same error. For simplicity, I'll post the gcloud method: I run gcloud ml-engine predict --model spell_correction --json-instances test.json where test.json is my input data file (a JSON array named instances ). I get the following result:

I am trying to convert a keras model to use it for predictions on google cloud's ml-engine. I have a pre-trained classifier that takes in a numpy array as input. The normal working data I send to model.predict is named input_data. I convert it to base 64 and dump it to a json file using the following few lines: data = {} data['image_bytes'] = [{'b64':base64.b64encode(input_data.tostring())}] with open('weights/keras/example.json', 'w') as outfile: json.dump(data, outfile) Now, I try to create the TF model from my existing model: from keras.models import model_from_json import tensorflow as tf

In the alpha release of CloudML's online prediction service, the format for exporting model was: inputs = {"x": x, "y_bytes": y} g.add_to_collection("inputs", json.dumps(inputs)) outputs = {"a": a, "b_bytes": b} g.add_to_collection("outputs", json.dumps(outputs)) I would like to convert this to a SavedModel without retraining my model. How can I do that? We can convert this to a SavedModel by importing the old model, creating the Signatures, and re-exporting it. This code is untested, but something like this should work: import json import tensorflow as tf from tensorflow.contrib.session

This is a ml-job I previously trained successfully . But when I tried it today it's not working . So after that I tried removing all the things is the bucket and start over . Still it's not working . Giving the following error . Internal error occurred. Please retry in a few minutes. If you still experience errors, contact Cloud ML. 来源： https://stackoverflow.com/questions/45609164/google-cloud-ml-engine-job-failed-due-to-an-internal-error-cant-execute-a-j

I want to train a model on about 2TB of image data on gcloud storage. I saved the image data as separate tfrecords and tried to use the tensorflow data api following this example https://medium.com/@moritzkrger/speeding-up-keras-with-tfrecord-datasets-5464f9836c36 But it seems like keras' model.fit(...) doesn't support validation for tfrecord datasets based on https://github.com/keras-team/keras/pull/8388 Is there a better approach for processing large amounts of data with keras from ml-engine that I'm missing? Thanks a lot! If you are willing to use tf.keras instead of actual Keras, you can

I'm predicting image classes using Keras. It works in Google Cloud ML (GCML), but for efficiency need change it to pass base64 strings instead of json array. Related Documentation I can easily run python code to decode a base64 string into json array, but when using GCML I don't have the opportunity to run a preprocessing step (unless maybe use a Lambda layer in Keras, but I don't think that is the correct approach). Another answer suggested adding tf.placeholder with type of tf.string , which makes sense, but how to incorporate that into the Keras model? Here is complete code for training the