tensorflow-estimator | 易学教程

estimator.predict raises “ValueError: None values not supported”

阅读更多关于 estimator.predict raises “ValueError: None values not supported”

问题 So I basically copypasted the code from the tensorflow tutorial adapted to this model: Which tries to model a neural network to identify "stairs" shape, as it shows here: (source: gormanalysis.com) import numpy as np import tensorflow as tf import _pickle as cPickle with open("var_x.txt", "rb") as fp: # Unpickling var_x = cPickle.load(fp) with open("var_y.txt", "rb") as fp: # Unpickling var_y = cPickle.load(fp) # Declare list of features, we only have one real-valued feature def model_fn

EXCLUDED from export because they cannot be be served via TensorFlow Serving APIs

阅读更多关于 EXCLUDED from export because they cannot be be served via TensorFlow Serving APIs

问题 Tensorflow version 1.10 Using: DNNClassifier and tf.estimator.FinalExporter I'm using the Iris example from TF blog. I defined the following code: # The CSV features in our training & test data. COLUMN_NAMES = ['SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth', 'Species'] FEATURE_COLUMNS = COLUMN_NAMES[:4] INPUT_COLUMNS = [ tf.feature_column.numeric_column(column) for column in COLUMN_NAMES ] def serving_input_receiver_fn(): """Build the serving inputs.""" inputs = {} for feat in INPUT

TensorFlow: how to export estimator using TensorHub module?

阅读更多关于 TensorFlow: how to export estimator using TensorHub module?

问题 I have an estimator using a TensorHub text_embedding column, like so: my_dataframe = pandas.DataFrame(columns=["title"}) # populate data labels = [] # populate labels with 0|1 embedded_text_feature_column = hub.text_embedding_column( key="title" ,module_spec="https://tfhub.dev/google/nnlm-en-dim128-with-normalization/1") estimator = tf.estimator.LinearClassifier( feature_columns = [ embedded_text_feature_column ] ,optimizer=tf.train.FtrlOptimizer( learning_rate=0.1 ,l1_regularization_strength

How to create a tf.feature_column by multiplying two other tf.feature_columns?

阅读更多关于 How to create a tf.feature_column by multiplying two other tf.feature_columns?

问题 In Tensorflow there is already a function to create feature by crossing columns tf.feature_column.crossed_column , but it is more for category data. How about numeric data? For example, there are 2 columns already age = tf.feature_column.numeric_column("age") education_num = tf.feature_column.numeric_column("education_num") if i want to create a third and fourth feature columns base on age and education_num like this my_feature = age * education_num my_another_feature = age * age How can it

Custom eval_metric_ops in Estimator in Tensorflow

阅读更多关于 Custom eval_metric_ops in Estimator in Tensorflow

问题 I am trying to add the r squared in the eval_metric_ops in my estimator like this: def model_fn(features, labels, mode, params): predict = prediction(features, params, mode) loss = my_loss_fn eval_metric_ops = { 'rsquared': tf.subtract(1.0, tf.div(tf.reduce_sum(tf.squared_difference(label, tf.reduce_sum(tf.squared_difference(labels, tf.reduce_mean(labels)))), name = 'rsquared') } train_op = tf.contrib.layers.optimize_loss( loss = loss, global_step = global_step, learning_rate = 0.1, optimizer

Tensorflow Estimator: using predict() function in separate script

阅读更多关于 Tensorflow Estimator: using predict() function in separate script

问题 I have successfully (I hope) trained and evaluated a model using the tf.Estimator where I reach a train/eval accuracy of around 83-85%. So now, I would like to test my model on a separate dataset using the predict() function call in the Estimator class. Preferably I would like to do this in a separate script. I've at this which says that I need to export as a SavedModel, but is this really necessary? Looking at the documentation for the Estimator class, it seems like I can just pass the path

How to get the last global_step from an tf.estimator.Estimator

阅读更多关于 How to get the last global_step from an tf.estimator.Estimator

问题 How can I obtain the last global_step from a tf.estimator.Estimator after train(...) finishes? For instance, a typical Estimator-based training routine might be set up like this: n_epochs = 10 model_dir = '/path/to/model_dir' def model_fn(features, labels, mode, params): # some code to build the model pass def input_fn(): ds = tf.data.Dataset() # obviously with specifying a data source # manipulate the dataset return ds run_config = tf.estimator.RunConfig(model_dir=model_dir) estimator = tf

Tensorflow MNIST Estimator: batch size affects the graph expected input?

阅读更多关于 Tensorflow MNIST Estimator: batch size affects the graph expected input?

问题 I have followed the TensorFlow MNIST Estimator tutorial and I have trained my MNIST model. It seems to work fine, but if I visualize it on Tensorboard I see something weird: the input shape that the model requires is 100 x 784. Here is a screenshot: as you can see in the right box, expected input size is 100x784. I thought I would see ?x784 there. Now, I did use 100 as a batch size in training, but in the Estimator model function I also specified that the amount of input samples size is

Graph optimizations on a tensorflow serveable created using tf.Estimator

阅读更多关于 Graph optimizations on a tensorflow serveable created using tf.Estimator

问题 Context : I have a simple classifier based on tf.estimator.DNNClassifier that takes text and output probabilities over an intent tags. I am able to train an export the model to a serveable as well as serve the serveable using tensorflow serving. The problem is this servable is too big (around 1GB) and so I wanted to try some tensorflow graph transforms to try to reduce the size of the files being served. Problem : I understand how to take the saved_model.pb and use freeze_model.py to create a

Tensorflow : Predict in Recurrent Neural Networks for Drawing Classification tutorial

阅读更多关于 Tensorflow : Predict in Recurrent Neural Networks for Drawing Classification tutorial

I used the tutorial code from https://www.tensorflow.org/tutorials/recurrent_quickdraw and all works fine until I tried to make a prediction instead of just evaluate it. I wrote a new input function for prediction, based on the code in create_dataset.py def predict_input_fn(): def parse_line(stroke_points): """Parse an ndjson line and return ink (as np array) and classname.""" inkarray = json.loads(stroke_points) stroke_lengths = [len(stroke[0]) for stroke in inkarray] total_points = sum(stroke_lengths) np_ink = np.zeros((total_points, 3), dtype=np.float32) current_t = 0 for stroke in inkarray