asimshankar

Keybase proof

I hereby claim:

• I am asimshankar on github.
• I am asimshankar (https://keybase.io/asimshankar) on keybase.
• I have a public key whose fingerprint is 5EB2 02EC 3AE5 51CB BCBA B808 4FFA CDA8 6927 0665

To claim this, I am signing this object:

asimshankar

import tensorflow as tf

# Construct the graph
x = tf.Variable(1, name='x')
y = tf.Variable(2, name='y')
sum = tf.assign_add(x, y, name='sum')

# Add operations to save and restore checkpoints
saver = tf.train.Saver()

asimshankar

export_path = "./tf"
builder = tf.saved_model.builder.SavedModelBuilder(export_path)
signature = tf.saved_model.signature_def_utils.predict_signature_def(
  inputs={"input": mod.input},
  outputs={"output": mod.output})
 
with K.get_session() as sess:
  builder.add_meta_graph_and_variables(sess=sess,
    tags=[tag_constants.SERVING],

asimshankar

# Mostly copied from https://keras.io/applications/#usage-examples-for-image-classification-models                                           
# Changing it to use InceptionV3 instead of ResNet50                                                                                         
from keras.applications.inception_v3 import InceptionV3, preprocess_input, decode_predictions                                                
from keras.preprocessing import image                                                                                                        
import numpy as np                                                                                                                           
                                                                                                                                             
model = InceptionV3()                                                                                                                        
img_path = 'elephant.jpg'     

asimshankar

Custom Datasets involve adding a new operation.

asimshankar

Training TensorFlow models in C++

Python is the primary language in which TensorFlow models are typically developed and trained. TensorFlow does have bindings for other programming languages. These bindings have the low-level primitives that are required to build a more complete API, however, lack much of the higher-level API richness of the Python bindings, particularly for defining the model structure.

This file demonstrates taking a model (a TensorFlow graph) created by a Python program and running the training loop in C++.

asimshankar

Training TensorFlow models in C

Python is the primary language in which TensorFlow models are typically developed and trained. TensorFlow does have bindings for other programming languages. These bindings have the low-level primitives that are required to build a more complete API, however, lack much of the higher-level API richness of the Python bindings, particularly for defining the model structure.

This gist demonstrates taking a model (a TensorFlow graph) created by a Python program and running the training loop in a C program.

The model