# How to find prediction probability in given CNN in tensor flow?

I am very new in tenser flow. Lets assume I already have a trained convolution neutral network, now I give one new data to this CNN, and I want to see whats the prediction probability in each class. (e.g, the CNN is for handwriting 0-2, now I give a new data 2 to this trained CNN, the prediction probability should give me something like, 0.01 for class 0, 0.02 for class 1, and 0.97 for class 2)

May I ask someone advise me, whats the right code to do that in tenser flow (1.13.1) for python ? Sorry about the elementary level question.

I am using the example code.

"""Convolutional Neural Network Estimator for MNIST, built with tf.layers."""

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np
import tensorflow as tf
print("heeeeeeeeeeeeeeeeeeeeere:", tf.VERSION)

tf.logging.set_verbosity(tf.logging.DEBUG)

def cnn_model_fn(features, labels, mode):
"""Model function for CNN."""

input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])

conv1 = tf.layers.conv2d(inputs=input_layer, filters=30, kernel_size=[5, 5], padding="same", activation=tf.nn.relu)

pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)

pool2_flat = tf.reshape(pool1, [-1, 14 * 14 * 30])

dense = tf.layers.dense(inputs=pool2_flat, units=1000, activation=tf.nn.relu)

# Add dropout operation; 0.6 probability that element will be kept
dropout = tf.layers.dropout(inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)

logits = tf.layers.dense(inputs=dropout, units=10)

predictions = {
# Generate predictions (for PREDICT and EVAL mode)
"classes": tf.argmax(input=logits, axis=1),
# Add softmax_tensor to the graph. It is used for PREDICT and by the
# logging_hook.
"probabilities": tf.nn.softmax(logits, name="softmax_tensor")
}

if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)

# Calculate Loss (for both TRAIN and EVAL modes)
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)

# Configure the Training Op (for TRAIN mode)
if mode == tf.estimator.ModeKeys.TRAIN:
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)

# Add evaluation metrics (for EVAL mode)
eval_metric_ops = {
"accuracy after all": tf.metrics.accuracy(
labels=labels, predictions=predictions["classes"])}
return tf.estimator.EstimatorSpec(
mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)

def main(unused_argv):
model_path = "/tmp/mnist_convnet_model"

# Load training and eval data
train_data = mnist.train.images  # Returns np.array
train_labels = np.asarray(mnist.train.labels, dtype=np.int32)
eval_data = mnist.test.images  # Returns np.array
eval_labels = np.asarray(mnist.test.labels, dtype=np.int32)

# delete old checkpoint if needed
delete_checkpoint = True
import os
if (delete_checkpoint and os.path.isfile(model_path + '/checkpoint')):
os.remove(model_path + '/checkpoint')

# Create the Estimator
mnist_classifier = tf.estimator.Estimator(
model_fn=cnn_model_fn, model_dir=model_path)

# Set up logging for predictions
# Log the values in the "Softmax" tensor with label "probabilities"
tensors_to_log = {"probabilities": "softmax_tensor"}
logging_hook = tf.train.LoggingTensorHook(
tensors=tensors_to_log, every_n_iter=50)

# Train the model
train_input_fn = tf.compat.v1.estimator.inputs.numpy_input_fn(
x={"x": train_data},
y=train_labels,
batch_size=100,
num_epochs=None,
shuffle=True)
mnist_classifier.train(
input_fn=train_input_fn,
steps=5000,
hooks=[logging_hook])

# Evaluate the model and print results
eval_input_fn = tf.compat.v1.estimator.inputs.numpy_input_fn(
x={"x": eval_data}, y=eval_labels, num_epochs=1, shuffle=False)
eval_results = mnist_classifier.evaluate(input_fn=eval_input_fn)
print(eval_results)

if __name__ == "__main__":
tf.app.run()


• You are already using the softmax activation function on the logits. It will output the class probabilities ( since they sum up to 1 ) – Shubham Panchal Jun 4 at 14:53