Probability is mismatching for the image classification example

[spadiyar67]

used same code what given in the below url ,
https://www.tensorflow.org/tutorials/images/classification

created the .tflite for Android and imported the tflite but while executing the code Probability is not matching with the python code.

Percentage in python is ,
This image most likely belongs to sunflowers with a 95.65 percent confidence.

The android code:
val model = Model.newInstance(this)
val bitmap: Bitmap =
BitmapFactory.decodeResource(resources, R.drawable.image)
// Creates inputs for reference.
val image = TensorImage.fromBitmap(bitmap)

// Runs model inference and gets result.
val outputs = model.process(image)
val probability = outputs.probabilityAsCategoryList

// Releases model resources if no longer used.
model.close()

    val outputsProbability = probability.apply {
        sortByDescending { it.score } // Sort with highest confidence first
    }.take(5)

    val items = mutableListOf<Recognition>()
    for (output in outputsProbability) {
        items.add(Recognition(output.label, output.score))
    }

    Log.d("propability", items.toString())

o/p:
D/propability: [dandelion / 554.4%, daisy / 61.7%, roses / -75.3%, tulips / -282.9%, sunflowers / -426.3%]

[tilakrayal]

@spadiyar67 ,

We see that the issue template has not been filled, could you please do so as it helps us analyse the issue [tf version, steps followed before you ran into this error] reported.

Thanks!

[spadiyar67]

@tilakrayal

System information

• Have I written custom code (as opposed to using a stock example script provided in TensorFlow):used the code as per the tensot flow link,
  https://www.tensorflow.org/tutorials/images/classification

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Mac

• Mobile device (e.g. iPhone 8, Pixel 2, Samsung Galaxy) if the issue happens on mobile device: Samsung Galaxy note 8

• TensorFlow installed from (source or binary):binary

• TensorFlow version (use command below):2.4.1

• Python version:3.8.2

• Bazel version (if compiling from source): not seeing bezel version from the command bazel --version

• GCC/Compiler version (if compiling from source): -

• CUDA/cuDNN version:-

• GPU model and memory: 500 GB

I have given python and android code below.
Steps:
Created tflite from the python code ->imported in Android studio->android code i have given below->the probability while running python and android code mismatching.

Python code:

import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf
import matplotlib.pyplot as plt

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
from tflite_support import flatbuffers
from tflite_support import metadata as _metadata
from tflite_support import metadata_schema_py_generated as _metadata_fb
from absl import flags
import imageio
import cv2
import numpy as np
import pathlib

batch_size = 32
img_height = 180
img_width = 180
data_dir = ".keras/datasets/flower_photos"

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="training",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)

class_names = train_ds.class_names
print(class_names)

for image_batch, labels_batch in train_ds:
print(image_batch.shape)
print(labels_batch.shape)
break

data_augmentation = keras.Sequential(
[
layers.experimental.preprocessing.RandomFlip("horizontal",
input_shape=(img_height,
img_width,
3)),
layers.experimental.preprocessing.RandomRotation(0.1),
layers.experimental.preprocessing.RandomZoom(0.1),
]
)
num_classes = 5
model = Sequential([
data_augmentation,
layers.experimental.preprocessing.Rescaling(1./255),
layers.Conv2D(16, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(64, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Dropout(0.2),
layers.Flatten(),
layers.Dense(128, activation='relu'),
layers.Dense(num_classes)
])

model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])

print(len(train_ds))
print(len(val_ds))

epochs = 15
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)
print(len(train_ds))
print(len(val_ds))

sunflower_url = "https://storage.googleapis.com/download.tensorflow.org/example_images/592px-Red_sunflower.jpg"
sunflower_path = tf.keras.utils.get_file('Red_sunflower', origin=sunflower_url)

img = keras.preprocessing.image.load_img(
sunflower_path, target_size=(img_height, img_width)
)
img_array = keras.preprocessing.image.img_to_array(img)
img_array = tf.expand_dims(img_array, 0) # Create a batch

predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])

print(
"This image most likely belongs to {} with a {:.2f} percent confidence."
.format(class_names[np.argmax(score)], 100 * np.max(score))
)

Convert the model.

converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()

Save the model.

with open('model.tflite', 'wb') as f:
f.write(tflite_model)

""" ... """
"""Creates the metadata for an image classifier."""

Creates model info.

model_meta = _metadata_fb.ModelMetadataT()
model_meta.name = "MobileNetV1 image classifier"
model_meta.description = ("Identify the most prominent object in the "
"image from a set of 1,001 categories such as "
"trees, animals, food, vehicles, person etc.")
model_meta.version = "v1"
model_meta.author = "TensorFlow"
model_meta.license = ("Apache License. Version 2.0 "
"http://www.apache.org/licenses/LICENSE-2.0.")

Creates input info.

input_meta = _metadata_fb.TensorMetadataT()

Creates output info.

output_meta = _metadata_fb.TensorMetadataT()

input_meta.name = "image"
input_meta.description = (
"Input image to be classified. The expected image is {0} x {1}, with "
"three channels (red, blue, and green) per pixel. Each value in the "
"tensor is a single byte between 0 and 255.".format(160, 160))
input_meta.content = _metadata_fb.ContentT()
input_meta.content.contentProperties = _metadata_fb.ImagePropertiesT()
input_meta.content.contentProperties.colorSpace = (
_metadata_fb.ColorSpaceType.RGB)
input_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.ImageProperties)
input_normalization = _metadata_fb.ProcessUnitT()
input_normalization.optionsType = (
_metadata_fb.ProcessUnitOptions.NormalizationOptions)
input_normalization.options = _metadata_fb.NormalizationOptionsT()
input_normalization.options.mean = [127.5]
input_normalization.options.std = [127.5]
input_meta.processUnits = [input_normalization]
input_stats = _metadata_fb.StatsT()
input_stats.max = [255]
input_stats.min = [0]
input_meta.stats = input_stats

Creates output info.

output_meta = _metadata_fb.TensorMetadataT()
output_meta.name = "probability"
output_meta.description = "Probabilities of the 1001 labels respectively."
output_meta.content = _metadata_fb.ContentT()
output_meta.content.content_properties = _metadata_fb.FeaturePropertiesT()
output_meta.content.contentPropertiesType = (
_metadata_fb.ContentProperties.FeatureProperties)
output_stats = _metadata_fb.StatsT()
output_stats.max = [1.0]
output_stats.min = [0.0]
output_meta.stats = output_stats
label_file = _metadata_fb.AssociatedFileT()
label_file.name = os.path.basename("/MachineLearning/TensorFlow/Label.txt")
label_file.description = "Labels for objects that the model can recognize."
label_file.type = _metadata_fb.AssociatedFileType.TENSOR_AXIS_LABELS
output_meta.associatedFiles = [label_file]

Creates subgraph info.

subgraph = _metadata_fb.SubGraphMetadataT()
subgraph.inputTensorMetadata = [input_meta]
subgraph.outputTensorMetadata = [output_meta]
model_meta.subgraphMetadata = [subgraph]

b = flatbuffers.Builder(0)
b.Finish(
model_meta.Pack(b),
_metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER)
metadata_buf = b.Output()

populator = _metadata.MetadataPopulator.with_model_file("model.tflite")
populator.load_metadata_buffer(metadata_buf)
populator.load_associated_files(["/MachineLearning/TensorFlow/Label.txt"])
populator.populate()

Android Code:

val model = Model.newInstance(this)
val bitmap: Bitmap =
BitmapFactory.decodeResource(resources, R.drawable.image)
// Creates inputs for reference.
val image = TensorImage.fromBitmap(bitmap)

// Runs model inference and gets result.
val outputs = model.process(image)
val probability = outputs.probabilityAsCategoryList

// Releases model resources if no longer used.
model.close()

val outputsProbability = probability.apply {
sortByDescending { it.score } // Sort with highest confidence first
}.take(5)

val items = mutableListOf<Recognition>()
for (output in outputsProbability) {
    items.add(Recognition(output.label, output.score))
}

Log.d("propability", items.toString())

[tilakrayal]

@spadiyar67 ,

On executing the given code, I am facing an error. Please find the gist of it here and share all dependencies to replicate the issue or share a colab gist with the reported error.

Thanks!

[spadiyar67]

@tilakrayal
I have uploaded all the necessary files and now able to create the tflite file in the colab . could you please give a try and check the probability in both the platform.

If you see same error then create "Label.txt" file and add below labels inside the file .
daisy
dandelion
roses
sunflowers
tulips

you can use the below link also for the Label.txt file,
https://drive.google.com/file/d/1IsuPh1VNFKWow1CHpyovnsWNfvhkzy44/view?usp=sharing

[tilakrayal]

@spadiyar67 ,

The code provided is fairly complex and indentation errors hence it would be difficult for us to pinpoint the issue. Could you please get the example down to the simplest possible repro? Please share the colab link.That will allow us to determine the source of the issue easily. Thanks!

[google-ml-butler]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you.

[google-ml-butler]

Closing as stale. Please reopen if you'd like to work on this further.