Code for Satellite Image Classification using TensorFlow in Python Tutorial

satellite_image_classification.py

# -*- coding: utf-8 -*-
"""Satellite-Image-Classification-with-TensorFlow_PythonCode.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1SVpaW9HSebpHNYf6LXTm7elnHOSdQA5i
"""

!pip install tensorflow tensorflow_addons tensorflow_datasets tensorflow_hub numpy matplotlib seaborn

import os

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import tensorflow as tf
import tensorflow_datasets as tfds
import tensorflow_hub as hub
import tensorflow_addons as tfa

# load the whole dataset, for data info
all_ds   = tfds.load("eurosat", with_info=True)
# load training, testing & validation sets, splitting by 60%, 20% and 20% respectively
train_ds = tfds.load("eurosat", split="train[:60%]")
test_ds  = tfds.load("eurosat", split="train[60%:80%]")
valid_ds = tfds.load("eurosat", split="train[80%:]")

# the class names
class_names = all_ds[1].features["label"].names
# total number of classes (10)
num_classes = len(class_names)
num_examples = all_ds[1].splits["train"].num_examples

# make a plot for number of samples on each class
fig, ax = plt.subplots(1, 1, figsize=(14,10))
labels, counts = np.unique(np.fromiter(all_ds[0]["train"].map(lambda x: x["label"]), np.int32), 
                       return_counts=True)

plt.ylabel('Counts')
plt.xlabel('Labels')
sns.barplot(x = [class_names[l] for l in labels], y = counts, ax=ax) 
for i, x_ in enumerate(labels):
  ax.text(x_-0.2, counts[i]+5, counts[i])
# set the title
ax.set_title("Bar Plot showing Number of Samples on Each Class")
# save the image
# plt.savefig("class_samples.png")

def prepare_for_training(ds, cache=True, batch_size=64, shuffle_buffer_size=1000):
  if cache:
    if isinstance(cache, str):
      ds = ds.cache(cache)
    else:
      ds = ds.cache()
  ds = ds.map(lambda d: (d["image"], tf.one_hot(d["label"], num_classes)))
  # shuffle the dataset
  ds = ds.shuffle(buffer_size=shuffle_buffer_size)
  # Repeat forever
  ds = ds.repeat()
  # split to batches
  ds = ds.batch(batch_size)
  # `prefetch` lets the dataset fetch batches in the background while the model
  # is training.
  ds = ds.prefetch(buffer_size=tf.data.experimental.AUTOTUNE)
  return ds

batch_size = 64

# preprocess training & validation sets
train_ds = prepare_for_training(train_ds, batch_size=batch_size)
valid_ds = prepare_for_training(valid_ds, batch_size=batch_size)

# validating shapes
for el in valid_ds.take(1):
  print(el[0].shape, el[1].shape)
for el in train_ds.take(1):
  print(el[0].shape, el[1].shape)

# take the first batch of the training set
batch = next(iter(train_ds))

def show_batch(batch):
  plt.figure(figsize=(16, 16))
  for n in range(min(32, batch_size)):
      ax = plt.subplot(batch_size//8, 8, n + 1)
      # show the image
      plt.imshow(batch[0][n])
      # and put the corresponding label as title upper to the image
      plt.title(class_names[tf.argmax(batch[1][n].numpy())])
      plt.axis('off')
      plt.savefig("sample-images.png")

# showing a batch of images along with labels
show_batch(batch)

model_url = "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_l/feature_vector/2"

# download & load the layer as a feature vector
keras_layer = hub.KerasLayer(model_url, output_shape=[1280], trainable=True)

m = tf.keras.Sequential([
  keras_layer,
  tf.keras.layers.Dense(num_classes, activation="softmax")
])
# build the model with input image shape as (64, 64, 3)
m.build([None, 64, 64, 3])
m.compile(
    loss="categorical_crossentropy", 
    optimizer="adam", 
    metrics=["accuracy", tfa.metrics.F1Score(num_classes)]
)

m.summary()

model_name = "satellite-classification"
model_path = os.path.join("results", model_name + ".h5")
model_checkpoint = tf.keras.callbacks.ModelCheckpoint(model_path, save_best_only=True, verbose=1)

n_training_steps   = int(num_examples * 0.6) // batch_size
n_validation_steps = int(num_examples * 0.2) // batch_size

history = m.fit(
    train_ds, validation_data=valid_ds,
    steps_per_epoch=n_training_steps,
    validation_steps=n_validation_steps,
    verbose=1, epochs=5, 
    callbacks=[model_checkpoint]
)

# number of testing steps
n_testing_steps = int(all_ds[1].splits["train"].num_examples * 0.2)

m.load_weights(model_path)

# get all testing images as NumPy array
images = np.array([ d["image"] for d in test_ds.take(n_testing_steps) ])
print("images.shape:", images.shape)

# get all testing labels as NumPy array
labels = np.array([ d["label"] for d in test_ds.take(n_testing_steps) ])
print("labels.shape:", labels.shape)

# feed the images to get predictions
predictions = m.predict(images)
# perform argmax to get class index
predictions = np.argmax(predictions, axis=1)
print("predictions.shape:", predictions.shape)

from sklearn.metrics import f1_score

accuracy = tf.keras.metrics.Accuracy()
accuracy.update_state(labels, predictions)
print("Accuracy:", accuracy.result().numpy())
print("F1 Score:", f1_score(labels, predictions, average="macro"))

# compute the confusion matrix
cmn = tf.math.confusion_matrix(labels, predictions).numpy()
# normalize the matrix to be in percentages
cmn = cmn.astype('float') / cmn.sum(axis=0)[:, np.newaxis]
# make a plot for the confusion matrix
fig, ax = plt.subplots(figsize=(10,10))
sns.heatmap(cmn, annot=True, fmt='.2f', 
            xticklabels=[f"pred_{c}" for c in class_names], 
            yticklabels=[f"true_{c}" for c in class_names],
            # cmap="Blues"
            cmap="rocket_r"
            )
plt.ylabel('Actual')
plt.xlabel('Predicted')
# plot the resulting confusion matrix
plt.savefig("confusion-matrix.png")
# plt.show()

def show_predicted_samples():
  plt.figure(figsize=(14, 14))
  for n in range(64):
      ax = plt.subplot(8, 8, n + 1)
      # show the image
      plt.imshow(images[n])
      # and put the corresponding label as title upper to the image
      if predictions[n] == labels[n]:
        # correct prediction
        ax.set_title(class_names[predictions[n]], color="green")
      else:
        # wrong prediction
        ax.set_title(f"{class_names[predictions[n]]}/T:{class_names[labels[n]]}", color="red")
      plt.axis('off')
      plt.savefig("predicted-sample-images.png")

# showing a batch of images along with predictions labels
show_predicted_samples()