The model can be used for identifying different galaxies from cutout images. It does not provide bounding boxes, so multiple galaxies in 1 image is not desired.

How to Get Started with the Model

Use the code below to get started with the model.

python

model = tf.keras.models.load_model('model.keras')
prediction = model.predict(image)
print(prediction)

Training Details

Training Data

From the kaggle zoo challenge the classes one_one(Spheroid) 80%> and one_two(Spiral) 90%> are used.

Furthermore are the image segmented for noice removal

Training Procedure

python

train_ds, val_ds = image_dataset_from_directory(
    dataset_directory,
    validation_split=0.2,
    subset="both",
    seed=123,
    image_size=(200, 200),
    batch_size=32,
    color_mode='grayscale'
)

data_augmentation = tf.keras.Sequential([
  tf.keras.layers.RandomFlip('horizontal'),
  tf.keras.layers.RandomRotation(0.2),
  tf.keras.layers.RandomZoom(0.2),
  tf.keras.layers.RandomContrast(0.2),
  tf.keras.layers.RandomBrightness(0.2),
  tf.keras.layers.GaussianNoise(0.1),
])

AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

model = tf.keras.Sequential([
    data_augmentation,
    tf.keras.layers.Rescaling(1./255, input_shape=(200, 200, 1)),
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dropout(0.5),
    tf.keras.layers.Dense(512, activation='relu'),
    tf.keras.layers.Dense(2, activation='softmax')
])

model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

Evaluation

Testing Data, Factors & Metrics

Model summary

text

┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ sequential (Sequential)         │ (None, 200, 200, 1)    │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ rescaling (Rescaling)           │ (None, 200, 200, 1)    │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv2d (Conv2D)                 │ (None, 198, 198, 64)   │           640 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ max_pooling2d (MaxPooling2D)    │ (None, 99, 99, 64)     │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv2d_1 (Conv2D)               │ (None, 97, 97, 128)    │        73,856 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ max_pooling2d_1 (MaxPooling2D)  │ (None, 48, 48, 128)    │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv2d_2 (Conv2D)               │ (None, 46, 46, 256)    │       295,168 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ max_pooling2d_2 (MaxPooling2D)  │ (None, 23, 23, 256)    │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv2d_3 (Conv2D)               │ (None, 21, 21, 256)    │       590,080 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ max_pooling2d_3 (MaxPooling2D)  │ (None, 10, 10, 256)    │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ flatten (Flatten)               │ (None, 25600)          │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 25600)          │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 1024)           │    26,215,424 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_1 (Dense)                 │ (None, 2)              │         2,050 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
Total params: 81,531,656 (311.02 MB)
Trainable params: 27,177,218 (103.67 MB)
Non-trainable params: 0 (0 MB)
Optimizer params 54,354,438 (207.35 MB)

Loss and Accuracy

Results

	precision	recall	f1-score	support
one_one	0.98	0.98	0.96	1637
one_two	0.98	0.98	0.98	1740
accuracy			0.96	3377
macro avg	0.98	0.98	0.98	3377
weighted avg	0.98	0.98	0.98	3377

Environmental Impact

Hardware Type: M3 Pro
Hours used: 72

IT-Guy007/AstroVisionV1

Model Card for Model ID

Model Details

Model Description

Model Sources

Uses