First model version

.gitattributes

@@ -17,7 +17,7 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
+tuner_model/**/* filter=lfs diff=lfs merge=lfs -text 
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,244 @@
+
+# Created by https://www.toptal.com/developers/gitignore/api/python,virtualenv,linux,windows,macos,git
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,virtualenv,linux,windows,macos,git
+
+### Git ###
+# Created by git for backups. To disable backups in Git:
+# $ git config --global mergetool.keepBackup false
+*.orig
+
+# Created by git when using merge tools for conflicts
+*.BACKUP.*
+*.BASE.*
+*.LOCAL.*
+*.REMOTE.*
+*_BACKUP_*.txt
+*_BASE_*.txt
+*_LOCAL_*.txt
+*_REMOTE_*.txt
+
+### Linux ###
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+### VirtualEnv ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+pip-selfcheck.json
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# End of https://www.toptal.com/developers/gitignore/api/python,virtualenv,linux,windows,macos,git
+
+data

inference.py

@@ -0,0 +1,26 @@
+import tensorflow as tf
+from keras_tuner import HyperParameters
+from src.models import MakeHyperModel
+from src.preprocessing import get_data_augmentation
+from src.config import IMAGE_SIZE
+
+data_augmentation = get_data_augmentation()
+
+img = tf.keras.preprocessing.image.load_img(
+    "examples/cat2.jpg", target_size=IMAGE_SIZE
+)
+img_array = tf.keras.preprocessing.image.img_to_array(img)
+img_array = tf.expand_dims(img_array, 0)
+
+latest = tf.train.latest_checkpoint('./tuner_model/cat-vs-dog/trial_0484d8d758a5ef7b91ca97d334ba7870/checkpoints/epoch_0')
+hypermodel = MakeHyperModel(input_shape=IMAGE_SIZE + (3,), num_classes=2, data_augmentation=data_augmentation)
+model = hypermodel.build(hp=HyperParameters())
+model.load_weights(latest).expect_partial()
+
+
+predictions = model.predict(img_array)
+score = predictions[0]
+print(
+    "This image is %.2f percent cat and %.2f percent dog."
+    % (100 * (1 - score), 100 * score)
+)

requirements.txt

@@ -0,0 +1,6 @@
+tensorflow==2.6.0
+keras-tuner==1.0.4
+matplotlib==3.4.3
+pydot==1.4.2
+pandas==1.3.4
+gradio==2.4.5

server.py

@@ -0,0 +1,37 @@
+import gradio as gr
+import tensorflow as tf
+from keras_tuner import HyperParameters
+from src.models import MakeHyperModel
+from src.preprocessing import get_data_augmentation
+
+from src.config import IMAGE_SIZE
+
+data_augmentation = get_data_augmentation()
+
+latest = tf.train.latest_checkpoint('./tuner_model/cat-vs-dog/trial_0484d8d758a5ef7b91ca97d334ba7870/checkpoints/epoch_0')
+hypermodel = MakeHyperModel(input_shape=IMAGE_SIZE + (3,), num_classes=2, data_augmentation=data_augmentation)
+model = hypermodel.build(hp=HyperParameters())
+model.load_weights(latest).expect_partial()
+
+def cat_vs_dog(image):
+    img_array = tf.constant(image, dtype=tf.float32)
+    img_array = tf.expand_dims(img_array, 0)
+    predictions = model.predict(img_array)
+    score = predictions[0]
+    return {'cat': float((1 - score)), 'dog': float(score)}
+
+iface = gr.Interface(
+    cat_vs_dog, 
+    gr.inputs.Image(shape=IMAGE_SIZE), 
+    gr.outputs.Label(num_top_classes=2),
+    capture_session=True,
+    interpretation="default",
+    examples=[
+        ["examples/cat1.jpg"],
+        ["examples/cat2.jpg"],
+        ["examples/dog1.jpeg"],
+        ["examples/dog2.jpeg"]
+    ])
+
+if __name__ == "__main__":
+    iface.launch()

src/config.py

@@ -0,0 +1,15 @@
+import os
+
+DATASET_URL = 'https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip'
+
+CACHE_DIR = os.getcwd()
+CACHE_SUBDIR = 'data'
+
+if not os.path.isdir(CACHE_SUBDIR):
+    os.mkdir(CACHE_SUBDIR)
+
+DATASET_PATH = os.path.join(CACHE_DIR, CACHE_SUBDIR, 'PetImages')
+
+IMAGE_SIZE = (180, 180)
+BATCH_SIZE = 32
+EPOCHS = 50

src/draw.py

@@ -0,0 +1,21 @@
+from typing import Optional
+
+import tensorflow as tf
+import matplotlib.pyplot as plt
+
+
+def visualize_data(dataset: tf.data.Dataset, data_augmentation: Optional[tf.keras.Sequential]=None) -> None:
+    plt.figure(figsize=(10, 10))
+    for images, labels in dataset.take(1):
+        for i in range(9):
+            _ = plt.subplot(3, 3, i + 1)
+            
+            if data_augmentation != None:
+                augmented_image = data_augmentation(images)
+                plt.imshow(augmented_image[0].numpy().astype('uint8'))
+            else:
+                plt.imshow(images[i].numpy().astype('uint8'))
+            
+            plt.title(int(labels[i]))
+            plt.axis('off')
+    plt.show()

src/models.py

@@ -0,0 +1,77 @@
+from typing import Tuple
+from typing import Optional
+
+import tensorflow as tf
+from tensorflow.keras import layers
+from keras_tuner import HyperModel
+
+class MakeHyperModel(HyperModel):
+    def __init__(self, input_shape: Tuple[int, int, int], num_classes: int, data_augmentation: Optional[tf.keras.Sequential] = None) -> None:
+        self.input_shape = input_shape
+        self.num_classes = num_classes
+        self.data_augmentation = data_augmentation
+    
+    def build(self, hp) -> tf.keras.Model:
+        inputs = tf.keras.Input(shape=self.input_shape)
+        
+        if self.data_augmentation != None:
+            x = self.data_augmentation(inputs)
+        else:
+            x = inputs
+        
+        x = layers.Rescaling(1.0/255)(x)
+        x = layers.Conv2D(32, 3, strides=2, padding='same')(x)
+        x = layers.BatchNormalization()(x)
+        x = layers.Activation('relu')(x)
+        
+        x = layers.Conv2D(64, 3,  padding='same')(x)
+        x = layers.BatchNormalization()(x)
+        x = layers.Activation('relu')(x)
+        
+        previous_block_activation = x
+        
+        for size in [128, 256, 512, 728]:
+            x = layers.Activation('relu')(x)
+            x = layers.SeparableConv2D(size, 3, padding='same')(x)
+            x = layers.BatchNormalization()(x)
+            
+            x = layers.Activation("relu")(x)
+            x = layers.SeparableConv2D(size, 3, padding='same')(x)
+            x = layers.BatchNormalization()(x)
+            
+            x = layers.MaxPooling2D(3, strides=2, padding='same')(x)
+            
+            residual = layers.Conv2D(size, 1, strides=2, padding='same')(previous_block_activation)
+            
+            x = layers.add([x, residual])
+            previous_block_activation = x
+        
+        x = layers.SeparableConv2D(1024, 3, padding='same')(x)
+        x = layers.BatchNormalization()(x)
+        x = layers.Activation('relu')(x)
+        
+        x = layers.GlobalAveragePooling2D()(x)
+        
+        if self.num_classes == 2:
+            activation = 'sigmoid'
+            loss_fn = 'binary_crossentropy'
+            units = 1
+        else:
+            activation = 'softmax'
+            loss_fn = 'categorical_crossentropy'
+            units = self.num_classes
+        
+        x = layers.Dropout(0.5)(x)
+        outputs = layers.Dense(units, activation=activation)(x)
+        
+        model = tf.keras.Model(inputs, outputs)
+        
+        model.compile(
+            optimizer=tf.keras.optimizers.Adam(
+                hp.Choice("learning_rate", values=[1e-2, 1e-3, 1e-4])
+            ),
+            loss=loss_fn,
+            metrics=['accuracy']
+        )
+        
+        return model

src/preprocessing.py

@@ -0,0 +1,29 @@
+import os
+from typing import Tuple
+
+import tensorflow as tf
+
+def delete_corrupted_image(dataset_path: str, categories: Tuple[str]) -> int:
+    num_skipped = 0
+    
+    for folder_name in categories:
+        folder_path = os.path.join(dataset_path, folder_name)
+        for fname in os.listdir(folder_path):
+            fpath = os.path.join(folder_path, fname)
+            try:
+                fobj = open(fpath, 'rb')
+                is_jfif = tf.compat.as_bytes("JFIF") in fobj.peek(10)
+            finally:
+                fobj.close()
+
+            if not is_jfif:
+                num_skipped += 1
+                os.remove(fpath)
+            
+    return num_skipped
+
+def get_data_augmentation() -> tf.keras.Sequential:
+    return tf.keras.Sequential([
+        tf.keras.layers.RandomFlip('horizontal'),
+        tf.keras.layers.RandomRotation(0.1)
+    ])

train.py

@@ -0,0 +1,62 @@
+from tensorflow.keras.utils import get_file
+import tensorflow as tf
+from keras_tuner import RandomSearch
+from keras_tuner import Objective
+
+from src.preprocessing import delete_corrupted_image
+from src.draw import visualize_data
+from src.preprocessing import get_data_augmentation
+from src.models import MakeHyperModel
+
+from src.config import DATASET_URL
+from src.config import CACHE_DIR
+from src.config import CACHE_SUBDIR
+from src.config import DATASET_PATH
+from src.config import IMAGE_SIZE
+from src.config import BATCH_SIZE
+from src.config import EPOCHS
+
+get_file(origin=DATASET_URL, extract=True, cache_dir=CACHE_DIR, cache_subdir=CACHE_SUBDIR)
+print(delete_corrupted_image(DATASET_PATH, ('Cat', 'Dog')))
+
+train_ds = tf.keras.preprocessing.image_dataset_from_directory(
+    DATASET_PATH,
+    validation_split=0.2,
+    subset='training',
+    seed=1337,
+    image_size=IMAGE_SIZE,
+    batch_size=BATCH_SIZE
+)
+
+val_ds = tf.keras.preprocessing.image_dataset_from_directory(
+    DATASET_PATH,
+    validation_split=0.2,
+    subset='validation',
+    seed=1337,
+    image_size=IMAGE_SIZE,
+    batch_size=BATCH_SIZE
+)
+
+train_ds = train_ds.prefetch(buffer_size=BATCH_SIZE)
+val_ds = val_ds.prefetch(buffer_size=BATCH_SIZE)
+
+data_augmentation = get_data_augmentation()
+
+visualize_data(train_ds, data_augmentation=data_augmentation)
+
+hypermodel = MakeHyperModel(input_shape=IMAGE_SIZE + (3,), num_classes=2, data_augmentation=data_augmentation)
+tuner = RandomSearch(
+    hypermodel,
+    objective=Objective("val_accuracy", direction="max"),
+    max_trials=3,
+    executions_per_trial=2,
+    overwrite=True,
+    directory='tuner_model',
+    project_name='cat-vs-dog'
+)
+
+tuner.search_space_summary()
+
+tuner.search(train_ds, epochs=EPOCHS, validation_data=val_ds)
+
+tuner.get_best_hyperparameters()

tuner_model/cat-vs-dog/oracle.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c510f2e84cb8c3a174dc13dc711552e795b4ffcd4d471c089c35b24d5ac740
+size 397

tuner_model/cat-vs-dog/trial_0484d8d758a5ef7b91ca97d334ba7870/checkpoints/epoch_0/checkpoint

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02988027faf3f16b4088ee83c2ade14098e8ffb325c23a576cc639dae48aa936
+size 77

tuner_model/cat-vs-dog/trial_0484d8d758a5ef7b91ca97d334ba7870/checkpoints/epoch_0/checkpoint.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de31100bc5b28acb3fd12d6dee73ceb96ef500f28182f8d9c38b1fa4010ee607
+size 33354255

tuner_model/cat-vs-dog/trial_0484d8d758a5ef7b91ca97d334ba7870/checkpoints/epoch_0/checkpoint.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1d98098058e8affa700b53eddef713ad9972bbd8e402c4790abcce74020e40
+size 15366

tuner_model/cat-vs-dog/trial_0484d8d758a5ef7b91ca97d334ba7870/trial.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baba34ec678fb7cc21b79b825ec6860dd6005acfaf2fc2d0b1b408a918bf8264
+size 739

tuner_model/cat-vs-dog/trial_7d8a24b4163e3b3211079dbc5be02dac/checkpoints/epoch_0/checkpoint

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02988027faf3f16b4088ee83c2ade14098e8ffb325c23a576cc639dae48aa936
+size 77

tuner_model/cat-vs-dog/trial_7d8a24b4163e3b3211079dbc5be02dac/checkpoints/epoch_0/checkpoint.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a05b0504c5858cbeb7d2ea62da18609806d4a401a548f4279569b0fced62bff
+size 33354255

tuner_model/cat-vs-dog/trial_7d8a24b4163e3b3211079dbc5be02dac/checkpoints/epoch_0/checkpoint.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d987efbc7b9c1ef4e26b0dd054afeb5a2b1c93450bd3904d1301ab51b8d91ec2
+size 15366

tuner_model/cat-vs-dog/trial_7d8a24b4163e3b3211079dbc5be02dac/trial.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb6aaf581a6dd09cb4343a00792274e425f7cc666c2213839a16ae36cf47673
+size 738

tuner_model/cat-vs-dog/trial_ee38b0cfcac1da6bbf8baa912585407e/checkpoints/epoch_0/checkpoint

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02988027faf3f16b4088ee83c2ade14098e8ffb325c23a576cc639dae48aa936
+size 77

tuner_model/cat-vs-dog/trial_ee38b0cfcac1da6bbf8baa912585407e/checkpoints/epoch_0/checkpoint.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8583811f52f9fe6579853e104a56031c8692e11c2fe3b3fe913453f63634287f
+size 33354255

tuner_model/cat-vs-dog/trial_ee38b0cfcac1da6bbf8baa912585407e/checkpoints/epoch_0/checkpoint.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca0876c4482e218982c25ab694ed94901bc7d2e9278719a1f5714cb6eb6523e9
+size 15366

tuner_model/cat-vs-dog/trial_ee38b0cfcac1da6bbf8baa912585407e/trial.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a35ec123a58b1af226a01c82051049340f712d85cda8fc6f595449598c2e87
+size 743

tuner_model/cat-vs-dog/tuner0.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a
+size 2