All

.gitignore

@@ -5,3 +5,6 @@ saved_models/weights.best.from_scratch.hdf5
 saved_models/weights.best.vgg16.hdf5
 .ipynb_checkpoints/
 bottleneck_features/DogVGG16Data.npz
+*.h5
+*.tflite
+

check_images.py

@@ -0,0 +1,21 @@
+from struct import unpack
+from tqdm import tqdm
+import os
+import glob
+
+fileList = glob.glob('./dogImages/*/*/*.*')
+
+import tensorflow.compat.v1 as tf
+tf.disable_v2_behavior()
+
+for i, image_name in enumerate(fileList):
+    print(i, image_name)
+
+    with tf.Graph().as_default():
+        image_contents = tf.read_file(image_name)
+        image = tf.image.decode_jpeg(image_contents, channels=3)
+        #
+        with tf.Session() as sess:
+            #sess.run(init_op)
+            sess.run(tf.global_variables_initializer())
+            tmp = sess.run(image)

extract_bottleneck_features.py

@@ -7,7 +7,7 @@ def extract_VGG19(tensor):
 	return VGG19(weights='imagenet', include_top=False).predict(preprocess_input(tensor))
 
 def extract_Resnet50(tensor):
-	from keras.applications.resnet50 import ResNet50, preprocess_input
+	from keras.applications.resnet import ResNet50, preprocess_input
 	return ResNet50(weights='imagenet', include_top=False).predict(preprocess_input(tensor))
 
 def extract_Xception(tensor):

requirements.txt

@@ -0,0 +1,101 @@
+absl-py==0.15.0
+argon2-cffi==21.3.0
+argon2-cffi-bindings==21.2.0
+astunparse==1.6.3
+attrs==21.4.0
+backcall==0.2.0
+bleach==4.1.0
+cachetools==4.2.4
+certifi==2020.6.20
+cffi==1.15.0
+charset-normalizer==2.0.10
+colorama==0.4.4
+cycler==0.11.0
+debugpy==1.5.1
+decorator==5.1.0
+defusedxml==0.7.1
+entrypoints==0.3
+flatbuffers==1.12
+fonttools==4.28.5
+gast==0.3.3
+google-auth==2.3.3
+google-auth-oauthlib==0.4.6
+google-pasta==0.2.0
+grpcio==1.32.0
+h5py==2.10.0
+idna==3.3
+importlib-metadata==4.10.0
+importlib-resources==5.4.0
+ipykernel==6.6.1
+ipython==7.31.0
+ipython-genutils==0.2.0
+jedi==0.18.1
+Jinja2==3.0.3
+joblib==1.1.0
+jsonschema==4.3.3
+jupyter-client==7.1.0
+jupyter-core==4.9.1
+jupyterlab-pygments==0.1.2
+Keras-Preprocessing==1.1.2
+kiwisolver==1.3.2
+Markdown==3.3.6
+MarkupSafe==2.0.1
+matplotlib==3.5.1
+matplotlib-inline==0.1.3
+mistune==0.8.4
+nbclient==0.5.9
+nbconvert==6.4.0
+nbformat==5.1.3
+nest-asyncio==1.5.4
+notebook==6.4.6
+numpy==1.19.5
+oauthlib==3.1.1
+opt-einsum==3.3.0
+packaging==21.3
+pandas==1.3.5
+pandocfilters==1.5.0
+parso==0.8.3
+pickleshare==0.7.5
+Pillow==9.0.0
+prometheus-client==0.12.0
+prompt-toolkit==3.0.24
+protobuf==3.19.1
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pycparser==2.21
+Pygments==2.11.2
+pyparsing==3.0.6
+pyrsistent==0.18.0
+python-dateutil==2.8.2
+pytz==2021.3
+pywin32==303
+pywinpty==1.1.6
+pyzmq==22.3.0
+requests==2.27.1
+requests-oauthlib==1.3.0
+rsa==4.8
+scikit-learn==1.0.2
+scipy==1.7.3
+Send2Trash==1.8.0
+six==1.15.0
+sklearn==0.0
+tensorboard==2.7.0
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorflow-estimator==2.4.0
+tensorflow-gpu==2.4.0
+termcolor==1.1.0
+terminado==0.12.1
+testpath==0.5.0
+threadpoolctl==3.0.0
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.1.1
+typing-extensions==3.7.4.3
+urllib3==1.26.7
+wcwidth==0.2.5
+webencodings==0.5.1
+Werkzeug==2.0.2
+wincertstore==0.2
+wrapt==1.12.1
+zipp==3.7.0

saved_models/convert.py

@@ -0,0 +1,15 @@
+from keras.models import load_model
+import tensorflow as tf
+
+model = load_model("catdog.h5")
+
+
+converter = tf.lite.TFLiteConverter.from_keras_model(model)
+tflite_model = converter.convert()
+
+print("model converted")
+
+# Save the model.
+with open('model.tflite', 'wb') as f:
+  f.write(tflite_model)
+

saved_models/inf.py

@@ -0,0 +1,30 @@
+import numpy as np
+import tensorflow as tf
+import cv2
+
+img = cv2.imread("dog.jpeg")
+img = cv2.resize(img, (128,128))
+img = np.array(img, dtype="float32")
+img = np.reshape(img, (1,128,128,3))
+
+
+# Load the TFLite model and allocate tensors.
+interpreter = tf.lite.Interpreter(model_path="model.tflite")
+interpreter.allocate_tensors()
+
+# Get input and output tensors.
+input_details = interpreter.get_input_details()
+output_details = interpreter.get_output_details()
+
+# Test the model on random input data.
+input_shape = input_details[0]['shape']
+
+print("*"*50, input_details)
+interpreter.set_tensor(input_details[0]['index'], img)
+
+interpreter.invoke()
+
+# The function `get_tensor()` returns a copy of the tensor data.
+# Use `tensor()` in order to get a pointer to the tensor.
+output_data = interpreter.get_tensor(output_details[0]['index'])
+print(output_data)