Migrate 3D_image_classification tutorial to Keras(all backends) (#1723)

* Convert 3D_image_classification to Keras3(all backend)

* Updated last_modified date

* Generated .md and .ipyng files

* added generated files

examples/vision/3D_image_classification.py

@@ -2,7 +2,7 @@
 Title: 3D image classification from CT scans
 Author: [Hasib Zunair](https://twitter.com/hasibzunair)
 Date created: 2020/09/23
-Last modified: 2020/09/23
+Last modified: 2024/01/11
 Description: Train a 3D convolutional neural network to predict presence of pneumonia.
 Accelerator: GPU
 """
@@ -17,9 +17,9 @@
 
 ## References
 
-- [A survey on Deep Learning Advances on Different 3D DataRepresentations](https://arxiv.org/pdf/1808.01462.pdf)
+- [A survey on Deep Learning Advances on Different 3D DataRepresentations](https://arxiv.org/abs/1808.01462)
 - [VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition](https://www.ri.cmu.edu/pub_files/2015/9/voxnet_maturana_scherer_iros15.pdf)
-- [FusionNet: 3D Object Classification Using MultipleData Representations](http://3ddl.cs.princeton.edu/2016/papers/Hegde_Zadeh.pdf)
+- [FusionNet: 3D Object Classification Using MultipleData Representations](https://arxiv.org/abs/1607.05695)
 - [Uniformizing Techniques to Process CT scans with 3D CNNs for Tuberculosis Prediction](https://arxiv.org/abs/2007.13224)
 """
 """
@@ -29,10 +29,10 @@
 import os
 import zipfile
 import numpy as np
-import tensorflow as tf
+import tensorflow as tf  # for data preprocessing
 
-from tensorflow import keras
-from tensorflow.keras import layers
+import keras
+from keras import layers
 
 """
 ## Downloading the MosMedData: Chest CT Scans with COVID-19 Related Findings
@@ -211,7 +211,6 @@ def process_scan(path):
 from scipy import ndimage
 
 
-@tf.function
 def rotate(volume):
     """Rotate the volume by a few degrees"""
 
@@ -375,11 +374,12 @@ def get_model(width=128, height=128, depth=64):
     loss="binary_crossentropy",
     optimizer=keras.optimizers.Adam(learning_rate=lr_schedule),
     metrics=["acc"],
+    run_eagerly=True,
 )
 
 # Define callbacks.
 checkpoint_cb = keras.callbacks.ModelCheckpoint(
-    "3d_image_classification.h5", save_best_only=True
+    "3d_image_classification.keras", save_best_only=True
 )
 early_stopping_cb = keras.callbacks.EarlyStopping(monitor="val_acc", patience=15)
 
@@ -426,7 +426,7 @@ def get_model(width=128, height=128, depth=64):
 """
 
 # Load best weights.
-model.load_weights("3d_image_classification.h5")
+model.load_weights("3d_image_classification.keras")
 prediction = model.predict(np.expand_dims(x_val[0], axis=0))[0]
 scores = [1 - prediction[0], prediction[0]]
 

examples/vision/ipynb/3D_image_classification.ipynb

@@ -10,7 +10,7 @@
     "\n",
     "**Author:** [Hasib Zunair](https://twitter.com/hasibzunair)<br>\n",
     "**Date created:** 2020/09/23<br>\n",
-    "**Last modified:** 2020/09/23<br>\n",
+    "**Last modified:** 2024/01/11<br>\n",
     "**Description:** Train a 3D convolutional neural network to predict presence of pneumonia."
    ]
   },
@@ -30,9 +30,9 @@
     "\n",
     "## References\n",
     "\n",
-    "- [A survey on Deep Learning Advances on Different 3D DataRepresentations](https://arxiv.org/pdf/1808.01462.pdf)\n",
+    "- [A survey on Deep Learning Advances on Different 3D DataRepresentations](https://arxiv.org/abs/1808.01462)\n",
     "- [VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition](https://www.ri.cmu.edu/pub_files/2015/9/voxnet_maturana_scherer_iros15.pdf)\n",
-    "- [FusionNet: 3D Object Classification Using MultipleData Representations](http://3ddl.cs.princeton.edu/2016/papers/Hegde_Zadeh.pdf)\n",
+    "- [FusionNet: 3D Object Classification Using MultipleData Representations](https://arxiv.org/abs/1607.05695)\n",
     "- [Uniformizing Techniques to Process CT scans with 3D CNNs for Tuberculosis Prediction](https://arxiv.org/abs/2007.13224)"
    ]
   },
@@ -56,10 +56,10 @@
     "import os\n",
     "import zipfile\n",
     "import numpy as np\n",
-    "import tensorflow as tf\n",
+    "import tensorflow as tf  # for data preprocessing\n",
     "\n",
-    "from tensorflow import keras\n",
-    "from tensorflow.keras import layers"
+    "import keras\n",
+    "from keras import layers"
    ]
   },
   {
@@ -308,7 +308,6 @@
     "from scipy import ndimage\n",
     "\n",
     "\n",
-    "@tf.function\n",
     "def rotate(volume):\n",
     "    \"\"\"Rotate the volume by a few degrees\"\"\"\n",
     "\n",
@@ -542,11 +541,12 @@
     "    loss=\"binary_crossentropy\",\n",
     "    optimizer=keras.optimizers.Adam(learning_rate=lr_schedule),\n",
     "    metrics=[\"acc\"],\n",
+    "    run_eagerly=True,\n",
     ")\n",
     "\n",
     "# Define callbacks.\n",
     "checkpoint_cb = keras.callbacks.ModelCheckpoint(\n",
-    "    \"3d_image_classification.h5\", save_best_only=True\n",
+    "    \"3d_image_classification.keras\", save_best_only=True\n",
     ")\n",
     "early_stopping_cb = keras.callbacks.EarlyStopping(monitor=\"val_acc\", patience=15)\n",
     "\n",
@@ -626,7 +626,7 @@
    "outputs": [],
    "source": [
     "# Load best weights.\n",
-    "model.load_weights(\"3d_image_classification.h5\")\n",
+    "model.load_weights(\"3d_image_classification.keras\")\n",
     "prediction = model.predict(np.expand_dims(x_val[0], axis=0))[0]\n",
     "scores = [1 - prediction[0], prediction[0]]\n",
     "\n",