Merge pull request rasbt#140 from rasbt/tf2.3.1-fix

Fix tf version dimension issue

ch15/ch15_part1.ipynb

@@ -697,18 +697,29 @@
     }
    ],
    "source": [
+    "from distutils.version import LooseVersion as Version\n",
+    "\n",
+    "\n",
     "####### Binary Crossentropy\n",
     "bce_probas = tf.keras.losses.BinaryCrossentropy(from_logits=False)\n",
     "bce_logits = tf.keras.losses.BinaryCrossentropy(from_logits=True)\n",
     "\n",
     "logits = tf.constant([0.8])\n",
     "probas = tf.keras.activations.sigmoid(logits)\n",
     "\n",
-    "tf.print(\n",
-    "    'BCE (w Probas): {:.4f}'.format(\n",
-    "    bce_probas(y_true=[1], y_pred=probas)),\n",
-    "    '(w Logits): {:.4f}'.format(\n",
-    "    bce_logits(y_true=[1], y_pred=logits)))\n",
+    "if Version(tf.__version__) >= '2.3.0':\n",
+    "    tf.print(\n",
+    "        'CCE (w Probas): {:.4f}'.format(\n",
+    "        cce_probas(y_true=[[0, 0, 1]], y_pred=probas)),\n",
+    "        '(w Logits): {:.4f}'.format(\n",
+    "        cce_logits(y_true=[[0, 0, 1]], y_pred=logits)))\n",
+    "    \n",
+    "else:\n",
+    "    tf.print(\n",
+    "        'CCE (w Probas): {:.4f}'.format(\n",
+    "        cce_probas(y_true=[0, 0, 1], y_pred=probas)),\n",
+    "        '(w Logits): {:.4f}'.format(\n",
+    "        cce_logits(y_true=[0, 0, 1], y_pred=logits)))\n",
     "\n",
     "\n",
     "####### Categorical Crossentropy\n",
@@ -1260,7 +1271,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.1"
+   "version": "3.8.2"
   }
  },
  "nbformat": 4,

ch15/ch15_part1.py

@@ -10,6 +10,7 @@
 import pandas as pd
 import matplotlib.pyplot as plt
 import os
+from distutils.version import LooseVersion as Version
 
 # *Python Machine Learning 3rd Edition* by [Sebastian Raschka](https://sebastianraschka.com) & [Vahid Mirjalili](http://vahidmirjalili.com), Packt Publishing Ltd. 2019
 # 
@@ -271,11 +272,19 @@ def conv2d(X, W, p=(0, 0), s=(1, 1)):
 logits = tf.constant([[1.5, 0.8, 2.1]])
 probas = tf.keras.activations.softmax(logits)
 
-tf.print(
-    'CCE (w Probas): {:.4f}'.format(
-    cce_probas(y_true=[0, 0, 1], y_pred=probas)),
-    '(w Logits): {:.4f}'.format(
-    cce_logits(y_true=[0, 0, 1], y_pred=logits)))
+if Version(tf.__version__) >= '2.3.0':
+    tf.print(
+        'CCE (w Probas): {:.4f}'.format(
+        cce_probas(y_true=[[0, 0, 1]], y_pred=probas)),
+        '(w Logits): {:.4f}'.format(
+        cce_logits(y_true=[[0, 0, 1]], y_pred=logits)))
+
+else:
+    tf.print(
+        'CCE (w Probas): {:.4f}'.format(
+        cce_probas(y_true=[0, 0, 1], y_pred=probas)),
+        '(w Logits): {:.4f}'.format(
+        cce_logits(y_true=[0, 0, 1], y_pred=logits)))
 
 ####### Sparse Categorical Crossentropy
 sp_cce_probas = tf.keras.losses.SparseCategoricalCrossentropy(