y_train_hinge must be paired with y_train_nocon (tensorflow#211)

* y_train_hinge must be paired with y_train_nocon y_train_hinge should be accordance with x_train_tfcirc, which originates from x_train_nocon * y_train_hinge must be paired with y_train_nocon update the doc * pin cirq==0.7 Co-authored-by: Mark Daoust <[email protected]>
ahrPope · May 5, 2020 · 2294622 · 2294622
1 parent a78c79a
commit 2294622
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/docs/tutorials/mnist.ipynb b/docs/tutorials/mnist.ipynb
@@ -775,7 +775,7 @@
         "\n",
         "Note: Another valid approach would be to shift the output range to `[0,1]`, and treat it as the probability the model assigns to class `3`. This could be used with a standard a `tf.losses.BinaryCrossentropy` loss.\n",
         "\n",
-        "To use the hinge loss here you need to make two small adjustments. First convert the labels, `y_train`, from boolean to `[-1,1]`, as expected by the hinge loss."
+        "To use the hinge loss here you need to make two small adjustments. First convert the labels, `y_train_nocon`, from boolean to `[-1,1]`, as expected by the hinge loss."
       ]
     },
     {
@@ -788,7 +788,7 @@
       },
       "outputs": [],
       "source": [
-        "y_train_hinge = 2.0*y_train-1.0\n",
+        "y_train_hinge = 2.0*y_train_nocon-1.0\n",
         "y_test_hinge = 2.0*y_test-1.0"
       ]
     },