Skip to content

Commit feab130

Browse files
authored
Add files via upload
1 parent baa825d commit feab130

1 file changed

Lines changed: 3 additions & 3 deletions

File tree

tf_2.x/lab-05-1-logistic_regression-eager.ipynb

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -52,7 +52,7 @@
5252
"outputs": [
5353
{
5454
"data": {
55-
"image/png": "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\n",
55+
"image/png": "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\n",
5656
"text/plain": [
5757
"<Figure size 432x288 with 1 Axes>"
5858
]
@@ -273,7 +273,7 @@
273273
"\n",
274274
"for step in range(EPOCHS):\n",
275275
" for features, labels in iter(dataset):\n",
276-
" grads = grad(logistic_regression(features), features, labels)\n",
276+
" grads = grad(features, labels)\n",
277277
" optimizer.apply_gradients(grads_and_vars=zip(grads,[W,b]))\n",
278278
" if step % 100 == 0:\n",
279279
" print(\"Iter: {}, Loss: {:.4f}\".format(step, loss_fn(logistic_regression(features),features,labels)))\n",
@@ -305,7 +305,7 @@
305305
"name": "python",
306306
"nbconvert_exporter": "python",
307307
"pygments_lexer": "ipython3",
308-
"version": "3.7.3"
308+
"version": "3.7.6"
309309
}
310310
},
311311
"nbformat": 4,

0 commit comments

Comments
 (0)