Fixed some typos (keras-team#1100)

* Fixed some typos

* Fixed typos

* Reverting VSCode automatic fixes

Author: leonardopaffi

examples/vision/edsr.py

@@ -106,7 +106,7 @@ def random_crop(lowres_img, highres_img, hr_crop_size=96, scale=4):
     """Crop images.
 
     low resolution images: 24x24
-    hight resolution images: 96x96
+    high resolution images: 96x96
     """
     lowres_crop_size = hr_crop_size // scale  # 96//4=24
     lowres_img_shape = tf.shape(lowres_img)[:2]  # (height,width)
@@ -175,7 +175,7 @@ def dataset_object(dataset_cache, training=True):
 
 lowres, highres = next(iter(train_ds))
 
-# Hight Resolution Images
+# High Resolution Images
 plt.figure(figsize=(10, 10))
 for i in range(9):
     ax = plt.subplot(3, 3, i + 1)
@@ -339,7 +339,7 @@ def plot_results(lowres, preds):
 training the model with a wider variety of inputs with mixed downgrading factors, so as to
 be able to handle a greater range of real-world images.
 
-You could also improve on the given basline EDSR model by implementing EDSR+,
+You could also improve on the given baseline EDSR model by implementing EDSR+,
 or MDSR( Multi-Scale super-resolution) and MDSR+,
 which were proposed in the same paper.
 """

examples/vision/ipynb/edsr.ipynb

@@ -160,7 +160,7 @@
     "    \"\"\"Crop images.\n",
     "\n",
     "    low resolution images: 24x24\n",
-    "    hight resolution images: 96x96\n",
+    "    high resolution images: 96x96\n",
     "    \"\"\"\n",
     "    lowres_crop_size = hr_crop_size // scale  # 96//4=24\n",
     "    lowres_img_shape = tf.shape(lowres_img)[:2]  # (height,width)\n",
@@ -257,7 +257,7 @@
    "source": [
     "lowres, highres = next(iter(train_ds))\n",
     "\n",
-    "# Hight Resolution Images\n",
+    "# High Resolution Images\n",
     "plt.figure(figsize=(10, 10))\n",
     "for i in range(9):\n",
     "    ax = plt.subplot(3, 3, i + 1)\n",
@@ -469,7 +469,7 @@
     "training the model with a wider variety of inputs with mixed downgrading factors, so as to\n",
     "be able to handle a greater range of real-world images.\n",
     "\n",
-    "You could also improve on the given basline EDSR model by implementing EDSR+,\n",
+    "You could also improve on the given baseline EDSR model by implementing EDSR+,\n",
     "or MDSR( Multi-Scale super-resolution) and MDSR+,\n",
     "which were proposed in the same paper."
    ]
@@ -503,4 +503,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 0
-}
+}

examples/vision/md/edsr.md

@@ -114,7 +114,7 @@ def random_crop(lowres_img, highres_img, hr_crop_size=96, scale=4):
     """Crop images.
 
     low resolution images: 24x24
-    hight resolution images: 96x96
+    high resolution images: 96x96
     """
     lowres_crop_size = hr_crop_size // scale  # 96//4=24
     lowres_img_shape = tf.shape(lowres_img)[:2]  # (height,width)
@@ -187,7 +187,7 @@ Let's visualize a few sample images:
 ```python
 lowres, highres = next(iter(train_ds))
 
-# Hight Resolution Images
+# High Resolution Images
 plt.figure(figsize=(10, 10))
 for i in range(9):
     ax = plt.subplot(3, 3, i + 1)
@@ -632,6 +632,6 @@ Super-Resolution). You could improve the model accuracy by training the model fo
 training the model with a wider variety of inputs with mixed downgrading factors, so as to
 be able to handle a greater range of real-world images.
 
-You could also improve on the given basline EDSR model by implementing EDSR+,
+You could also improve on the given baseline EDSR model by implementing EDSR+,
 or MDSR( Multi-Scale super-resolution) and MDSR+,
 which were proposed in the same paper.