d2l-ai · AnirudhDagar · Aug 16, 2020 · Aug 16, 2020
diff --git a/chapter_computer-vision/bounding-box.md b/chapter_computer-vision/bounding-box.md
@@ -16,6 +16,18 @@ from mxnet import image, npx
 npx.set_np()
 ```
 
+```{.python .input}
+#@tab pytorch
+%matplotlib inline
+from d2l import torch as d2l
+```
+
+```{.python .input}
+#@tab tensorflow
+%matplotlib inline
+from d2l import tensorflow as d2l
+```
+
 Next, we will load the sample images that will be used in this section. We can see there is a dog on the left side of the image and a cat on the right. They are the two main targets in this image.
 
 ```{.python .input}
@@ -24,18 +36,27 @@ img = image.imread('../img/catdog.jpg').asnumpy()
 d2l.plt.imshow(img);
 ```
 
+```{.python .input}
+#@tab pytorch, tensorflow
+d2l.set_figsize()
+img = d2l.plt.imread('../img/catdog.jpg')
+d2l.plt.imshow(img);
+```
+
 ## Bounding Box
 
 In object detection, we usually use a bounding box to describe the target location. The bounding box is a rectangular box that can be determined by the $x$ and $y$ axis coordinates in the upper-left corner and the $x$ and $y$ axis coordinates in the lower-right corner of the rectangle. We will define the bounding boxes of the dog and the cat in the image based on the coordinate information in the above image. The origin of the coordinates in the above image is the upper left corner of the image, and to the right and down are the positive directions of the $x$ axis and the $y$ axis, respectively.
 
-```{.python .input  n=2}
+```{.python .input}
+#@tab all
 # bbox is the abbreviation for bounding box
 dog_bbox, cat_bbox = [60, 45, 378, 516], [400, 112, 655, 493]
 ```
 
 We can draw the bounding box in the image to check if it is accurate. Before drawing the box, we will define a helper function `bbox_to_rect`. It represents the bounding box in the bounding box format of `matplotlib`.
 
-```{.python .input  n=3}
+```{.python .input}
+#@tab all
 #@save
 def bbox_to_rect(bbox, color):
     """Convert bounding box to matplotlib format."""
@@ -50,6 +71,7 @@ def bbox_to_rect(bbox, color):
 After loading the bounding box on the image, we can see that the main outline of the target is basically inside the box.
 
 ```{.python .input}
+#@tab all
 fig = d2l.plt.imshow(img)
 fig.axes.add_patch(bbox_to_rect(dog_bbox, 'blue'))
 fig.axes.add_patch(bbox_to_rect(cat_bbox, 'red'));
@@ -63,7 +85,6 @@ fig.axes.add_patch(bbox_to_rect(cat_bbox, 'red'));
 
 1. Find some images and try to label a bounding box that contains the target. Compare the difference between the time it takes to label the bounding box and label the category.
 
-
 :begin_tab:`mxnet`
 [Discussions](https://discuss.d2l.ai/t/369)
 :end_tab:
diff --git a/d2l/tensorflow.py b/d2l/tensorflow.py
@@ -873,6 +873,17 @@ def train_concise_ch11(trainer_fn, hyperparams, data_iter, num_epochs=2):
     print(f'loss: {animator.Y[0][-1]:.3f}, {timer.avg():.3f} sec/epoch')
 
 
+# Defined in file: ./chapter_computer-vision/bounding-box.md
+def bbox_to_rect(bbox, color):
+    """Convert bounding box to matplotlib format."""
+    # Convert the bounding box (top-left x, top-left y, bottom-right x,
+    # bottom-right y) format to matplotlib format: ((upper-left x,
+    # upper-left y), width, height)
+    return d2l.plt.Rectangle(
+        xy=(bbox[0], bbox[1]), width=bbox[2]-bbox[0], height=bbox[3]-bbox[1],
+        fill=False, edgecolor=color, linewidth=2)
+
+
 # Alias defined in config.ini
 size = lambda a: tf.size(a).numpy()
 

diff --git a/d2l/torch.py b/d2l/torch.py
@@ -1208,6 +1208,17 @@ def init_weights(m):
     print(f'loss: {animator.Y[0][-1]:.3f}, {timer.avg():.3f} sec/epoch')
 
 
+# Defined in file: ./chapter_computer-vision/bounding-box.md
+def bbox_to_rect(bbox, color):
+    """Convert bounding box to matplotlib format."""
+    # Convert the bounding box (top-left x, top-left y, bottom-right x,
+    # bottom-right y) format to matplotlib format: ((upper-left x,
+    # upper-left y), width, height)
+    return d2l.plt.Rectangle(
+        xy=(bbox[0], bbox[1]), width=bbox[2]-bbox[0], height=bbox[3]-bbox[1],
+        fill=False, edgecolor=color, linewidth=2)
+
+
 # Alias defined in config.ini