.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "build/examples_instance/demo_mask_rcnn.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note Click :ref:`here ` to download the full example code .. rst-class:: sphx-glr-example-title .. _sphx_glr_build_examples_instance_demo_mask_rcnn.py: 1. Predict with pre-trained Mask RCNN models =============================================== This article shows how to play with pre-trained Mask RCNN model. Mask RCNN networks are extensions to Faster RCNN networks. :py:class:`gluoncv.model_zoo.MaskRCNN` is inherited from :py:class:`gluoncv.model_zoo.FasterRCNN`. It is highly recommended to read :doc:`../examples_detection/demo_faster_rcnn` first. First let's import some necessary libraries: .. GENERATED FROM PYTHON SOURCE LINES 13-17 .. code-block:: default from matplotlib import pyplot as plt from gluoncv import model_zoo, data, utils .. GENERATED FROM PYTHON SOURCE LINES 18-28 Load a pretrained model ------------------------- Let's get an Mask RCNN model trained on COCO dataset with ResNet-50 backbone. By specifying ``pretrained=True``, it will automatically download the model from the model zoo if necessary. For more pretrained models, please refer to :doc:`../../model_zoo/index`. The returned model is a HybridBlock :py:class:`gluoncv.model_zoo.MaskRCNN` with a default context of `cpu(0)`. .. GENERATED FROM PYTHON SOURCE LINES 28-31 .. code-block:: default net = model_zoo.get_model('mask_rcnn_resnet50_v1b_coco', pretrained=True) .. GENERATED FROM PYTHON SOURCE LINES 32-52 Pre-process an image -------------------- The pre-processing step is identical to Faster RCNN. Next we download an image, and pre-process with preset data transforms. The default behavior is to resize the short edge of the image to 600px. But you can feed an arbitrarily sized image. You can provide a list of image file names, such as ``[im_fname1, im_fname2, ...]`` to :py:func:`gluoncv.data.transforms.presets.rcnn.load_test` if you want to load multiple image together. This function returns two results. The first is a NDArray with shape `(batch_size, RGB_channels, height, width)`. It can be fed into the model directly. The second one contains the images in numpy format to easy to be plotted. Since we only loaded a single image, the first dimension of `x` is 1. Please beware that `orig_img` is resized to short edge 600px. .. GENERATED FROM PYTHON SOURCE LINES 52-58 .. code-block:: default im_fname = utils.download('https://github.com/dmlc/web-data/blob/master/' + 'gluoncv/detection/biking.jpg?raw=true', path='biking.jpg') x, orig_img = data.transforms.presets.rcnn.load_test(im_fname) .. rst-class:: sphx-glr-script-out Out: .. code-block:: none Downloading biking.jpg from https://github.com/dmlc/web-data/blob/master/gluoncv/detection/biking.jpg?raw=true... 0%| | 0/244 [00:00` .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: demo_mask_rcnn.ipynb ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_