This repository has been archived by the owner on Jun 25, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 553
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
109 additions
and
15 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,91 @@ | ||
import numpy as np | ||
import os | ||
from xml.etree import ElementTree | ||
|
||
class XML_preprocessor(object): | ||
|
||
def __init__(self, data_path): | ||
self.path_prefix = data_path | ||
self.num_classes = 20 | ||
self.data = dict() | ||
self._preprocess_XML() | ||
|
||
def _preprocess_XML(self): | ||
filenames = os.listdir(self.path_prefix) | ||
for filename in filenames: | ||
tree = ElementTree.parse(self.path_prefix + filename) | ||
root = tree.getroot() | ||
bounding_boxes = [] | ||
one_hot_classes = [] | ||
size_tree = root.find('size') | ||
width = float(size_tree.find('width').text) | ||
height = float(size_tree.find('height').text) | ||
for object_tree in root.findall('object'): | ||
for bounding_box in object_tree.iter('bndbox'): | ||
xmin = float(bounding_box.find('xmin').text)/width | ||
ymin = float(bounding_box.find('ymin').text)/height | ||
xmax = float(bounding_box.find('xmax').text)/width | ||
ymax = float(bounding_box.find('ymax').text)/height | ||
bounding_box = [xmin,ymin,xmax,ymax] | ||
bounding_boxes.append(bounding_box) | ||
class_name = object_tree.find('name').text | ||
one_hot_class = self._to_one_hot(class_name) | ||
one_hot_classes.append(one_hot_class) | ||
image_name = root.find('filename').text | ||
bounding_boxes = np.asarray(bounding_boxes) | ||
one_hot_classes = np.asarray(one_hot_classes) | ||
image_data = np.hstack((bounding_boxes, one_hot_classes)) | ||
self.data[image_name] = image_data | ||
|
||
def _to_one_hot(self,name): | ||
one_hot_vector = [0] * self.num_classes | ||
if name == 'aeroplane': | ||
one_hot_vector[0] = 1 | ||
elif name == 'bicycle': | ||
one_hot_vector[1] = 1 | ||
elif name == 'bird': | ||
one_hot_vector[2] = 1 | ||
elif name == 'boat': | ||
one_hot_vector[3] = 1 | ||
elif name == 'bottle': | ||
one_hot_vector[4] = 1 | ||
elif name == 'bus': | ||
one_hot_vector[5] = 1 | ||
elif name == 'car': | ||
one_hot_vector[6] = 1 | ||
elif name == 'cat': | ||
one_hot_vector[7] = 1 | ||
elif name == 'chair': | ||
one_hot_vector[8] = 1 | ||
elif name == 'cow': | ||
one_hot_vector[9] = 1 | ||
elif name == 'diningtable': | ||
one_hot_vector[10] = 1 | ||
elif name == 'dog': | ||
one_hot_vector[11] = 1 | ||
elif name == 'horse': | ||
one_hot_vector[12] = 1 | ||
elif name == 'motorbike': | ||
one_hot_vector[13] = 1 | ||
elif name == 'person': | ||
one_hot_vector[14] = 1 | ||
elif name == 'pottedplant': | ||
one_hot_vector[15] = 1 | ||
elif name == 'sheep': | ||
one_hot_vector[16] = 1 | ||
elif name == 'sofa': | ||
one_hot_vector[17] = 1 | ||
elif name == 'train': | ||
one_hot_vector[18] = 1 | ||
elif name == 'tvmonitor': | ||
one_hot_vector[19] = 1 | ||
else: | ||
print('unknown label: %s' %name) | ||
|
||
return one_hot_vector | ||
|
||
## example on how to use it | ||
# import pickle | ||
# data = XML_preprocessor('VOC2007/Annotations/').data | ||
# pickle.dump(data,open('VOC2007.p','wb')) | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,5 +1,8 @@ | ||
[![license](https://img.shields.io/github/license/mashape/apistatus.svg)](LICENSE) | ||
# A port of [SSD: Single Shot MultiBox Detector](https://github.com/weiliu89/caffe/tree/ssd) to [Keras](https://keras.io) framework. | ||
For more details, please refer to [arXiv paper](http://arxiv.org/abs/1512.02325). | ||
For forward pass for 300x300 model, please, follow `SSD.ipynb` for examples. For training procedure for 300x300 model, please, follow `SSD_training.ipynb` for examples. Moreover, in `testing_utils` folder there is a useful script to test `SSD` on video or on camera input. | ||
|
||
Weights are ported from the original models and are available [here](https://mega.nz/#F!7RowVLCL!q3cEVRK9jyOSB9el3SssIA). You need `weights_SSD300.hdf5`, `weights_300x300_old.hdf5` is for the old version of architecture with 3x3 convolution for `pool6`. | ||
|
||
This code was tested with `Keras` v1.2.2, `Tensorflow` v1.0.0, `OpenCV` v3.1.0-dev |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters