diff --git a/.github/coco.png b/.github/coco.png
deleted file mode 100644
index 93a36fd..0000000
Binary files a/.github/coco.png and /dev/null differ
diff --git a/README.md b/README.md
index 8d88fcc..6923414 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
 [](https://www.codacy.com/manual/ashnair1/COCO-Assistant?utm_source=github.com&utm_medium=referral&utm_content=ashnair1/COCO-Assistant&utm_campaign=Badge_Grade) [](https://badge.fury.io/py/coco-assistant) [](https://opensource.org/licenses/MIT)
-Helper for dealing with MS-COCO annotations. 
+Helper for dealing with MS-COCO annotations.
## Overview
The MS COCO annotation format along with the pycocotools library is quite popular among the computer vision community. Yet I for one found it difficult to play around with the annotations. Deleting a specific category, combining multiple mini datasets to generate a larger dataset, viewing distribution of classes in the annotation file are things I would like to do without writing a separate script for each. The COCO Assistant is designed (or being designed) to assist with this problem. **Please note that currently, the Assistant can only help out with object detection datasets**. Any contributions and/or suggestions are welcome.
@@ -10,7 +10,7 @@ The MS COCO annotation format along with the pycocotools library is quite popula
### Requirements
Your data directory should look as follows:
-```shell script
+```markdown
Example:
.
├── images
@@ -32,7 +32,7 @@ Example:
`pip install coco-assistant`
### 2. Installation: From Source
-```shell script
+```markdown
# Clone the repository
git clone https://github.com/ashnair1/COCO-Assistant.git
# Build and install the library
@@ -43,7 +43,7 @@ make
Usage is similar to how you would use `pycocotools`
-```shell script
+```markdown
from coco_assistant import COCO_Assistant
# Specify image and annotation directories
@@ -59,7 +59,7 @@ cas = COCO_Assistant(img_dir, ann_dir)
The `merge` function allows you to merge multiple datasets.
-```shell script
+```markdown
In[1]: cas = COCO_Assistant(img_dir, ann_dir)
loading annotations into memory...
Done (t=0.09s)
@@ -83,7 +83,7 @@ The merged dataset (images and annotation) can be found in `./results/combinatio
Removes a specific category from an annotation file.
-```shell script
+```markdown
In[1]: cas = COCO_Assistant(img_dir, ann_dir)
loading annotations into memory...
Done (t=0.09s)
@@ -125,7 +125,7 @@ The modified annotation can be found in `./results/removal`
Couldn't `pycocotools` visualise annotations (via [showAnns](https://github.com/cocodataset/cocoapi/blob/636becdc73d54283b3aac6d4ec363cffbb6f9b20/PythonAPI/pycocotools/coco.py#L233)) as well? Sure it could, but I required a way to freely view all the annotations of a particular dataset so here we are.
-```shell script
+```markdown
In[1]: cas.visualise()
Choose directory:
['tiny', 'tiny2']
@@ -142,6 +142,3 @@ The `cas.get_segmasks()` function allows you to create segmentation masks from y
| **SpaceNet** | 
| 
|
| **iSAID** | 
| 
|
-### Todo
-1. Converter for converting COCO annotations to YOLO format.
-2. Write tests for untested functions :)
diff --git a/coco_assistant/VERSION b/coco_assistant/VERSION
index 0c62199..0d91a54 100644
--- a/coco_assistant/VERSION
+++ b/coco_assistant/VERSION
@@ -1 +1 @@
-0.2.1
+0.3.0
diff --git a/coco_assistant/coco_assistant.py b/coco_assistant/coco_assistant.py
index b3fae78..b588d16 100755
--- a/coco_assistant/coco_assistant.py
+++ b/coco_assistant/coco_assistant.py
@@ -8,11 +8,9 @@
from tqdm import tqdm
-from . import coco_converters as converter
from . import coco_stats as stats
from . import coco_visualiser as cocovis
-from coco_assistant.utils import anchors
-from coco_assistant.utils import det2seg
+from coco_assistant.utils import anchors, det2seg
logging.basicConfig(level=logging.ERROR)
logging.getLogger().setLevel(logging.WARNING)
@@ -292,25 +290,6 @@ def get_segmasks(self):
output_dir = os.path.join(self.res_dir, 'segmasks', name)
det2seg.det2seg(ann, output_dir)
- def converter(self, to="TFRecord"):
- """
- Function for converting annotations to other formats
-
- :param to: Format to which annotations are to be converted
- """
- print("Choose directory:")
- print(self.imgfolders)
-
- dir_choice = input()
-
- if dir_choice.lower() not in [item.lower() for item in self.imgfolders]:
- raise AssertionError("Choice not in images folder")
- ind = self.imgfolders.index(dir_choice.lower())
- ann = self.annfiles[ind]
- img_dir = os.path.join(self.img_dir, dir_choice)
-
- converter.convert(ann, img_dir, _format=to)
-
def visualise(self):
"""
Function for visualising annotations.
diff --git a/coco_assistant/coco_converters.py b/coco_assistant/coco_converters.py
deleted file mode 100755
index 342d722..0000000
--- a/coco_assistant/coco_converters.py
+++ /dev/null
@@ -1,138 +0,0 @@
-import logging
-import os
-from random import shuffle
-
-from PIL import Image
-
-from pycocotools.coco import COCO
-
-import tensorflow as tf
-
-from .utils import dataset_util
-
-logging.basicConfig(level=logging.WARNING)
-
-# flags = tf.app.flags
-# flags.DEFINE_string('data_dir', '', 'Root directory to raw Microsoft COCO dataset.')
-# flags.DEFINE_string('set', 'train', 'Convert training set or validation set')
-# flags.DEFINE_string('output_filepath', '', 'Path to output TFRecord')
-# flags.DEFINE_bool('shuffle_imgs',True,'whether to shuffle images of coco')
-# FLAGS = flags.FLAGS
-
-
-def load_coco_detection_dataset(imgs_dir, annotations, shuffle_img=True):
- """Load data from dataset by pycocotools. This tools can be download from "http://mscoco.org/dataset/#download"
- Args:
- imgs_dir: directories of coco images
- annotations_filepath: file path of coco annotations file
- shuffle_img: wheter to shuffle images order
- Return:
- coco_data: list of dictionary format information of each image
- """
- coco = annotations
- img_ids = coco.getImgIds() # totally 82783 images
- cat_ids = coco.getCatIds() #totally 90 catagories, however, the number of categories is not continuous, \
- # [0,12,26,29,30,45,66,68,69,71,83] are missing, this is the problem of coco dataset.
-
- if shuffle_img:
- shuffle(img_ids)
-
- coco_data = []
-
- nb_imgs = len(img_ids)
- for index, img_id in enumerate(img_ids):
- if index % 100 == 0:
- print("Readling images: %d / %d " % (index, nb_imgs))
- img_info = {}
- bboxes = []
- labels = []
-
- img_detail = coco.loadImgs(img_id)[0]
- try:
- pic_height = img_detail['height']
- pic_width = img_detail['width']
- except KeyError:
- logging.warning("Image dimension is missing from the image field."
- " Proceeding to read it manually")
- im = Image.open(os.path.join(imgs_dir, img_detail['file_name']))
- pic_height = im.size[1]
- pic_width = im.size[0]
-
- ann_ids = coco.getAnnIds(imgIds=img_id, catIds=cat_ids)
- anns = coco.loadAnns(ann_ids)
- for ann in anns:
- bboxes_data = ann['bbox']
- # the format of coco bounding boxes are [Xmin, Ymin, width, height]
- bboxes_data = [bboxes_data[0] / float(pic_width), bboxes_data[1] / float(pic_height),
- bboxes_data[2] / float(pic_width), bboxes_data[3] / float(pic_height)]
- bboxes.append(bboxes_data)
- labels.append(ann['category_id'])
-
- img_path = os.path.join(imgs_dir, img_detail['file_name'])
- img_bytes = tf.gfile.GFile(img_path, 'rb').read()
-
- img_info['pixel_data'] = img_bytes
- img_info['height'] = pic_height
- img_info['width'] = pic_width
- img_info['bboxes'] = bboxes
- img_info['labels'] = labels
-
- coco_data.append(img_info)
-
- return coco_data
-
-
-def dict_to_coco_example(img_data):
- """Convert python dictionary formath data of one image to tf.Example proto.
- Args:
- img_data: infomation of one image, inclue bounding box, labels of bounding box,\
- height, width, encoded pixel data.
- Returns:
- example: The converted tf.Example
- """
- bboxes = img_data['bboxes']
- xmin, xmax, ymin, ymax = [], [], [], []
- for bbox in bboxes:
- xmin.append(bbox[0])
- xmax.append(bbox[0] + bbox[2])
- ymin.append(bbox[1])
- ymax.append(bbox[1] + bbox[3])
-
- example = tf.train.Example(features=tf.train.Features(feature={
- 'image/height': dataset_util.int64_feature(img_data['height']),
- 'image/width': dataset_util.int64_feature(img_data['width']),
- 'image/object/bbox/xmin': dataset_util.float_list_feature(xmin),
- 'image/object/bbox/xmax': dataset_util.float_list_feature(xmax),
- 'image/object/bbox/ymin': dataset_util.float_list_feature(ymin),
- 'image/object/bbox/ymax': dataset_util.float_list_feature(ymax),
- 'image/object/class/label': dataset_util.int64_list_feature(img_data['labels']),
- 'image/encoded': dataset_util.bytes_feature(img_data['pixel_data']),
- 'image/format': dataset_util.bytes_feature('jpeg'.encode('utf-8')),
- }))
- return example
-
-
-def convert(ann, img_dir, _format):
-
- dst = os.path.join(os.path.dirname(os.path.dirname(img_dir)),
- 'annotations',
- os.path.basename(img_dir) + ".tfrecord")
-
- if _format == "TFRecord":
- # load total coco data
- coco_data = load_coco_detection_dataset(img_dir, ann, shuffle_img=True)
- total_imgs = len(coco_data)
- # write coco data to tf record
- with tf.python_io.TFRecordWriter(dst) as tfrecord_writer:
- for index, img_data in enumerate(coco_data):
- if index % 100 == 0:
- print("Converting images: %d / %d" % (index, total_imgs))
- example = dict_to_coco_example(img_data)
- tfrecord_writer.write(example.SerializeToString())
-
-
-if __name__ == "__main__":
- _format = "TFRecord"
- ann = COCO("/home/ashwin/COCO-Assistant/data/annotations/coco.json")
- img_dir = "/home/ashwin/COCO-Assistant/data/images/coco"
- convert(ann, img_dir, _format)
diff --git a/requirements.txt b/requirements.txt
index 3c21069..ee0164e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -7,7 +7,6 @@ Pillow>=6.2.2
git+https://github.com/ashnair1/cocoapi.git#egg=pycocotools&subdirectory=PythonAPI
seaborn
scikit-image
-tensorflow==1.12.0
tqdm
# packaging