Develop Reference

How can I alter TFRecords for my COCO format dataset?

I am currently trying to get the Caltech camera traps benchmark dataset into TFRecords but I am struggling quite a bit. https://lila.science/datasets/caltech-camera-traps. The annotations are displayed as follows:
"info": {"contributor": "Sara Beery", "date_created": "2018-07-03 18:34:36.573636", "version": "Caltech Camera Traps - ECCV18", "description": "Database of camera trap images collected from the NPS and the USGS with help from Justin Brown and Erin Boydston", "year": 2018}]
"categories": [{"id": 6, "name": "bobcat"}, ....]
"images": [{"file_name": "59b93afb-23d2-11e8-a6a3-ec086b02610b.jpg", "rights_holder": "Justin Brown", "height": 1494, "width": 2048, "frame_num": 2, "date_captured": "2012-05-09 07:33:45", "location": 38, "seq_num_frames": 3, "seq_id": "6f04895c-5567-11e8-a3d6-dca9047ef277", "id": "59b93afb-23d2-11e8-a6a3-ec086b02610b"},...]
"annotations": [{"image_id": "59ffbd00-23d2-11e8-a6a3-ec086b02610b", "category_id": 1, "bbox": [1118.72, 570.88, 328.96000000000004, 180.48000000000002], "id": "36132"}
I am trying to use the create_coco_tf_record.py file and adapt it. I do not have the 'iscrowd' or 'segmentations' in my annotations and a lot of the images do not have bounding boxes. I was wondering if someone has done similar and would be able to help please. Thanks! Here is the file...
# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
r"""Convert raw COCO dataset to TFRecord for object_detection.
This tool supports data generation for object detection (boxes, masks),
keypoint detection, and DensePose.
Please note that this tool creates sharded output files.
Example usage:
python create_coco_tf_record.py --logtostderr \
--train_image_dir="${TRAIN_IMAGE_DIR}" \
--val_image_dir="${VAL_IMAGE_DIR}" \
--test_image_dir="${TEST_IMAGE_DIR}" \
--train_annotations_file="${TRAIN_ANNOTATIONS_FILE}" \
--val_annotations_file="${VAL_ANNOTATIONS_FILE}" \
--testdev_annotations_file="${TESTDEV_ANNOTATIONS_FILE}" \
--output_dir="${OUTPUT_DIR}"
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import hashlib
import io
import json
import logging
import os
import contextlib2
import numpy as np
import PIL.Image
from pycocotools import mask
import tensorflow.compat.v1 as tf
from object_detection.dataset_tools import tf_record_creation_util
from object_detection.utils import dataset_util
from object_detection.utils import label_map_util
flags = tf.app.flags
tf.flags.DEFINE_boolean(
'include_masks', False, 'Whether to include instance segmentations masks '
'(PNG encoded) in the result. default: False.')
tf.flags.DEFINE_string('train_image_dir', '', 'Training image directory.')
tf.flags.DEFINE_string('val_image_dir', '', 'Validation image directory.')
tf.flags.DEFINE_string('test_image_dir', '', 'Test image directory.')
tf.flags.DEFINE_string('train_annotations_file', '',
'Training annotations JSON file.')
tf.flags.DEFINE_string('val_annotations_file', '',
'Validation annotations JSON file.')
tf.flags.DEFINE_string('testdev_annotations_file', '',
'Test-dev annotations JSON file.')
tf.flags.DEFINE_string('train_keypoint_annotations_file', '',
'Training annotations JSON file.')
tf.flags.DEFINE_string('val_keypoint_annotations_file', '',
'Validation annotations JSON file.')
# DensePose is only available for coco 2014.
tf.flags.DEFINE_string('train_densepose_annotations_file', '',
'Training annotations JSON file for DensePose.')
tf.flags.DEFINE_string('val_densepose_annotations_file', '',
'Validation annotations JSON file for DensePose.')
tf.flags.DEFINE_string('output_dir', '/tmp/', 'Output data directory.')
# Whether to only produce images/annotations on person class (for keypoint /
# densepose task).
tf.flags.DEFINE_boolean('remove_non_person_annotations', False, 'Whether to '
'remove all annotations for non-person objects.')
tf.flags.DEFINE_boolean('remove_non_person_images', False, 'Whether to '
'remove all examples that do not contain a person.')
FLAGS = flags.FLAGS
logger = tf.get_logger()
logger.setLevel(logging.INFO)
_COCO_KEYPOINT_NAMES = [
b'nose', b'left_eye', b'right_eye', b'left_ear', b'right_ear',
b'left_shoulder', b'right_shoulder', b'left_elbow', b'right_elbow',
b'left_wrist', b'right_wrist', b'left_hip', b'right_hip',
b'left_knee', b'right_knee', b'left_ankle', b'right_ankle'
]
_COCO_PART_NAMES = [
b'torso_back', b'torso_front', b'right_hand', b'left_hand', b'left_foot',
b'right_foot', b'right_upper_leg_back', b'left_upper_leg_back',
b'right_upper_leg_front', b'left_upper_leg_front', b'right_lower_leg_back',
b'left_lower_leg_back', b'right_lower_leg_front', b'left_lower_leg_front',
b'left_upper_arm_back', b'right_upper_arm_back', b'left_upper_arm_front',
b'right_upper_arm_front', b'left_lower_arm_back', b'right_lower_arm_back',
b'left_lower_arm_front', b'right_lower_arm_front', b'right_face',
b'left_face',
]
_DP_PART_ID_OFFSET = 1
def clip_to_unit(x):
return min(max(x, 0.0), 1.0)
def create_tf_example(image,
annotations_list,
image_dir,
category_index,
include_masks=False,
keypoint_annotations_dict=None,
densepose_annotations_dict=None,
remove_non_person_annotations=False,
remove_non_person_images=False):
"""Converts image and annotations to a tf.Example proto.
Args:
image: dict with keys: [u'license', u'file_name', u'coco_url', u'height',
u'width', u'date_captured', u'flickr_url', u'id']
annotations_list:
list of dicts with keys: [u'segmentation', u'area', u'iscrowd',
u'image_id', u'bbox', u'category_id', u'id'] Notice that bounding box
coordinates in the official COCO dataset are given as [x, y, width,
height] tuples using absolute coordinates where x, y represent the
top-left (0-indexed) corner. This function converts to the format
expected by the Tensorflow Object Detection API (which is which is
[ymin, xmin, ymax, xmax] with coordinates normalized relative to image
size).
image_dir: directory containing the image files.
category_index: a dict containing COCO category information keyed by the
'id' field of each category. See the label_map_util.create_category_index
function.
include_masks: Whether to include instance segmentations masks
(PNG encoded) in the result. default: False.
keypoint_annotations_dict: A dictionary that maps from annotation_id to a
dictionary with keys: [u'keypoints', u'num_keypoints'] represeting the
keypoint information for this person object annotation. If None, then
no keypoint annotations will be populated.
densepose_annotations_dict: A dictionary that maps from annotation_id to a
dictionary with keys: [u'dp_I', u'dp_x', u'dp_y', 'dp_U', 'dp_V']
representing part surface coordinates. For more information see
http://densepose.org/.
remove_non_person_annotations: Whether to remove any annotations that are
not the "person" class.
remove_non_person_images: Whether to remove any images that do not contain
at least one "person" annotation.
Returns:
key: SHA256 hash of the image.
example: The converted tf.Example
num_annotations_skipped: Number of (invalid) annotations that were ignored.
num_keypoint_annotation_skipped: Number of keypoint annotations that were
skipped.
num_densepose_annotation_skipped: Number of DensePose annotations that were
skipped.
Raises:
ValueError: if the image pointed to by data['filename'] is not a valid JPEG
"""
image_height = image['height']
image_width = image['width']
filename = image['file_name']
image_id = image['id']
full_path = os.path.join(image_dir, filename)
with tf.gfile.GFile(full_path, 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = PIL.Image.open(encoded_jpg_io)
key = hashlib.sha256(encoded_jpg).hexdigest()
xmin = []
xmax = []
ymin = []
ymax = []
is_crowd = []
category_names = []
category_ids = []
area = []
encoded_mask_png = []
keypoints_x = []
keypoints_y = []
keypoints_visibility = []
keypoints_name = []
num_keypoints = []
include_keypoint = keypoint_annotations_dict is not None
num_annotations_skipped = 0
num_keypoint_annotation_used = 0
num_keypoint_annotation_skipped = 0
dp_part_index = []
dp_x = []
dp_y = []
dp_u = []
dp_v = []
dp_num_points = []
densepose_keys = ['dp_I', 'dp_U', 'dp_V', 'dp_x', 'dp_y', 'bbox']
include_densepose = densepose_annotations_dict is not None
num_densepose_annotation_used = 0
num_densepose_annotation_skipped = 0
for object_annotations in annotations_list:
(x, y, width, height) = tuple(object_annotations['bbox'])
if width <= 0 or height <= 0:
num_annotations_skipped += 1
continue
if x + width > image_width or y + height > image_height:
num_annotations_skipped += 1
continue
category_id = int(object_annotations['category_id'])
category_name = category_index[category_id]['name'].encode('utf8')
if remove_non_person_annotations and category_name != b'person':
num_annotations_skipped += 1
continue
xmin.append(float(x) / image_width)
xmax.append(float(x + width) / image_width)
ymin.append(float(y) / image_height)
ymax.append(float(y + height) / image_height)
#is_crowd.append(object_annotations['iscrowd'])
category_ids.append(category_id)
category_names.append(category_name)
#area.append(object_annotations['area'])
# if include_masks:
# run_len_encoding = mask.frPyObjects(object_annotations['segmentation'],
# image_height, image_width)
# binary_mask = mask.decode(run_len_encoding)
# if not object_annotations['iscrowd']:
# binary_mask = np.amax(binary_mask, axis=2)
# pil_image = PIL.Image.fromarray(binary_mask)
# output_io = io.BytesIO()
# pil_image.save(output_io, format='PNG')
# encoded_mask_png.append(output_io.getvalue())
# if include_keypoint:
# annotation_id = object_annotations['id']
# if annotation_id in keypoint_annotations_dict:
# num_keypoint_annotation_used += 1
# keypoint_annotations = keypoint_annotations_dict[annotation_id]
# keypoints = keypoint_annotations['keypoints']
# num_kpts = keypoint_annotations['num_keypoints']
# keypoints_x_abs = keypoints[::3]
# keypoints_x.extend(
# [float(x_abs) / image_width for x_abs in keypoints_x_abs])
# keypoints_y_abs = keypoints[1::3]
# keypoints_y.extend(
# [float(y_abs) / image_height for y_abs in keypoints_y_abs])
# keypoints_visibility.extend(keypoints[2::3])
# keypoints_name.extend(_COCO_KEYPOINT_NAMES)
# num_keypoints.append(num_kpts)
# else:
# keypoints_x.extend([0.0] * len(_COCO_KEYPOINT_NAMES))
# keypoints_y.extend([0.0] * len(_COCO_KEYPOINT_NAMES))
# keypoints_visibility.extend([0] * len(_COCO_KEYPOINT_NAMES))
# keypoints_name.extend(_COCO_KEYPOINT_NAMES)
# num_keypoints.append(0)
# if include_densepose:
# annotation_id = object_annotations['id']
# if (annotation_id in densepose_annotations_dict and
# all(key in densepose_annotations_dict[annotation_id]
# for key in densepose_keys)):
# dp_annotations = densepose_annotations_dict[annotation_id]
# num_densepose_annotation_used += 1
# dp_num_points.append(len(dp_annotations['dp_I']))
# dp_part_index.extend([int(i - _DP_PART_ID_OFFSET)
# for i in dp_annotations['dp_I']])
# # DensePose surface coordinates are defined on a [256, 256] grid
# # relative to each instance box (i.e. absolute coordinates in range
# # [0., 256.]). The following converts the coordinates
# # so that they are expressed in normalized image coordinates.
# dp_x_box_rel = [
# clip_to_unit(val / 256.) for val in dp_annotations['dp_x']]
# dp_x_norm = [(float(x) + x_box_rel * width) / image_width
# for x_box_rel in dp_x_box_rel]
# dp_y_box_rel = [
# clip_to_unit(val / 256.) for val in dp_annotations['dp_y']]
# dp_y_norm = [(float(y) + y_box_rel * height) / image_height
# for y_box_rel in dp_y_box_rel]
# dp_x.extend(dp_x_norm)
# dp_y.extend(dp_y_norm)
# dp_u.extend(dp_annotations['dp_U'])
# dp_v.extend(dp_annotations['dp_V'])
# else:
# dp_num_points.append(0)
# if (remove_non_person_images and
# not any(name == b'person' for name in category_names)):
# return (key, None, num_annotations_skipped,
# num_keypoint_annotation_skipped, num_densepose_annotation_skipped)
feature_dict = {
'image/height':
dataset_util.int64_feature(image_height),
'image/width':
dataset_util.int64_feature(image_width),
'image/filename':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/source_id':
dataset_util.bytes_feature(str(image_id).encode('utf8')),
'image/key/sha256':
dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature('jpeg'.encode('utf8')),
'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/text':
dataset_util.bytes_list_feature(category_names),
'image/object/is_crowd':
dataset_util.int64_list_feature(is_crowd),
'image/object/area':
dataset_util.float_list_feature(area),
}
# if include_masks:
# feature_dict['image/object/mask'] = (
# dataset_util.bytes_list_feature(encoded_mask_png))
# if include_keypoint:
# feature_dict['image/object/keypoint/x'] = (
# dataset_util.float_list_feature(keypoints_x))
# feature_dict['image/object/keypoint/y'] = (
# dataset_util.float_list_feature(keypoints_y))
# feature_dict['image/object/keypoint/num'] = (
# dataset_util.int64_list_feature(num_keypoints))
# feature_dict['image/object/keypoint/visibility'] = (
# dataset_util.int64_list_feature(keypoints_visibility))
# feature_dict['image/object/keypoint/text'] = (
# dataset_util.bytes_list_feature(keypoints_name))
# num_keypoint_annotation_skipped = (
# len(keypoint_annotations_dict) - num_keypoint_annotation_used)
# if include_densepose:
# feature_dict['image/object/densepose/num'] = (
# dataset_util.int64_list_feature(dp_num_points))
# feature_dict['image/object/densepose/part_index'] = (
# dataset_util.int64_list_feature(dp_part_index))
# feature_dict['image/object/densepose/x'] = (
# dataset_util.float_list_feature(dp_x))
# feature_dict['image/object/densepose/y'] = (
# dataset_util.float_list_feature(dp_y))
# feature_dict['image/object/densepose/u'] = (
# dataset_util.float_list_feature(dp_u))
# feature_dict['image/object/densepose/v'] = (
# dataset_util.float_list_feature(dp_v))
# num_densepose_annotation_skipped = (
# len(densepose_annotations_dict) - num_densepose_annotation_used)
example = tf.train.Example(features=tf.train.Features(feature=feature_dict))
return (key, example, num_annotations_skipped,
num_keypoint_annotation_skipped, num_densepose_annotation_skipped)
def _create_tf_record_from_coco_annotations(annotations_file, image_dir,
output_path, include_masks,
num_shards,
keypoint_annotations_file='',
densepose_annotations_file='',
remove_non_person_annotations=False,
remove_non_person_images=False):
"""Loads COCO annotation json files and converts to tf.Record format.
Args:
annotations_file: JSON file containing bounding box annotations.
image_dir: Directory containing the image files.
output_path: Path to output tf.Record file.
include_masks: Whether to include instance segmentations masks
(PNG encoded) in the result. default: False.
num_shards: number of output file shards.
keypoint_annotations_file: JSON file containing the person keypoint
annotations. If empty, then no person keypoint annotations will be
generated.
densepose_annotations_file: JSON file containing the DensePose annotations.
If empty, then no DensePose annotations will be generated.
remove_non_person_annotations: Whether to remove any annotations that are
not the "person" class.
remove_non_person_images: Whether to remove any images that do not contain
at least one "person" annotation.
"""
with contextlib2.ExitStack() as tf_record_close_stack, \
tf.gfile.GFile(annotations_file, 'r') as fid:
output_tfrecords = tf_record_creation_util.open_sharded_output_tfrecords(
tf_record_close_stack, output_path, num_shards)
groundtruth_data = json.load(fid)
images = groundtruth_data['images']
category_index = label_map_util.create_category_index(
groundtruth_data['categories'])
annotations_index = {}
if 'annotations' in groundtruth_data:
logging.info('Found groundtruth annotations. Building annotations index.')
for annotation in groundtruth_data['annotations']:
image_id = annotation['image_id']
if image_id not in annotations_index:
annotations_index[image_id] = []
annotations_index[image_id].append(annotation)
missing_annotation_count = 0
for image in images:
image_id = image['id']
if image_id not in annotations_index:
missing_annotation_count += 1
annotations_index[image_id] = []
logging.info('%d images are missing annotations.',
missing_annotation_count)
keypoint_annotations_index = {}
if keypoint_annotations_file:
with tf.gfile.GFile(keypoint_annotations_file, 'r') as kid:
keypoint_groundtruth_data = json.load(kid)
if 'annotations' in keypoint_groundtruth_data:
for annotation in keypoint_groundtruth_data['annotations']:
image_id = annotation['image_id']
if image_id not in keypoint_annotations_index:
keypoint_annotations_index[image_id] = {}
keypoint_annotations_index[image_id][annotation['id']] = annotation
densepose_annotations_index = {}
if densepose_annotations_file:
with tf.gfile.GFile(densepose_annotations_file, 'r') as fid:
densepose_groundtruth_data = json.load(fid)
if 'annotations' in densepose_groundtruth_data:
for annotation in densepose_groundtruth_data['annotations']:
image_id = annotation['image_id']
if image_id not in densepose_annotations_index:
densepose_annotations_index[image_id] = {}
densepose_annotations_index[image_id][annotation['id']] = annotation
total_num_annotations_skipped = 0
total_num_keypoint_annotations_skipped = 0
total_num_densepose_annotations_skipped = 0
for idx, image in enumerate(images):
if idx % 100 == 0:
logging.info('On image %d of %d', idx, len(images))
annotations_list = annotations_index[image['id']]
keypoint_annotations_dict = None
if keypoint_annotations_file:
keypoint_annotations_dict = {}
if image['id'] in keypoint_annotations_index:
keypoint_annotations_dict = keypoint_annotations_index[image['id']]
densepose_annotations_dict = None
if densepose_annotations_file:
densepose_annotations_dict = {}
if image['id'] in densepose_annotations_index:
densepose_annotations_dict = densepose_annotations_index[image['id']]
(_, tf_example, num_annotations_skipped, num_keypoint_annotations_skipped,
num_densepose_annotations_skipped) = create_tf_example(
image, annotations_list, image_dir, category_index, include_masks,
keypoint_annotations_dict, densepose_annotations_dict,
remove_non_person_annotations, remove_non_person_images)
total_num_annotations_skipped += num_annotations_skipped
total_num_keypoint_annotations_skipped += num_keypoint_annotations_skipped
total_num_densepose_annotations_skipped += (
num_densepose_annotations_skipped)
shard_idx = idx % num_shards
if tf_example:
output_tfrecords[shard_idx].write(tf_example.SerializeToString())
logging.info('Finished writing, skipped %d annotations.',
total_num_annotations_skipped)
if keypoint_annotations_file:
logging.info('Finished writing, skipped %d keypoint annotations.',
total_num_keypoint_annotations_skipped)
if densepose_annotations_file:
logging.info('Finished writing, skipped %d DensePose annotations.',
total_num_densepose_annotations_skipped)
def main(_):
assert FLAGS.train_image_dir, '`train_image_dir` missing.'
assert FLAGS.val_image_dir, '`val_image_dir` missing.'
assert FLAGS.test_image_dir, '`test_image_dir` missing.'
assert FLAGS.train_annotations_file, '`train_annotations_file` missing.'
assert FLAGS.val_annotations_file, '`val_annotations_file` missing.'
assert FLAGS.testdev_annotations_file, '`testdev_annotations_file` missing.'
if not tf.gfile.IsDirectory(FLAGS.output_dir):
tf.gfile.MakeDirs(FLAGS.output_dir)
train_output_path = os.path.join(FLAGS.output_dir, 'coco_train.record')
val_output_path = os.path.join(FLAGS.output_dir, 'coco_val.record')
testdev_output_path = os.path.join(FLAGS.output_dir, 'coco_testdev.record')
_create_tf_record_from_coco_annotations(
FLAGS.train_annotations_file,
FLAGS.train_image_dir,
train_output_path,
FLAGS.include_masks,
num_shards=100,
keypoint_annotations_file=FLAGS.train_keypoint_annotations_file,
densepose_annotations_file=FLAGS.train_densepose_annotations_file,
remove_non_person_annotations=FLAGS.remove_non_person_annotations,
remove_non_person_images=FLAGS.remove_non_person_images)
_create_tf_record_from_coco_annotations(
FLAGS.val_annotations_file,
FLAGS.val_image_dir,
val_output_path,
FLAGS.include_masks,
num_shards=50,
keypoint_annotations_file=FLAGS.val_keypoint_annotations_file,
densepose_annotations_file=FLAGS.val_densepose_annotations_file,
remove_non_person_annotations=FLAGS.remove_non_person_annotations,
remove_non_person_images=FLAGS.remove_non_person_images)
_create_tf_record_from_coco_annotations(
FLAGS.testdev_annotations_file,
FLAGS.test_image_dir,
testdev_output_path,
FLAGS.include_masks,
num_shards=50)
if __name__ == '__main__':
tf.app.run()

You can leave the iscrowd and segmentations as empty if you are doing object detection or classification or ... tasks. But You wouldn't make use of the data with missing bounding boxes for such tasks.

Skip image during tensorflow input pipeline

I have a Tensorflow input pipeline that reads in two png files (example, label) from disk. I want to tell tensorflow to skip an example/label pair based on a value in the label. Anyone know how to do this?
Here is a simplified example of the input pipeline and with a comment where I want to do the filtering:
import tensorflow as tf
import glob2 as glob
def preprocess_images(impath, labpath):
image = tf.io.read_file(impath)
label = tf.io.read_file(labpath)
image = tf.image.decode_png(image, channels=3)
label = tf.image.decode_png(label, channels=1)
if tf.reduce_sum(label) == 0:
#skip the image and move on to the next, don't include this in the batch
else:
return (image, label)
im_files = glob.glob(impath + '*.png')
lab_files = glob.glob(labpath + '*.png')
files = (im_files, lab_files)
path = tf.data.Dataset.from_tensor_slices(files)
pair = path.map(preprocess_images)
ds = tf.data.Dataset.zip(pair)
ds = ds.batch(64)

The easiest way seems to be to use filter method on your tf.data.Dataset object.
Here I am going to load the label only and filter out the entries with a sum of 0:
def load_label_only(impath, labpath):
label = tf.io.read_file(labpath)
label = tf.image.decode_png(label, channels=1)
return impath, label
# Create the dataset as in your example:
im_files = glob.glob(impath + '*.png')
lab_files = glob.glob(labpath + '*.png')
files = (im_files, lab_files)
ds = tf.data.Dataset.from_tensor_slices(files)
ds = ds.map(load_label_only)
# Here, I am going to keep only non-zero labels:
filtered_ds = ds.filter(lambda image_path, label_map: tf.reduce_sum(label_map) != 0)
# Load the rest of the images...

How do I take care of GDALDatasetShadow TypeError when reprojecting and writing GEOTIFF multi-band raster to GEOTIFF 3-band raster?

I've been trying to reproject an input (multi-band) GEOTIFF file to a destination transformation/projection and write these reprojected bands to a new 3 band GEOTIFF file (since I don't need the other bands). I've tried combining 2 blocks of code that work independently of each other (one writes 3 bands to a new GEOTIFF, the other reprojects a 1 band GEOTIFF to a reference file). However, I receive the following error:
TypeError: in method 'ReprojectImage', argument 1 of type 'GDALDatasetShadow *'
Find the function that I've used below:
def reprojectRaster(inputfile, referencefile, outputfile):
if os.path.exists(outputfile):
os.remove(outputfile)
input = gdal.Open(inputfile, gdalconst.GA_ReadOnly)
with rasterio.open(inputfile) as src:
input_array = src.read((2,1,4)) #red band, green band, nir band
inputProj = input.GetProjection()
#inputTrans = input.GetGeoTransform
reference = gdal.Open(referencefile, gdalconst.GA_ReadOnly)
referenceProj = reference.GetProjection()
referenceTrans = reference.GetGeoTransform()
bandreference = reference.GetRasterBand(1)
x = reference.RasterXSize
y = reference.RasterYSize
no_bands = reference.RasterCount
driver= gdal.GetDriverByName('GTiff')
output = driver.Create(outputfile,x,y,no_bands, bandreference.DataType)
output.SetGeoTransform(referenceTrans)
output.SetProjection(referenceProj)
#I've been trying to make put this loop inside from the other code
for i, image in enumerate(input_array, 1):
input.GetRasterBand(i).WriteArray( image )
gdal.ReprojectImage(inputfile,outputfile,inputProj,referenceProj,gdalconst.GRA_Bilinear)
del output
def CreateGeoTiff(outputfile, inputfile, referencefile):
with rasterio.open(inputfile) as src:
input_array = src.read((2,1,4)) #red, green, nir bands
reference = gdal.Open(referencefile, gdalconst.GA_ReadOnly)
referenceProj = reference.GetProjection()
referenceTrans = reference.GetGeoTransform()
driver = gdal.GetDriverByName('GTiff')
no_bands, cols, rows = input_array.shape
DataSet = driver.Create(outputfile, cols, rows, no_bands, gdal.GDT_Float32)
DataSet.SetGeoTransform(referenceTrans)
DataSet.SetProjection(referenceProj)
for i, image in enumerate(input_array, 1):
DataSet.GetRasterBand(i).WriteArray( image )
DataSet = None
return(gdal.Open(outputfile, gdalconst.GA_ReadOnly))
The tried to combine the following 2 functions:
def reprojectRaster(inputfile, referencefile, outputfile):
input = gdal.Open(inputfile, gdalconst.GA_ReadOnly)
inputProj = input.GetProjection()
reference = gdal.Open(referencefile, gdalconst.GA_ReadOnly)
referenceProj = reference.GetProjection()
referenceTrans = reference.GetGeoTransform()
bandreference = reference.GetRasterBand(1)
x = reference.RasterXSize
y = reference.RasterYSize
driver= gdal.GetDriverByName('GTiff')
output = driver.Create(outputfile,x,y,1,bandreference.DataType)
output.SetGeoTransform(referenceTrans)
output.SetProjection(referenceProj)
gdal.ReprojectImage(input,output,inputProj,referenceProj,gdalconst.GRA_Bilinear)
del output
def CreateGeoTiff(outputfile, inputfile, referencefile):
with rasterio.open(inputfile) as src:
input_array = src.read((2,1,4)) #red, green, nir bands
reference = gdal.Open(referencefile, gdalconst.GA_ReadOnly)
referenceProj = reference.GetProjection()
referenceTrans = reference.GetGeoTransform()
driver = gdal.GetDriverByName('GTiff')
no_bands, cols, rows = input_array.shape
DataSet = driver.Create(outputfile, cols, rows, no_bands, gdal.GDT_Float32)
DataSet.SetGeoTransform(referenceTrans)
DataSet.SetProjection(referenceProj)
for i, image in enumerate(input_array, 1):
DataSet.GetRasterBand(i).WriteArray( image )
DataSet = None
return(gdal.Open(outputfile, gdalconst.GA_ReadOnly))
The code seems to check out, the right inputs and calling the right functions, Python however raises the TypeError mentioned above. Does anyone have an idea where it went wrong?

Error preprocessing the input data when using Tensorflow Dataset API

I have images of [64,512,5] stored in *.npy files which I convert into *.tfrecords files.
I have verified that the reading of said records corresponds correctly with what is present in the *.npy files. However, when I perform some operation on the parser, like adding 1 to each pixel of the image, the result is not the expected one. The result should be 65*512*5 = 163840 but it is 163839.99980013957 (not always the same)
I have tried to perform different operations like tf.subtract, but the results are the same.
Could someone tell me what is wrong?
import re
import ast
import sys, select
import random as rn
from glob import glob
from tqdm import tqdm
from datetime import datetime
from configparser import SafeConfigParser
import numpy as np
import numpy.ma as ma
import scipy.misc
import os.path
from os import mkdir, stat
from os.path import exists, dirname, abspath
from os.path import join as dir_join
import tensorflow as tf
''' File hierarchy
'''
_code_dir = dirname(abspath(__file__))
_python_dir = dirname(_code_dir)
_model_dir = dirname(_python_dir)
_project_dir = dirname(_model_dir)
_ml_dir = dirname(_project_dir)
_srv_dir = dirname(_ml_dir)
_root_datasets_dir = dir_join(_srv_dir,'machine_learning','data_sets/ssd_prepared')
_config_dir = dir_join(_python_dir, 'config')
'''Data sets directories
'''
THIS_DATA_SET_DIR = 'Sph_50m' #WARNING: Global variable also used in helper.py
_data_dir = dir_join(_root_datasets_dir, THIS_DATA_SET_DIR)
_data_set_dir = dir_join(_data_dir,'ImageSet')
_data_npy_dir = dir_join(_data_dir,'data')
_data_tfRecord_dir = dir_join(_data_dir,'tfRecord')
''' Configuration parser
'''
cfg_parser = SafeConfigParser()
cfg_parser.read(dir_join(_config_dir,'cfg_model.ini'))
''' Private variables
'''
_batch_size = cfg_parser.getint(section='train', option='batch_size')
_max_epoch = cfg_parser.getint(section='train', option='max_epoch')
_standarize = cfg_parser.getboolean(section='train', option='standarize_input')
_input_shape = ast.literal_eval(cfg_parser.get(section='data_shape', option='input_shape'))
_label_channel = cfg_parser.getint(section='data_shape', option='label_channel')
_track_channel = cfg_parser.getint(section='data_shape', option='track_channel')
_mask_channel = cfg_parser.getint(section='data_shape', option='mask_channel')
_data_train = cfg_parser.get(section='data_set', option='data_train')
_data_val = cfg_parser.get(section='data_set', option='data_val')
_data_test = cfg_parser.get(section='data_set', option='data_test')
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=value.reshape(-1)))
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
def _floats_feature(value):
return tf.train.Feature(float_list=tf.train.FloatList(value=value.reshape(-1)))
def numpy_to_TFRecord():
if not exists(_data_tfRecord_dir): mkdir(_data_tfRecord_dir)
for dataset in [_data_train, _data_val, _data_test]:
tfRecord_folder = dir_join(_data_tfRecord_dir, dataset)
if not exists(tfRecord_folder): mkdir(tfRecord_folder)
#Retrieve list of files
projections_dir=[]
file_ = open(dir_join(_data_set_dir, dataset+'.txt'), 'r')
for x in file_.readlines():
file_nat = x.strip()+'.npy'
filename = dir_join(_data_npy_dir, file_nat)
assert exists(filename), "{} doesn't exist".format(filename)
projections_dir.append(filename)
file_.close()
totaltfRecordSize = 0
numFile = 0
for projection_dir in tqdm(projections_dir, ncols= 100, desc = 'TFRecord {}'.format(dataset)):
scanName = projection_dir.split('/')[-1].split('.')[0]
if totaltfRecordSize > 100*(10**6) or totaltfRecordSize == 0:
# address to save the TFRecords file
train_filename = dir_join(tfRecord_folder, \
str(numFile) + '_' + dataset +'.tfrecords')
# open the TFRecords file
writer = tf.python_io.TFRecordWriter(train_filename)
numFile += 1
totaltfRecordSize = 0
# Load the image
projection = np.load(projection_dir)
image = projection[:,:,:_label_channel]
label = projection[:,:,_label_channel].astype(int)
mask = projection[:,:,_mask_channel].astype(int)
track = projection[:,:,_track_channel].astype(int)
# Create a feature
feature = {'image': _floats_feature(image),
'label': _int64_feature(label),
'mask' : _int64_feature(mask),
'track': _int64_feature(track),
'scanName': _bytes_feature(tf.compat.as_bytes(scanName))}
# Create an example protocol buffer
example = tf.train.Example(features=tf.train.Features(feature=feature))
# Serialize to string and write on the file
writer.write(example.SerializeToString())
fileSize = stat(train_filename).st_size
totaltfRecordSize += fileSize
writer.close()
sys.stdout.flush()
def readTFRecord():
# Transforms a scalar string `example_proto` into a pair of a scalar string and
# a scalar integer, representing an image and its label, respectively.
image_dim = _input_shape[0] * _input_shape[1] * _label_channel
label_dim = _input_shape[0] * _input_shape[1]
mean = np.load(dir_join(_data_dir,'mean.npy'))
std = np.load(dir_join(_data_dir,'std.npy'))
mean_tf = tf.convert_to_tensor(mean, dtype=tf.float32, name='mean')
std_tf = tf.convert_to_tensor(std, dtype=tf.float32, name='std')
with tf.variable_scope('TFRecord'):
def _parse_function(example_proto):
with tf.variable_scope('parser'):
features = {'image': tf.FixedLenFeature([image_dim], tf.float32),
'label': tf.FixedLenFeature([label_dim], tf.int64),
'mask' : tf.FixedLenFeature([label_dim], tf.int64),
'track': tf.FixedLenFeature([label_dim], tf.int64),
'scanName': tf.FixedLenFeature([], tf.string)}
parsed_features = tf.parse_single_example(example_proto, features)
# Reshape image data into the original shape
image = tf.reshape(parsed_features['image'], [_input_shape[0], _input_shape[1], _label_channel], name='image')
label = tf.reshape(parsed_features['label'], _input_shape, name='lable_reshape')
mask = tf.reshape(parsed_features['mask'], _input_shape, name='mask_reshape')
track = tf.reshape(parsed_features['track'], _input_shape, name='track_reshape')
scanName = parsed_features['scanName']
image = image + tf.constant(1., dtype=tf.float32)
return image, label, mask, track, scanName
training_filenames = glob(dir_join(_data_tfRecord_dir, _data_train, '*.tfrecords'))
validation_filenames = glob(dir_join(_data_tfRecord_dir, _data_val, '*.tfrecords'))
filenames = tf.placeholder(tf.string, shape=[None], name='filenames')
dataset = tf.data.TFRecordDataset(filenames)
dataset = dataset.map(_parse_function, num_parallel_calls=20) # Parse the record into tensors.
dataset = dataset.shuffle(buffer_size=10000)
dataset = dataset.batch(_batch_size, drop_remainder=True)
dataset = dataset.prefetch(buffer_size=10)
iterator = dataset.make_initializable_iterator()
next = iterator.get_next()
sess = tf.Session()
while True:
sess.run(iterator.initializer, feed_dict={filenames: training_filenames})
try:
img, _, _, _, scanX = sess.run(next)
for i, scan in enumerate(scanX):
print(scan.decode("utf-8"))
projection = np.load(dir_join(_data_npy_dir, scan.decode("utf-8") + '.npy'))
imagenp = projection[:,:,:_label_channel]
if np.abs(np.sum(img[i,...] - imagenp)) > 0.:
print(np.sum(img[i,...] - imagenp))
except tf.errors.OutOfRangeError:
break
return training_filenames, validation_filenames, filenames, iterator
if __name__ == '__main__':
numpy_to_TFRecord()
readTFRecord()
The test I'm doing in the previous code is to convert the *.npy files to *.tfrecords. Then, I compare the *.trecords with the *.npy. The value should be 0 if both images were identical.
img, _, _, _, scanX = sess.run(next)
for i, scan in enumerate(scanX):
print(scan.decode("utf-8"))
projection = np.load(dir_join(_data_npy_dir, scan.decode("utf-8") + '.npy'))
imagenp = projection[:,:,:_label_channel]
print(np.sum(img[i,...] - imagenp))
If the data is not preprocessed, these images are the same, however, if we perform some kind of transformation, the results do not match what was expected. In this case we are adding 1 to each pixel of the image, so the total difference should be 64 * 512 * 5.
image = image + tf.constant(1., dtype=tf.float32)
I would like to solve this error, since so far I have not been able to obtain the results obtained by my neural network using feed_dict instead of Tensorflow Dataset API, and this is the only point where I can observe a difference in the input data.

Basic a tiff processing with photoshop using python

I need to write a script that does the following:
# open a tiff
# get it's dpi, width, height and colorspace
# set the dpi, width, height and colorspace
# and then save the tiff out with no compression and no layers.
So far I've gotten:
from win32com.client.dynamic import Dispatch
ps = Dispatch( "Photoshop.Application" )
file_path = "C:\\Users\\me\\myImg.tif"
doc = ps.Open( file_path )
dpi = doc.Resolution
width = doc.Width # in cm
height = doc.Height # in cm
# up to here the code works, but then I try
doc.Resolution = 72
ps.ResizeImage( 120 , 120 )
ps.PsColorSpaceType( 3 ) # psSRGB
ps.TiffSaveOptions.ImageCompression = 1 # psNoTIFFCompression
ps.TiffSaveOptions.Layers = False
ps.Save()
# and this last section fails
Please help, any ideas, tips, soultions would be greatly appreciated :D

After a lot of googeling and some trial and error and then even more trial and error I've managed to come up with the code below.
Hope this can help someone else.
Code
file_path = "C:\\Users\\me\\myImg.tif"
color_settings = "North America General Purpose 2"
from win32com.client.dynamic import Dispatch
ps_app = Dispatch( "Photoshop.Application" )
# set photoshop to use pixels as dimensions
ps_app.Preferences.RulerUnits = 1 # 'for PsUnits --> 1 (psPixels)
ps_app.Preferences.TypeUnits = 1 # 'for PsTypeUnits --> 1 (psPixels)
doc = ps_app.Open( file_path ) # Open a file and store open file as doc
dpi = doc.Resolution
width = doc.Width
height = doc.Height
cor_res = 1024
ps_app.ChangeColorSettings( color_settings )
doc.ResizeImage( cor_res , cor_res , 72 )
options = Dispatch('Photoshop.TiffSaveOptions')
options.ImageCompression = 1 # ps_appNoTIFFCompression
options.Layers = False # no layers
doc.SaveAs( file_path , options ) # Save with specified options
doc.Close( 2 ) # psDoNotSaveChanges