I want to train a ssd-inception-v2 model from Tensorflow Object Detection API. The training dataset I want to use is a bunch of cropped images with different sizes without bounding boxes, as the crop itself is the bounding boxes.
I followed the create_pascal_tf_record.py example replacing the bounding boxes and classifications portion accordingly to generate the TFRecords as follows:
def dict_to_tf_example(imagepath, label):
image = Image.open(imagepath)
if image.format != 'JPEG':
print("Skipping file: " + imagepath)
return
img = np.array(image)
with tf.gfile.GFile(imagepath, 'rb') as fid:
encoded_jpg = fid.read()
# The reason to store image sizes was demonstrated
# in the previous example -- we have to know sizes
# of images to later read raw serialized string,
# convert to 1d array and convert to respective
# shape that image used to have.
height = img.shape[0]
width = img.shape[1]
key = hashlib.sha256(encoded_jpg).hexdigest()
# Put in the original images into array
# Just for future check for correctness
xmin = [5.0/100.0]
ymin = [5.0/100.0]
xmax = [95.0/100.0]
ymax = [95.0/100.0]
class_text = [label['name'].encode('utf8')]
classes = [label['id']]
example = tf.train.Example(features=tf.train.Features(feature={
'image/height':dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(imagepath.encode('utf8')),
'image/source_id': dataset_util.bytes_feature(imagepath.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/class/text': dataset_util.bytes_list_feature(class_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
'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)
}))
return example
def main(_):
data_dir = FLAGS.data_dir
output_path = os.path.join(data_dir,FLAGS.output_path + '.record')
writer = tf.python_io.TFRecordWriter(output_path)
label_map = label_map_util.load_labelmap(FLAGS.label_map_path)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=80, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
category_list = os.listdir(data_dir)
gen = (category for category in categories if category['name'] in category_list)
for category in gen:
examples_path = os.path.join(data_dir,category['name'])
examples_list = os.listdir(examples_path)
for example in examples_list:
imagepath = os.path.join(examples_path,example)
tf_example = dict_to_tf_example(imagepath,category)
writer.write(tf_example.SerializeToString())
# print(tf_example)
writer.close()
The bounding box is hard coded encompassing the whole image. The labels are given accordingly to its corresponding directory. I am using the mscoco_label_map.pbxt for labeling and the ssd_inception_v2_pets.config as base for my pipeline.
I trained and froze the model to use with the jupyter notebook example. However, the final result is a single box surrounding the whole image. Any idea on what went wrong?