我正在使用python包midi2audio将midi文件转换为WAV。
运行：
filepath = 'C:/Users/Jack/Documents/GaTech/Research/Code/Data/Midi/C4/test12.mid'
soundfont = 'C:/Users/Jack/Downloads/weedsgm3.sf2'
fs = FluidSynth(soundfont)
if os.path.isfile(filepath):
print('The File Exists')
else:
print('The File does not exist')
fs.midi_to_audio(filepath, 'output.wav')
输出：
The File Exists
FileNotFoundError: [WinError 2] The system cannot find the file specified
要清楚错误是引用filepath中指定的文件而不是soundfont。包装上的文档很少，所以我不知道该怎么做。
有没有midi2audio经验的人遇到过同样的问题，知道问题的根源是什么？
答案 0 :(得分：1)
def create_tf_example(image,
annotations_list,
image_dir,
category_index,
include_masks=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.
Returns:
example: The converted tf.Example
num_annotations_skipped: Number of (invalid) annotations that were ignored.
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 = []
num_annotations_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
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_id = int(object_annotations['category_id'])
category_ids.append(category_id)
category_names.append(category_index[category_id]['name'].encode('utf8'))
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())
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/label':
dataset_util.int64_list_feature(category_ids),
'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))
example = tf.train.Example(features=tf.train.Features(feature=feature_dict))
return key, example, num_annotations_skipped
def _create_tf_record_from_coco_annotations(
annotations_file, image_dir, output_path, include_masks):
"""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.
"""
with tf.gfile.GFile(annotations_file, 'r') as fid:
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:
tf.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] = []
tf.logging.info('%d images are missing annotations.',
missing_annotation_count)
tf.logging.info('writing to output path: %s', output_path)
writer = tf.python_io.TFRecordWriter(output_path)
total_num_annotations_skipped = 0
for idx, image in enumerate(images):
if idx % 100 == 0:
tf.logging.info('On image %d of %d', idx, len(images))
annotations_list = annotations_index[image['id']]
_, tf_example, num_annotations_skipped = create_tf_example(
image, annotations_list, image_dir, category_index, include_masks)
total_num_annotations_skipped += num_annotations_skipped
writer.write(tf_example.SerializeToString())
writer.close()
tf.logging.info('Finished writing, skipped %d annotations.',
total_num_annotations_skipped)
这将创建一个fs = FluidSynth()
对象，其中包含所有构造函数参数的默认值。
FluidSynth这将创建第二个FluidSynth(sample_rate=22050)
对象。对象引用未分配给任何变量，因此会立即丢弃。
FluidSynth第三个目标。
FluidSynth(soundfont)
fs.midi_to_audio(filepath, 'output.wav')
引用的对象使用默认的声音字体和默认采样率。
您必须立即将所有参数提供给构造函数：
fs（指定输出文件的完整路径可能是个好主意。）