def dispatch_keras_h5_to_tensorflowjs_conversion(h5_path,
output_dir=None,
quantization_dtype=None,
split_weights_by_layer=False):
"""Converts a Keras HDF5 saved-model file to TensorFlow.js format.
Auto-detects saved_model versus weights-only and generates the correct
json in either case. This function accepts Keras HDF5 files in two formats:
- A weights-only HDF5 (e.g., generated with Keras Model's `save_weights()`
method),
- A topology+weights combined HDF5 (e.g., generated with
`keras.model.save_model`).
Args:
h5_path: path to an HDF5 file containing keras model data as a `str`.
output_dir: Output directory to which the TensorFlow.js-format model JSON
file and weights files will be written. If the directory does not exist,
it will be created.
quantization_dtype: The quantized data type to store the weights in
(Default: `None`).
split_weights_by_layer: Whether to split the weights into separate weight
groups (corresponding to separate binary weight files) layer by layer
(Default: `False`).
Returns:
(model_json, groups)
model_json: a json dictionary (empty if unused) for model topology.
If `h5_path` points to a weights-only HDF5 file, this return value
will be `None`.
groups: an array of weight_groups as defined in tfjs weights_writer.
"""
if not os.path.exists(h5_path):
raise ValueError('Nonexistent path to HDF5 file: %s' % h5_path)
elif os.path.isdir(h5_path):
raise ValueError(
'Expected path to point to an HDF5 file, but it points to a '
'directory: %s' % h5_path)
converter = keras_h5_conversion.HDF5Converter()
h5_file = h5py.File(h5_path)
if 'layer_names' in h5_file.attrs:
model_json = None
groups = converter.h5_weights_to_tfjs_format(
h5_file, split_by_layer=split_weights_by_layer)
else:
model_json, groups = converter.h5_merged_saved_model_to_tfjs_format(
h5_file, split_by_layer=split_weights_by_layer)
if output_dir:
if os.path.isfile(output_dir):
raise ValueError('Output path "%s" already exists as a file' %
output_dir)
elif not os.path.isdir(output_dir):
os.makedirs(output_dir)
converter.write_artifacts(model_json, groups, output_dir,
quantization_dtype)
return model_json, groups
def dispatch_pykeras_conversion(h5_path, output_dir=None):
"""Converts a Keras HDF5 saved-model file to TensorFlow.js format.
Auto-detects saved_model versus weights-only and generates the correct
json in either case. This function accepts Keras HDF5 files in two formats:
- A weights-only HDF5 (e.g., generated with Keras Model's `save_weights()`
method),
- A topology+weights combined HDF5 (e.g., generated with
`keras.model.save_model`).
Args:
h5_path: path to an HDF5 file containing keras model data as a `str`.
output_dir: Output directory to which the TensorFlow.js-format model JSON
file and weights files will be written. If the directory does not exist,
it will be created.
Returns:
(model_json, groups)
model_json: a json dictionary (empty if unused) for model topology.
If `h5_path` points to a weights-only HDF5 file, this return value
will be `None`.
groups: an array of weight_groups as defined in tfjs weights_writer.
"""
converter = keras_h5_conversion.HDF5Converter()
h5_file = h5py.File(h5_path)
if 'layer_names' in h5_file.attrs:
model_json = None
groups = converter.h5_weights_to_tfjs_format(h5_file)
else:
model_json, groups = converter.h5_merged_saved_model_to_tfjs_format(
h5_file)
if output_dir:
if os.path.isfile(output_dir):
raise ValueError(
'Output path "%s" already exists as a file' % output_dir)
elif not os.path.isdir(output_dir):
os.makedirs(output_dir)
converter.write_artifacts(model_json, groups, output_dir)
return model_json, groups
def setUp(self):
self._tmp_dir = tempfile.mkdtemp()
self._converter = keras_h5_conversion.HDF5Converter()
super(ConvertH5WeightsTest, self).setUp()