def deserialize(self, stream, content_type):
"""Read a recordio-protobuf stream from a SageMaker Semantic Segmentation algorithm endpoint
Args:
stream (botocore.response.StreamingBody): A stream of bytes.
content_type (str): The MIME type of the data.
Returns:
array: numpy array of class probabilities per pixel
"""
try:
# Unpack the RecordIO wrapper first:
reccontent = HackyProtobufDeserializer.next_recordio_record(stream)
# Then load the protocol buffer:
rec = Record()
print("Parsing protobuf...")
protobuf = rec.ParseFromString(reccontent)
# Then read the two provided tensors `target` (predictions) and `shape`, squeeze out any batch
# dimensions (since we'll always be predicting on a single image) and shape target appropriately:
print("Fetching Tensors...")
values = list(rec.features["target"].float32_tensor.values)
shape = list(rec.features["shape"].int32_tensor.values)
print("reshaping arrays...")
shape = squeeze(shape)
mask = reshape(array(values), shape)
return squeeze(mask, axis=0)
finally:
stream.close()
def read_records(file):
"""Eagerly read a collection of amazon Record protobuf objects from file."""
records = []
for record_data in read_recordio(file):
record = Record()
record.ParseFromString(record_data)
records.append(record)
return records
def test_serializer():
s = RecordSerializer()
array_data = [[1.0, 2.0, 3.0], [10.0, 20.0, 30.0]]
buf = s.serialize(np.array(array_data))
for record_data, expected in zip(read_recordio(buf), array_data):
record = Record()
record.ParseFromString(record_data)
assert record.features["values"].float64_tensor.values == expected
def test_serializer_accepts_one_dimensional_array():
s = RecordSerializer()
array_data = [1.0, 2.0, 3.0]
buf = s.serialize(np.array(array_data))
record_data = next(read_recordio(buf))
record = Record()
record.ParseFromString(record_data)
assert record.features["values"].float64_tensor.values == array_data
def read_pipe(pipe):
with open(pipe,'rb') as f:
for rec in read_recordio(f):
print("read record")
print(rec)
record = Record()
record.ParseFromString(rec)
print("record parsed")
print(record)
def test_int_write_numpy_to_dense_tensor():
array_data = [[1, 2, 3], [10, 20, 3]]
array = np.array(array_data)
with tempfile.TemporaryFile() as f:
write_numpy_to_dense_tensor(f, array)
f.seek(0)
for record_data, expected in zip(read_recordio(f), array_data):
record = Record()
record.ParseFromString(record_data)
assert record.features["values"].int32_tensor.values == expected
def test_float32_write_numpy_to_dense_tensor():
array_data = [[1.0, 2.0, 3.0], [10.0, 20.0, 30.0]]
array = np.array(array_data).astype(np.dtype("float32"))
with tempfile.TemporaryFile() as f:
write_numpy_to_dense_tensor(f, array)
f.seek(0)
for record_data, expected in zip(read_recordio(f), array_data):
record = Record()
record.ParseFromString(record_data)
assert record.features["values"].float32_tensor.values == expected
def test_float32_label():
array_data = [[1, 2, 3], [10, 20, 3]]
array = np.array(array_data)
label_data = np.array([99, 98, 97]).astype(np.dtype('float32'))
with tempfile.TemporaryFile() as f:
write_numpy_to_dense_tensor(f, array, label_data)
f.seek(0)
for record_data, expected, label in zip(_read_recordio(f), array_data, label_data):
record = Record()
record.ParseFromString(record_data)
assert record.features["values"].int32_tensor.values == expected
assert record.label["values"].float32_tensor.values == [label]
def test_dense_int_write_spmatrix_to_sparse_tensor():
array_data = [[1.0, 2.0, 3.0], [10.0, 20.0, 30.0]]
keys_data = [[0, 1, 2], [0, 1, 2]]
array = coo_matrix(np.array(array_data).astype(np.dtype('int')))
with tempfile.TemporaryFile() as f:
write_spmatrix_to_sparse_tensor(f, array)
f.seek(0)
for record_data, expected_data, expected_keys in zip(read_recordio(f), array_data, keys_data):
record = Record()
record.ParseFromString(record_data)
assert record.features["values"].int32_tensor.values == expected_data
assert record.features["values"].int32_tensor.keys == expected_keys
assert record.features["values"].int32_tensor.shape == [len(expected_data)]
def test_dense_float64_spmatrix_to_sparse_label():
array_data = [[1, 2, 3], [10, 20, 3]]
keys_data = [[0, 1, 2], [0, 1, 2]]
array = coo_matrix(np.array(array_data).astype("float64"))
label_data = np.array([99, 98, 97])
with tempfile.TemporaryFile() as f:
write_spmatrix_to_sparse_tensor(f, array, label_data)
f.seek(0)
for record_data, expected_data, expected_keys, label in zip(
read_recordio(f), array_data, keys_data, label_data
):
record = Record()
record.ParseFromString(record_data)
assert record.features["values"].float64_tensor.values == expected_data
assert record.features["values"].float64_tensor.keys == expected_keys
assert record.label["values"].int32_tensor.values == [label]
assert record.features["values"].float64_tensor.shape == [len(expected_data)]
def infer(self, filename, output_folder, endpoint, show_image):
"""
:param filename:
:param output_folder:
:param endpoint:
:param show_image:
:return:
"""
output_filename = os.path.splitext(filename)[0]
output_filename = os.path.basename(output_filename)
output_filename = os.path.join(output_folder, output_filename + '_inference.png')
runtime = boto3.Session().client('sagemaker-runtime')
image = pillow.Image.open(filename)
image.thumbnail([800, 600], pillow.Image.ANTIALIAS)
image.save(filename, "JPEG")
with open(filename, 'rb') as f:
payload = f.read()
payload = bytearray(payload)
response = runtime.invoke_endpoint(EndpointName=endpoint, ContentType='application/x-image', Body=payload)
results_file = 'results.rec'
with open(results_file, 'wb') as f:
f.write(response['Body'].read())
rec = Record()
recordio = mx.recordio.MXRecordIO(results_file, 'r')
protobuf = rec.ParseFromString(recordio.read())
values = list(rec.features["target"].float32_tensor.values)
shape = list(rec.features["shape"].int32_tensor.values)
shape = np.squeeze(shape)
mask = np.reshape(np.array(values), shape)
mask = np.squeeze(mask, axis=0)
pred_map = np.argmax(mask, axis=0)
if show_image is True:
utils_obj = utils.Utils()
utils_obj.show_image(pred_map)
plt.imshow(pred_map, vmin=0, vmax=settings.HYPER['num_classes'] - 1, cmap='jet')
plt.savefig(output_filename)
def test_sparse_int_write_spmatrix_to_sparse_tensor():
n = 4
array_data = [[1.0, 2.0], [10.0, 30.0], [100.0, 200.0, 300.0, 400.0], [1000.0, 2000.0, 3000.0]]
keys_data = [[0, 1], [1, 2], [0, 1, 2, 3], [0, 2, 3]]
flatten_data = list(itertools.chain.from_iterable(array_data))
y_indices = list(itertools.chain.from_iterable(keys_data))
x_indices = [[i] * len(keys_data[i]) for i in range(len(keys_data))]
x_indices = list(itertools.chain.from_iterable(x_indices))
array = coo_matrix((flatten_data, (x_indices, y_indices)), dtype='int')
with tempfile.TemporaryFile() as f:
write_spmatrix_to_sparse_tensor(f, array)
f.seek(0)
for record_data, expected_data, expected_keys in zip(read_recordio(f), array_data, keys_data):
record = Record()
record.ParseFromString(record_data)
assert record.features["values"].int32_tensor.values == expected_data
assert record.features["values"].int32_tensor.keys == expected_keys
assert record.features["values"].int32_tensor.shape == [n]