Add PaddlePaddle export and inference (#9240)
* Add PaddlePaddle Model Export Test on Yolov5 DockerEnviroment with paddlepaddle-gpu v2.2 Signed-off-by: Katteria <39751846+kisaragychihaya@users.noreply.github.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Cleanup Paddle Export Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update common.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Update export.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update export.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Update export.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Update export.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Use PyTorch2Paddle Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Paddle no longer requires ONNX Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Update export.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Update export.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update benchmarks.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Add inference code of PaddlePaddle Signed-off-by: Katteria <39751846+kisaragychihaya@users.noreply.github.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update common.py Signed-off-by: Katteria <39751846+kisaragychihaya@users.noreply.github.com> * Update common.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Add paddlepaddle-gpu install if cuda Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update common.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Update common.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> * Update common.py Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> Signed-off-by: Katteria <39751846+kisaragychihaya@users.noreply.github.com> Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
3 files changed
+111
-75
No files matched your search
+66
-46
@@ -320,14 +320,16 @@ class DetectMultiBackend(nn.Module):
|
||||
# TensorFlow GraphDef: *.pb
|
||||
# TensorFlow Lite: *.tflite
|
||||
# TensorFlow Edge TPU: *_edgetpu.tflite
|
||||
# PaddlePaddle: *_paddle_model
|
||||
from models.experimental import attempt_download, attempt_load # scoped to avoid circular import
|
||||
|
||||
super().__init__()
|
||||
w = str(weights[0] if isinstance(weights, list) else weights)
|
||||
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = self._model_type(w) # get backend
|
||||
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle = self._model_type(w) # type
|
||||
w = attempt_download(w) # download if not local
|
||||
fp16 &= pt or jit or onnx or engine # FP16
|
||||
stride = 32 # default stride
|
||||
cuda = torch.cuda.is_available() and device.type != 'cpu' # use CUDA
|
||||
|
||||
if pt: # PyTorch
|
||||
model = attempt_load(weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse)
|
||||
@@ -351,7 +353,6 @@ class DetectMultiBackend(nn.Module):
|
||||
net = cv2.dnn.readNetFromONNX(w)
|
||||
elif onnx: # ONNX Runtime
|
||||
LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
|
||||
cuda = torch.cuda.is_available() and device.type != 'cpu'
|
||||
check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
|
||||
import onnxruntime
|
||||
providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
|
||||
@@ -408,48 +409,60 @@ class DetectMultiBackend(nn.Module):
|
||||
LOGGER.info(f'Loading {w} for CoreML inference...')
|
||||
import coremltools as ct
|
||||
model = ct.models.MLModel(w)
|
||||
else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
|
||||
if saved_model: # SavedModel
|
||||
LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
|
||||
import tensorflow as tf
|
||||
keras = False # assume TF1 saved_model
|
||||
model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w)
|
||||
elif pb: # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
|
||||
LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
|
||||
import tensorflow as tf
|
||||
elif saved_model: # TF SavedModel
|
||||
LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
|
||||
import tensorflow as tf
|
||||
keras = False # assume TF1 saved_model
|
||||
model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w)
|
||||
elif pb: # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
|
||||
LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
|
||||
import tensorflow as tf
|
||||
|
||||
def wrap_frozen_graph(gd, inputs, outputs):
|
||||
x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped
|
||||
ge = x.graph.as_graph_element
|
||||
return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs))
|
||||
def wrap_frozen_graph(gd, inputs, outputs):
|
||||
x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped
|
||||
ge = x.graph.as_graph_element
|
||||
return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs))
|
||||
|
||||
gd = tf.Graph().as_graph_def() # graph_def
|
||||
with open(w, 'rb') as f:
|
||||
gd.ParseFromString(f.read())
|
||||
frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs="Identity:0")
|
||||
elif tflite or edgetpu: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
|
||||
try: # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
|
||||
from tflite_runtime.interpreter import Interpreter, load_delegate
|
||||
except ImportError:
|
||||
import tensorflow as tf
|
||||
Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate,
|
||||
if edgetpu: # Edge TPU https://coral.ai/software/#edgetpu-runtime
|
||||
LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...')
|
||||
delegate = {
|
||||
'Linux': 'libedgetpu.so.1',
|
||||
'Darwin': 'libedgetpu.1.dylib',
|
||||
'Windows': 'edgetpu.dll'}[platform.system()]
|
||||
interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
|
||||
else: # Lite
|
||||
LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
|
||||
interpreter = Interpreter(model_path=w) # load TFLite model
|
||||
interpreter.allocate_tensors() # allocate
|
||||
input_details = interpreter.get_input_details() # inputs
|
||||
output_details = interpreter.get_output_details() # outputs
|
||||
elif tfjs:
|
||||
raise NotImplementedError('ERROR: YOLOv5 TF.js inference is not supported')
|
||||
else:
|
||||
raise NotImplementedError(f'ERROR: {w} is not a supported format')
|
||||
gd = tf.Graph().as_graph_def() # TF GraphDef
|
||||
with open(w, 'rb') as f:
|
||||
gd.ParseFromString(f.read())
|
||||
frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs="Identity:0")
|
||||
elif tflite or edgetpu: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
|
||||
try: # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
|
||||
from tflite_runtime.interpreter import Interpreter, load_delegate
|
||||
except ImportError:
|
||||
import tensorflow as tf
|
||||
Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate,
|
||||
if edgetpu: # TF Edge TPU https://coral.ai/software/#edgetpu-runtime
|
||||
LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...')
|
||||
delegate = {
|
||||
'Linux': 'libedgetpu.so.1',
|
||||
'Darwin': 'libedgetpu.1.dylib',
|
||||
'Windows': 'edgetpu.dll'}[platform.system()]
|
||||
interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
|
||||
else: # TFLite
|
||||
LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
|
||||
interpreter = Interpreter(model_path=w) # load TFLite model
|
||||
interpreter.allocate_tensors() # allocate
|
||||
input_details = interpreter.get_input_details() # inputs
|
||||
output_details = interpreter.get_output_details() # outputs
|
||||
elif tfjs: # TF.js
|
||||
raise NotImplementedError('ERROR: YOLOv5 TF.js inference is not supported')
|
||||
elif paddle: # PaddlePaddle
|
||||
LOGGER.info(f'Loading {w} for PaddlePaddle inference...')
|
||||
check_requirements('paddlepaddle-gpu' if cuda else 'paddlepaddle')
|
||||
import paddle.inference as pdi
|
||||
if not Path(w).is_file(): # if not *.pdmodel
|
||||
w = next(Path(w).rglob('*.pdmodel')) # get *.xml file from *_openvino_model dir
|
||||
weights = Path(w).with_suffix('.pdiparams')
|
||||
config = pdi.Config(str(w), str(weights))
|
||||
if cuda:
|
||||
config.enable_use_gpu(memory_pool_init_size_mb=2048, device_id=0)
|
||||
predictor = pdi.create_predictor(config)
|
||||
input_names = predictor.get_input_names()
|
||||
input_handle = predictor.get_input_handle(input_names[0])
|
||||
else:
|
||||
raise NotImplementedError(f'ERROR: {w} is not a supported format')
|
||||
|
||||
# class names
|
||||
if 'names' not in locals():
|
||||
@@ -502,6 +515,13 @@ class DetectMultiBackend(nn.Module):
|
||||
else:
|
||||
k = 'var_' + str(sorted(int(k.replace('var_', '')) for k in y)[-1]) # output key
|
||||
y = y[k] # output
|
||||
elif self.paddle: # PaddlePaddle
|
||||
im = im.cpu().numpy().astype("float32")
|
||||
self.input_handle.copy_from_cpu(im)
|
||||
self.predictor.run()
|
||||
output_names = self.predictor.get_output_names()
|
||||
output_handle = self.predictor.get_output_handle(output_names[0])
|
||||
y = output_handle.copy_to_cpu()
|
||||
else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
|
||||
im = im.permute(0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3)
|
||||
if self.saved_model: # SavedModel
|
||||
@@ -542,13 +562,13 @@ class DetectMultiBackend(nn.Module):
|
||||
def _model_type(p='path/to/model.pt'):
|
||||
# Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx
|
||||
from export import export_formats
|
||||
suffixes = list(export_formats().Suffix) + ['.xml'] # export suffixes
|
||||
check_suffix(p, suffixes) # checks
|
||||
sf = list(export_formats().Suffix) + ['.xml'] # export suffixes
|
||||
check_suffix(p, sf) # checks
|
||||
p = Path(p).name # eliminate trailing separators
|
||||
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, xml2 = (s in p for s in suffixes)
|
||||
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, xml2 = (s in p for s in sf)
|
||||
xml |= xml2 # *_openvino_model or *.xml
|
||||
tflite &= not edgetpu # *.tflite
|
||||
return pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs
|
||||
return pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle
|
||||
|
||||
@staticmethod
|
||||
def _load_metadata(f=Path('path/to/meta.yaml')):
|
||||
|
||||
Reference in new issue
Block a user