2021SC@SDUSC山东大学软件学院软件工程应用与实践——yolov5代码分析——第三篇——export.py(1)
2021SC@SDUSC
目录
导入第三方库
导出操作
export_torchscript函数
export_onnx函数
export_coreml函数
export_saved_model函数
export_pb函数
export_tflite函数
export_tfjs函数
代码分析
parse_opt函数
main函数
导入第三方库
import argparse # 解析命令行参数模块
import subprocess
import sys # sys系统模块，包含了与python解释器和它的环境有关的函数
import time # 时间模块
from pathlib import Path # path将str转化为path对象，使字符串路径易于操作
import torch # PyTorch深度学习模块
import torch.nn as nn
from torch.utils.mobile_optimizer import optimize_for_mobile
FILE = Path(__file__).resolve()
ROOT = FILE.parents[0] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
from models.common import Conv
from models.experimental import attempt_load
from models.yolo import Detect
from utils.activations import SiLU
from utils.datasets import LoadImages
from utils.general import colorstr, check_dataset, check_img_size, check_requirements, file_size, print_args, \
set_logging, url2file
from utils.torch_utils import select_device导出操作
def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:'))
def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:'))
def export_coreml
def export_saved_model(model, im, file, dynamic,
tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
conf_thres=0.25, prefix=colorstr('TensorFlow saved_model:'))
def export_pb(keras_model, im, file, prefix=colorstr('TensorFlow GraphDef:'))
def export_tflite(keras_model, im, file, int8, data, ncalib, prefix=colorstr('TensorFlow Lite:'))
def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:'))
以上函数用于yolov5导出，此处不做过于详细的分析
export_torchscript函数
def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')):
# YOLOv5 TorchScript model export
try:
print(f'\n{prefix} starting export with torch {torch.__version__}...')
f = file.with_suffix('.torchscript.pt')
ts = torch.jit.trace(model, im, strict=False)
(optimize_for_mobile(ts) if optimize else ts).save(f)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'{prefix} export failure: {e}')导出模型为TorchScript。
如果报错TorchScript: export failure: save(): incompatible function arguments.可在f = file.with_suffix(’.torchscript.pt’)后加上这句代码f = str(f)试试
export_onnx函数
def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:')):
# YOLOv5 ONNX export
try:
check_requirements(('onnx',))
import onnx
print(f'\n{prefix} starting export with onnx {onnx.__version__}...')
f = file.with_suffix('.onnx')
torch.onnx.export(model, im, f, verbose=False, opset_version=opset,
training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
do_constant_folding=not train,
input_names=['images'],
output_names=['output'],
dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # shape(1,3,640,640)
'output': {0: 'batch', 1: 'anchors'} # shape(1,25200,85)
} if dynamic else None)
# Checks
model_onnx = onnx.load(f) # load onnx model
onnx.checker.check_model(model_onnx) # check onnx model
# print(onnx.helper.printable_graph(model_onnx.graph)) # print
# Simplify
if simplify:
try:
check_requirements(('onnx-simplifier',))
import onnxsim
print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
model_onnx, check = onnxsim.simplify(
model_onnx,
dynamic_input_shape=dynamic,
input_shapes={'images': list(im.shape)} if dynamic else None)
assert check, 'assert check failed'
onnx.save(model_onnx, f)
except Exception as e:
print(f'{prefix} simplifier failure: {e}')
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
print(f"{prefix} run --dynamic ONNX model inference with: 'python detect.py --weights {f}'")
except Exception as e:
print(f'{prefix} export failure: {e}')导出模型为oonx模型。
model (torch.nn.Module)：要导出的模型.
im：模型的输入
export_coreml函数
def export_coreml(model, im, file, prefix=colorstr('CoreML:')):
# YOLOv5 CoreML export
ct_model = None
try:
check_requirements(('coremltools',))
import coremltools as ct
print(f'\n{prefix} starting export with coremltools {ct.__version__}...')
f = file.with_suffix('.mlmodel')
model.train() # CoreML exports should be placed in model.train() mode
ts = torch.jit.trace(model, im, strict=False) # TorchScript model
ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255.0, bias=[0, 0, 0])])
ct_model.save(f)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'\n{prefix} export failure: {e}')
return ct_model将模型导出为coreML模型
model (torch.nn.Module)：要导出的模型.
im：模型的输入
export_saved_model函数
def export_saved_model(model, im, file, dynamic,
tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
conf_thres=0.25, prefix=colorstr('TensorFlow saved_model:')):
# YOLOv5 TensorFlow saved_model export
keras_model = None
try:
import tensorflow as tf
from tensorflow import keras
from models.tf import TFModel, TFDetect
print(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
f = str(file).replace('.pt', '_saved_model')
batch_size, ch, *imgsz = list(im.shape) # BCHW
tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
im = tf.zeros((batch_size, *imgsz, 3)) # BHWC order for TensorFlow
y = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
inputs = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
keras_model = keras.Model(inputs=inputs, outputs=outputs)
keras_model.trainable = False
keras_model.summary()
keras_model.save(f, save_format='tf')
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'\n{prefix} export failure: {e}')
return keras_modelmodel (torch.nn.Module)：要导出的模型.
im：模型的输入
export_pb函数
def export_pb(keras_model, im, file, prefix=colorstr('TensorFlow GraphDef:')):
# YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
try:
import tensorflow as tf
from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
print(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
f = file.with_suffix('.pb')
m = tf.function(lambda x: keras_model(x)) # full model
m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype))
frozen_func = convert_variables_to_constants_v2(m)
frozen_func.graph.as_graph_def()
tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'\n{prefix} export failure: {e}')保存模型为pb格式
export_tflite函数
def export_tflite(keras_model, im, file, int8, data, ncalib, prefix=colorstr('TensorFlow Lite:')):
# YOLOv5 TensorFlow Lite export
try:
import tensorflow as tf
from models.tf import representative_dataset_gen
print(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
batch_size, ch, *imgsz = list(im.shape) # BCHW
f = str(file).replace('.pt', '-fp16.tflite')
converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
converter.target_spec.supported_types = [tf.float16]
converter.optimizations = [tf.lite.Optimize.DEFAULT]
if int8:
dataset = LoadImages(check_dataset(data)['train'], img_size=imgsz, auto=False) # representative data
converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
converter.target_spec.supported_types = []
converter.inference_input_type = tf.uint8 # or tf.int8
converter.inference_output_type = tf.uint8 # or tf.int8
converter.experimental_new_quantizer = False
f = str(file).replace('.pt', '-int8.tflite')
tflite_model = converter.convert()
open(f, "wb").write(tflite_model)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'\n{prefix} export failure: {e}')将模型保存为tflite轻量级推理库
export_tfjs函数
def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')):
# YOLOv5 TensorFlow.js export
try:
check_requirements(('tensorflowjs',))
import tensorflowjs as tfjs
print(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...')
f = str(file).replace('.pt', '_web_model') # js dir
f_pb = file.with_suffix('.pb') # *.pb path
cmd = f"tensorflowjs_converter --input_format=tf_frozen_model " \
f"--output_node_names='Identity,Identity_1,Identity_2,Identity_3' {f_pb} {f}"
subprocess.run(cmd, shell=True)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'\n{prefix} export failure: {e}')