yolov7 mask训练笔记

目录

训练过程：

yaml文件解析

关于预训练：

dataloader

coco128-seg.yaml

segments 格式：

导出onnx

onnx结构：

---

训练过程：

https://github.com/chelsea456/yolov7_mask/tree/main/yolov7_mask

yaml文件解析

3、backbone（骨干网络*）
# yolov7 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [32, 3, 1]],  # 0
  
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2      
   [-1, 1, Conv, [64, 3, 1]],
   
   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4  
   [-1, 1, Conv, [64, 1, 1]],
   [-2, 1, Conv, [64, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]],  # 11
         
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 16-P3/8  
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]],  # 24
         
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 29-P4/16  
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 37
         
   [-1, 1, MP, []],
   [-1, 1, Conv, [512, 1, 1]],
   [-3, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 42-P5/32  
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 50
  ]
from 表示该层的输入从哪来。-1表示输入取自上一层，-2表示上两层，3表示第3层（从0开始数），[-1, 4]表示取自上一层和第4层，依次类推。。。。。
number 表示该层模块堆叠的次数，对于C3、BottleneckCSP等模块，表示其子模块的堆叠，具体细节可以查看源代码。当然最终的次数还要乘上depth_multiple系数。
module 表示该层的模块是什么类型。Conv就是卷积+BN+激活模块。所有的模块在 model/common.py 中都有定义。
args 表示输入到模块的参数。例如Conv：[128, 3, 2] 表示输出通道128，卷积核尺寸3，strid=2，当然最终的输出通道数还要乘上 width_multiple，对于其他模块，第一个参数值一般都是指输出通道数，具体细节可以看 model/common.py 中的定义。
 
原文链接：https://blog.csdn.net/weixin_43397302/article/details/126708227

关于预训练：

提高了3个预训练：

yolov5s-seg.pt

yolov7-seg.pt

yolov7x-seg.pt

python segment/train.py --data coco.yaml --batch 16 --weights '' --cfg yolov7-seg.yaml --epochs 300 --name yolov7-seg --img 640 --hyp hyp.scratch-high.yaml

dataloader

labels, shapes, self.segments = zip(*cache.values())

image_detect/coco128-seg.yaml at master · HoyoenKim/image_detect · GitHub

coco128-seg.yaml

download: https://ultralytics.com/assets/coco128-seg.zip

# YOLOv5 by Ultralytics, GPL-3.0 license
# COCO128-seg dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
# Example usage: python train.py --data coco128.yaml
# parent
# ├── yolov5
# └── datasets
#     └── coco128-seg  ← downloads here (7 MB)


# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/coco128-seg  # dataset root dir
train: images/train2017  # train images (relative to 'path') 128 images
val: images/train2017  # val images (relative to 'path') 128 images
test:  # test images (optional)

# Classes
names:
  0: person
  1: bicycle
  2: car
  3: motorcycle
  4: airplane
  5: bus
  6: train
  7: truck
  8: boat
  9: traffic light
  10: fire hydrant
  11: stop sign
  12: parking meter
  13: bench
  14: bird
  15: cat
  16: dog
  17: horse
  18: sheep
  19: cow
  20: elephant
  21: bear
  22: zebra
  23: giraffe
  24: backpack
  25: umbrella
  26: handbag
  27: tie
  28: suitcase
  29: frisbee
  30: skis
  31: snowboard
  32: sports ball
  33: kite
  34: baseball bat
  35: baseball glove
  36: skateboard
  37: surfboard
  38: tennis racket
  39: bottle
  40: wine glass
  41: cup
  42: fork
  43: knife
  44: spoon
  45: bowl
  46: banana
  47: apple
  48: sandwich
  49: orange
  50: broccoli
  51: carrot
  52: hot dog
  53: pizza
  54: donut
  55: cake
  56: chair
  57: couch
  58: potted plant
  59: bed
  60: dining table
  61: toilet
  62: tv
  63: laptop
  64: mouse
  65: remote
  66: keyboard
  67: cell phone
  68: microwave
  69: oven
  70: toaster
  71: sink
  72: refrigerator
  73: book
  74: clock
  75: vase
  76: scissors
  77: teddy bear
  78: hair drier
  79: toothbrush


# Download script/URL (optional)
download: https://ultralytics.com/assets/coco128-seg.zip

segments 格式：

segments = [xyn2xy(x, w, h, padw, padh) for x in segments]

segments2boxes

def segments2boxes(segments):
    # Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
    boxes = []
    for s in segments:
        x, y = s.T  # segment xy
        boxes.append([x.min(), y.min(), x.max(), y.max()])  # cls, xyxy
    return xyxy2xywh(np.array(boxes))  # cls, xywh

导出onnx

import argparse
import json
import os
import platform
import subprocess
import sys
import time
import warnings
from pathlib import Path

import pandas as pd
import torch
import yaml
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
if platform.system() != 'Windows':
    ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative

from models.experimental import attempt_load
from models.yolo import Detect
from utils.dataloaders import LoadImages
from utils.general import (LOGGER, Profile, check_dataset, check_img_size, check_requirements, check_version,
                           check_yaml, colorstr, file_size, get_default_args, print_args, url2file)
from utils.torch_utils import select_device, smart_inference_mode


def export_formats():
    # YOLOv5 export formats
    x = [['PyTorch', '-', '.pt', True, True], ['TorchScript', 'torchscript', '.torchscript', True, True],
        ['ONNX', 'onnx', '.onnx', True, True], ['OpenVINO', 'openvino', '_openvino_model', True, False],
        ['TensorRT', 'engine', '.engine', False, True], ['CoreML', 'coreml', '.mlmodel', True, False],
        ['TensorFlow SavedModel', 'saved_model', '_saved_model', True, True],
        ['TensorFlow GraphDef', 'pb', '.pb', True, True], ['TensorFlow Lite', 'tflite', '.tflite', True, False],
        ['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite', False, False],
        ['TensorFlow.js', 'tfjs', '_web_model', False, False], ]
    return pd.DataFrame(x, columns=['Format', 'Argument', 'Suffix', 'CPU', 'GPU'])


def try_export(inner_func):
    # YOLOv5 export decorator, i..e @try_export
    inner_args = get_default_args(inner_func)

    def outer_func(*args, **kwargs):
        prefix = inner_args['prefix']
        try:
            with Profile() as dt:
                f, model = inner_func(*args, **kwargs)
            LOGGER.info(f'{prefix} export success ✅ {dt.t:.1f}s, saved as {f} ({file_size(f):.1f} MB)')
            return f, model
        except Exception as e:
            LOGGER.info(f'{prefix} export failure ❌ {dt.t:.1f}s: {e}')
            return None, None

    return outer_func


@try_export
def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:')):
    # YOLOv5 ONNX export
    check_requirements(('onnx',))
    import onnx

    LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...')
    f = file.with_suffix('.onnx')

    torch.onnx.export(model.cpu() if dynamic else model,  # --dynamic only compatible with cpu
        im.cpu() if dynamic else 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

    # Metadata
    d = {'stride': int(max(model.stride)), 'names': model.names}
    for k, v in d.items():
        meta = model_onnx.metadata_props.add()
        meta.key, meta.value = k, str(v)
    onnx.save(model_onnx, f)

    # Simplify
    if simplify:
        try:
            cuda = torch.cuda.is_available()
            check_requirements(('onnxruntime-gpu' if cuda else 'onnxruntime', 'onnx-simplifier>=0.4.1'))
            import onnxsim

            LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
            model_onnx, check = onnxsim.simplify(model_onnx)
            assert check, 'assert check failed'
            onnx.save(model_onnx, f)
        except Exception as e:
            LOGGER.info(f'{prefix} simplifier failure: {e}')
    return f, model_onnx


@try_export
def export_openvino(model, file, half, prefix=colorstr('OpenVINO:')):
    # YOLOv5 OpenVINO export
    check_requirements(('openvino-dev',))  # requires openvino-dev: https://pypi.org/project/openvino-dev/
    import openvino.inference_engine as ie

    LOGGER.info(f'\n{prefix} starting export with openvino {ie.__version__}...')
    f = str(file).replace('.pt', f'_openvino_model{os.sep}')

    cmd = f"mo --input_model {file.with_suffix('.onnx')} --output_dir {f} --data_type {'FP16' if half else 'FP32'}"
    subprocess.check_output(cmd.split())  # export
    with open(Path(f) / file.with_suffix('.yaml').name, 'w') as g:
        yaml.dump({'stride': int(max(model.stride)), 'names': model.names}, g)  # add metadata.yaml
    return f, None


@try_export
def export_coreml(model, im, file, int8, half, prefix=colorstr('CoreML:')):
    # YOLOv5 CoreML export
    check_requirements(('coremltools',))
    import coremltools as ct

    LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...')
    f = file.with_suffix('.mlmodel')

    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, bias=[0, 0, 0])])
    bits, mode = (8, 'kmeans_lut') if int8 else (16, 'linear') if half else (32, None)
    if bits < 32:
        if platform.system() == 'Darwin':  # quantization only supported on macOS
            with warnings.catch_warnings():
                warnings.filterwarnings("ignore", category=DeprecationWarning)  # suppress numpy==1.20 float warning
                ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
        else:
            print(f'{prefix} quantization only supported on macOS, skipping...')
    ct_model.save(f)
    return f, ct_model


@try_export
def export_engine(model, im, file, half, dynamic, simplify, workspace=4, verbose=False, prefix=colorstr('TensorRT:')):
    # YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt
    assert im.device.type != 'cpu', 'export running on CPU but must be on GPU, i.e. `python export.py --device 0`'
    try:
        import tensorrt as trt
    except Exception:
        if platform.system() == 'Linux':
            check_requirements(('nvidia-tensorrt',), cmds=('-U --index-url https://pypi.ngc.nvidia.com',))
        import tensorrt as trt

    if trt.__version__[0] == '7':  # TensorRT 7 handling https://github.com/ultralytics/yolov5/issues/6012
        grid = model.model[-1].anchor_grid
        model.model[-1].anchor_grid = [a[..., :1, :1, :] for a in grid]
        export_onnx(model, im, file, 12, False, dynamic, simplify)  # opset 12
        model.model[-1].anchor_grid = grid
    else:  # TensorRT >= 8
        check_version(trt.__version__, '8.0.0', hard=True)  # require tensorrt>=8.0.0
        export_onnx(model, im, file, 13, False, dynamic, simplify)  # opset 13
    onnx = file.with_suffix('.onnx')

    LOGGER.info(f'\n{prefix} starting export with TensorRT {trt.__version__}...')
    assert onnx.exists(), f'failed to export ONNX file: {onnx}'
    f = file.with_suffix('.engine')  # TensorRT engine file
    logger = trt.Logger(trt.Logger.INFO)
    if verbose:
        logger.min_severity = trt.Logger.Severity.VERBOSE

    builder = trt.Builder(logger)
    config = builder.create_builder_config()
    config.max_workspace_size = workspace * 1 << 30
    # config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace << 30)  # fix TRT 8.4 deprecation notice

    flag = (1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH))
    network = builder.create_network(flag)
    parser = trt.OnnxParser(network, logger)
    if not parser.parse_from_file(str(onnx)):
        raise RuntimeError(f'failed to load ONNX file: {onnx}')

    inputs = [network.get_input(i) for i in range(network.num_inputs)]
    outputs = [network.get_output(i) for i in range(network.num_outputs)]
    LOGGER.info(f'{prefix} Network Description:')
    for inp in inputs:
        LOGGER.info(f'{prefix}\tinput "{inp.name}" with shape {inp.shape} and dtype {inp.dtype}')
    for out in outputs:
        LOGGER.info(f'{prefix}\toutput "{out.name}" with shape {out.shape} and dtype {out.dtype}')

    if dynamic:
        if im.shape[0] <= 1:
            LOGGER.warning(f"{prefix}WARNING: --dynamic model requires maximum --batch-size argument")
        profile = builder.create_optimization_profile()
        for inp in inputs:
            profile.set_shape(inp.name, (1, *im.shape[1:]), (max(1, im.shape[0] // 2), *im.shape[1:]), im.shape)
        config.add_optimization_profile(profile)

    LOGGER.info(f'{prefix} building FP{16 if builder.platform_has_fast_fp16 and half else 32} engine in {f}')
    if builder.platform_has_fast_fp16 and half:
        config.set_flag(trt.BuilderFlag.FP16)
    with builder.build_engine(network, config) as engine, open(f, 'wb') as t:
        t.write(engine.serialize())
    return f, None


@try_export
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, keras=False, prefix=colorstr('TensorFlow SavedModel:')):
    # YOLOv5 TensorFlow SavedModel export
    import tensorflow as tf
    from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2

    from models.tf import TFModel

    LOGGER.info(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, ch))  # BHWC order for TensorFlow
    _ = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
    inputs = tf.keras.Input(shape=(*imgsz, ch), 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 = tf.keras.Model(inputs=inputs, outputs=outputs)
    keras_model.trainable = False
    keras_model.summary()
    if keras:
        keras_model.save(f, save_format='tf')
    else:
        spec = tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype)
        m = tf.function(lambda x: keras_model(x))  # full model
        m = m.get_concrete_function(spec)
        frozen_func = convert_variables_to_constants_v2(m)
        tfm = tf.Module()
        tfm.__call__ = tf.function(lambda x: frozen_func(x)[:4] if tf_nms else frozen_func(x)[0], [spec])
        tfm.__call__(im)
        tf.saved_model.save(tfm, f,
                            options=tf.saved_model.SaveOptions(experimental_custom_gradients=False) if check_version(
                                tf.__version__, '2.6') else tf.saved_model.SaveOptions())
    return f, keras_model


@try_export
def export_pb(keras_model, file, prefix=colorstr('TensorFlow GraphDef:')):
    # YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
    import tensorflow as tf
    from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2

    LOGGER.info(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)
    return f, None


@try_export
def export_tflite(keras_model, im, file, int8, data, nms, agnostic_nms, prefix=colorstr('TensorFlow Lite:')):
    # YOLOv5 TensorFlow Lite export
    import tensorflow as tf

    LOGGER.info(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:
        from models.tf import representative_dataset_gen
        dataset = LoadImages(check_dataset(check_yaml(data))['train'], img_size=imgsz, auto=False)
        converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib=100)
        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 = True
        f = str(file).replace('.pt', '-int8.tflite')
    if nms or agnostic_nms:
        converter.target_spec.supported_ops.append(tf.lite.OpsSet.SELECT_TF_OPS)

    tflite_model = converter.convert()
    open(f, "wb").write(tflite_model)
    return f, None


@try_export
def export_edgetpu(file, prefix=colorstr('Edge TPU:')):
    # YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/
    cmd = 'edgetpu_compiler --version'
    help_url = 'https://coral.ai/docs/edgetpu/compiler/'
    assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}'
    if subprocess.run(f'{cmd} >/dev/null', shell=True).returncode != 0:
        LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}')
        sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0  # sudo installed on system
        for c in ('curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -',
                  'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list',
                  'sudo apt-get update', 'sudo apt-get install edgetpu-compiler'):
            subprocess.run(c if sudo else c.replace('sudo ', ''), shell=True, check=True)
    ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1]

    LOGGER.info(f'\n{prefix} starting export with Edge TPU compiler {ver}...')
    f = str(file).replace('.pt', '-int8_edgetpu.tflite')  # Edge TPU model
    f_tfl = str(file).replace('.pt', '-int8.tflite')  # TFLite model

    cmd = f"edgetpu_compiler -s -d -k 10 --out_dir {file.parent} {f_tfl}"
    subprocess.run(cmd.split(), check=True)
    return f, None


@try_export
def export_tfjs(file, prefix=colorstr('TensorFlow.js:')):
    # YOLOv5 TensorFlow.js export
    check_requirements(('tensorflowjs',))
    import re

    import tensorflowjs as tfjs

    LOGGER.info(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
    f_json = f'{f}/model.json'  # *.json 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.split())

    json = Path(f_json).read_text()
    with open(f_json, 'w') as j:  # sort JSON Identity_* in ascending order
        subst = re.sub(r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
                       r'"Identity.?.?": {"name": "Identity.?.?"}, '
                       r'"Identity.?.?": {"name": "Identity.?.?"}, '
                       r'"Identity.?.?": {"name": "Identity.?.?"}}}', r'{"outputs": {"Identity": {"name": "Identity"}, '
                                                                      r'"Identity_1": {"name": "Identity_1"}, '
                                                                      r'"Identity_2": {"name": "Identity_2"}, '
                                                                      r'"Identity_3": {"name": "Identity_3"}}}', json)
        j.write(subst)
    return f, None


@smart_inference_mode()
def run(data=ROOT / 'data/coco128.yaml',  # 'dataset.yaml path'
        weights=ROOT / 'yolov5s.pt',  # weights path
        imgsz=(640, 640),  # image (height, width)
        batch_size=1,  # batch size
        device='cpu',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
        include=('torchscript', 'onnx'),  # include formats
        half=False,  # FP16 half-precision export
        inplace=False,  # set YOLOv5 Detect() inplace=True
        train=False,  # model.train() mode
        keras=False,  # use Keras
        optimize=False,  # TorchScript: optimize for mobile
        int8=False,  # CoreML/TF INT8 quantization
        dynamic=False,  # ONNX/TF/TensorRT: dynamic axes
        simplify=False,  # ONNX: simplify model
        opset=12,  # ONNX: opset version
        verbose=False,  # TensorRT: verbose log
        workspace=4,  # TensorRT: workspace size (GB)
        nms=False,  # TF: add NMS to model
        agnostic_nms=False,  # TF: add agnostic NMS to model
        topk_per_class=100,  # TF.js NMS: topk per class to keep
        topk_all=100,  # TF.js NMS: topk for all classes to keep
        iou_thres=0.45,  # TF.js NMS: IoU threshold
        conf_thres=0.25,  # TF.js NMS: confidence threshold
):
    t = time.time()
    include = [x.lower() for x in include]  # to lowercase
    fmts = tuple(export_formats()['Argument'][1:])  # --include arguments
    flags = [x in include for x in fmts]
    assert sum(flags) == len(include), f'ERROR: Invalid --include {include}, valid --include arguments are {fmts}'
    jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = flags  # export booleans
    file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else weights)  # PyTorch weights

    # Load PyTorch model
    device = select_device(device)
    if half:
        assert device.type != 'cpu' or coreml, '--half only compatible with GPU export, i.e. use --device 0'
        assert not dynamic, '--half not compatible with --dynamic, i.e. use either --half or --dynamic but not both'
    model = attempt_load(weights, device=device, inplace=True, fuse=True)  # load FP32 model

    # Checks
    imgsz *= 2 if len(imgsz) == 1 else 1  # expand
    if optimize:
        assert device.type == 'cpu', '--optimize not compatible with cuda devices, i.e. use --device cpu'

    # Input
    gs = int(max(model.stride))  # grid size (max stride)
    imgsz = [check_img_size(x, gs) for x in imgsz]  # verify img_size are gs-multiples
    im = torch.zeros(batch_size, 3, *imgsz).to(device)  # image size(1,3,320,192) BCHW iDetection

    # Update model
    model.train() if train else model.eval()  # training mode = no Detect() layer grid construction
    for k, m in model.named_modules():
        if isinstance(m, Detect):
            m.inplace = inplace
            m.dynamic = dynamic
            m.export = True

    for _ in range(2):
        y = model(im)  # dry runs
    if half and not coreml:
        im, model = im.half(), model.half()  # to FP16
    shape = tuple((y[0] if isinstance(y, tuple) else y).shape)  # model output shape
    LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} with output shape {shape} ({file_size(file):.1f} MB)")

    # Exports
    f = [''] * 10  # exported filenames
    warnings.filterwarnings(action='ignore', category=torch.jit.TracerWarning)  # suppress TracerWarning

    if engine:  # TensorRT required before ONNX
        f[1], _ = export_engine(model, im, file, half, dynamic, simplify, workspace, verbose)
    if onnx or xml:  # OpenVINO requires ONNX
        f[2], _ = export_onnx(model, im, file, opset, train, dynamic, simplify)
    if xml:  # OpenVINO
        f[3], _ = export_openvino(model, file, half)
    if coreml:
        f[4], _ = export_coreml(model, im, file, int8, half)

    # TensorFlow Exports
    if any((saved_model, pb, tflite, edgetpu, tfjs)):
        if int8 or edgetpu:  # TFLite --int8 bug https://github.com/ultralytics/yolov5/issues/5707
            check_requirements(('flatbuffers==1.12',))  # required before `import tensorflow`
        assert not tflite or not tfjs, 'TFLite and TF.js models must be exported separately, please pass only one type.'
        f[5], model = export_saved_model(model.cpu(), im, file, dynamic, tf_nms=nms or agnostic_nms or tfjs,
                                         agnostic_nms=agnostic_nms or tfjs, topk_per_class=topk_per_class,
                                         topk_all=topk_all, iou_thres=iou_thres, conf_thres=conf_thres, keras=keras)
        if pb or tfjs:  # pb prerequisite to tfjs
            f[6], _ = export_pb(model, file)
        if tflite or edgetpu:
            f[7], _ = export_tflite(model, im, file, int8 or edgetpu, data=data, nms=nms, agnostic_nms=agnostic_nms)
        if edgetpu:
            f[8], _ = export_edgetpu(file)
        if tfjs:
            f[9], _ = export_tfjs(file)

    # Finish
    f = [str(x) for x in f if x]  # filter out '' and None
    if any(f):
        h = '--half' if half else ''  # --half FP16 inference arg
        LOGGER.info(f'\nExport complete ({time.time() - t:.1f}s)'
                    f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
                    f"\nDetect:          python detect.py --weights {f[-1]} {h}"
                    f"\nValidate:        python val.py --weights {f[-1]} {h}"
                    f"\nPyTorch Hub:     model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}')"
                    f"\nVisualize:       https://netron.app")
    return f  # return list of exported files/dirs


def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--data', type=str, default='../data/data_y.yaml', help='dataset.yaml path')
    parser.add_argument('--weights', nargs='+', type=str, default='./runs/train-seg/exp/weights/best.pt',
                        help='model.pt path(s)')
    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)')
    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
    parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
    parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True')
    parser.add_argument('--train', action='store_true', help='model.train() mode')
    parser.add_argument('--keras', action='store_true', help='TF: use Keras')
    parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile')
    parser.add_argument('--int8', action='store_true', help='CoreML/TF INT8 quantization')
    parser.add_argument('--dynamic', action='store_true', help='ONNX/TF/TensorRT: dynamic axes')
    parser.add_argument('--simplify', action='store_true',default=True, help='ONNX: simplify model')
    parser.add_argument('--opset', type=int, default=12, help='ONNX: opset version')
    parser.add_argument('--verbose', action='store_true', help='TensorRT: verbose log')
    parser.add_argument('--workspace', type=int, default=4, help='TensorRT: workspace size (GB)')
    parser.add_argument('--nms', action='store_true', help='TF: add NMS to model')
    parser.add_argument('--agnostic-nms', action='store_true', help='TF: add agnostic NMS to model')
    parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep')
    parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep')
    parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold')
    parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold')
    parser.add_argument('--include', nargs='+', default=['onnx'],
                        help='torchscript, onnx, openvino, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs')
    opt = parser.parse_args()
    print_args(vars(opt))
    return opt


if __name__ == "__main__":
    opt = parse_opt()
    for opt.weights in (opt.weights if isinstance(opt.weights, list) else [opt.weights]):
        run(**vars(opt))

onnx结构：

转ncnn：

onnx2ncnn yolov7_mask.onnx yolov7_mask.param yolov7_mask.bin

报错：

Unsupported slice axes !
ScatterND not supported yet!
Unsupported slice axes !
ScatterND not supported yet!
Unsupported slice axes !
ScatterND not supported yet!

yolov7 mask python训练，tensorrt推理框架

整套框架已跑通，有需要的私信联系 AI视觉网奇的博客_CSDN博客-python宝典,深度学习宝典,pytorch知识宝典领域博主。