Export

Export¶

You can simply export model to ONNX format by calling export method.

Load trained hub¶

In [1]:

                
                    Copied!
                    
from waffle_hub.hub import Hub

hub = Hub.load("detector")
from waffle_hub.hub import Hub

hub = Hub.load("detector")

/home/lhj/anaconda3/envs/waffle/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm

In [2]:

                
                    Copied!
                    
hub.export()
hub.export()

/home/lhj/anaconda3/envs/waffle/lib/python3.9/site-packages/ultralytics/nn/modules/head.py:50: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
  elif self.dynamic or self.shape != shape:
/home/lhj/anaconda3/envs/waffle/lib/python3.9/site-packages/ultralytics/yolo/utils/tal.py:251: TracerWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
  for i, stride in enumerate(strides):
/home/lhj/anaconda3/envs/waffle/lib/python3.9/site-packages/torch/onnx/utils.py:617: UserWarning: ONNX Preprocess - Removing mutation from node aten::sub_ on block input: 'tensor.1'. This changes graph semantics. (Triggered internally at ../torch/csrc/jit/passes/onnx/remove_inplace_ops_for_onnx.cpp:335.)
  _C._jit_pass_onnx_remove_inplace_ops_for_onnx(graph, module)

Out[2]:

ExportResult(export_file=PosixPath('hubs/detector/weights/model.onnx'))

In [ ]: