通过 ONNX 从 PyTorch 转换为 CoreML 时缺少权重向量
Missing Weight Vectors when converting from PyTorch to CoreML via ONNX
我正在尝试通过 ONNX 将 PyTorch 模型转换为 CoreML，但是 ONNX-->CoreML 转换缺少权重向量？
我正在按照教程 here 进行以下声明：
Step 3: Converting the model to CoreML
It's as easy as running the convert function. The resulting object is a coremltools MLModel object that you can save to a file and import in XCode later.
cml = onnx_coreml.convert(model)
不幸的是，当我尝试这样做时，它失败了。
这是我的代码：
# convert.py
import torch
import torch.onnx
from torch.autograd import Variable
import onnx
from onnx_coreml import convert
from hourglass_model import Hourglass
model_no = 1
torch_model = Hourglass(joint_count=14, size=256)
state_dict = torch.load("hourglass_model_{}.model".format(model_no))
torch_model.load_state_dict(state_dict)
torch_model.train(False)
torch_model.eval()
# Dummy Input to the model
x = Variable(torch.randn(1,3,256,256,dtype=torch.float32))
# Export the model
onnx_filename = "test_hourglass.onnx"
torch_out = torch.onnx.export(torch_model, x, onnx_filename, export_params=False)
# Load back in ONNX model
onnx_model = onnx.load(onnx_filename)
# Check that the IR is well formed
onnx.checker.check_model(onnx_model)
# Print a human readable representation of the graph
graph = onnx.helper.printable_graph(onnx_model.graph)
print(graph)
coreml_model = convert(onnx_model,
add_custom_layers=True,
image_input_names=["input"],
image_output_names=["output"])
coreml_model.save('test_hourglass.mlmodel')
这是 print(graph) 行给出的内容。
graph torch-jit-export (
%0[FLOAT, 1x3x256x256]
%1[FLOAT, 64x3x5x5]
%2[FLOAT, 64]
%3[FLOAT, 64x64x5x5]
%4[FLOAT, 64]
%5[FLOAT, 64x64x5x5]
%6[FLOAT, 64]
%7[FLOAT, 64x64x5x5]
%8[FLOAT, 64]
%9[FLOAT, 64x64x5x5]
%10[FLOAT, 64]
%11[FLOAT, 64x64x5x5]
%12[FLOAT, 64]
%13[FLOAT, 64x64x5x5]
%14[FLOAT, 64]
%15[FLOAT, 64x64x1x1]
%16[FLOAT, 64]
%17[FLOAT, 14x64x1x1]
%18[FLOAT, 14]
) {
%19 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%0, %1, %2)
%20 = Relu(%19)
%21 = MaxPool[kernel_shape = [4, 4], pads = [0, 0, 0, 0], strides = [4, 4]](%20)
%22 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%21, %3, %4)
%23 = Relu(%22)
%24 = MaxPool[kernel_shape = [4, 4], pads = [0, 0, 0, 0], strides = [4, 4]](%23)
%25 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%24, %5, %6)
%26 = Relu(%25)
%27 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%26, %7, %8)
%28 = Relu(%27)
%29 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%28, %9, %10)
%30 = Relu(%29)
%31 = Upsample[height_scale = 4, mode = 'nearest', width_scale = 4](%30)
%32 = Add(%31, %23)
%33 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%32, %11, %12)
%34 = Relu(%33)
%35 = Upsample[height_scale = 4, mode = 'nearest', width_scale = 4](%34)
%36 = Add(%35, %20)
%37 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%36, %13, %14)
%38 = Relu(%37)
%39 = Conv[dilations = [1, 1], group = 1, kernel_shape = [1, 1], pads = [0, 0, 0, 0], strides = [1, 1]](%38, %15, %16)
%40 = Relu(%39)
%41 = Conv[dilations = [1, 1], group = 1, kernel_shape = [1, 1], pads = [0, 0, 0, 0], strides = [1, 1]](%40, %17, %18)
%42 = Relu(%41)
return %42
}
这是错误信息：
1/24: Converting Node Type Conv
Traceback (most recent call last):
File "convert.py", line 38, in <module>
image_output_names=["output"])
File "/Users/stephenf/Developer/miniconda3/envs/pytorch/lib/python3.6/site-packages/onnx_coreml/converter.py", line 396, in convert
_convert_node(builder, node, graph, err)
File "/Users/stephenf/Developer/miniconda3/envs/pytorch/lib/python3.6/site-packages/onnx_coreml/_operators.py", line 994, in _convert_node
return converter_fn(builder, node, graph, err)
File "/Users/stephenf/Developer/miniconda3/envs/pytorch/lib/python3.6/site-packages/onnx_coreml/_operators.py", line 31, in _convert_conv
"Weight tensor: {} not found in the graph initializer".format(weight_name,))
File "/Users/stephenf/Developer/miniconda3/envs/pytorch/lib/python3.6/site-packages/onnx_coreml/_error_utils.py", line 71, in missing_initializer
format(node.op_type, node.inputs[0], node.outputs[0], err_message)
ValueError: Missing initializer error in op of type Conv, with input name = 0, output name = 19. Error message: Weight tensor: 1 not found in the graph initializer
据我所知，它说缺少权重张量 %1[FLOAT, 64x3x5x5]。这就是我保存模型的方式：
torch.save(model.state_dict(), "hourglass_model_{}.model".format(epoch))
ONNX 加载正常 - 这只是我从 ONNX 转换为 CoreML 的步骤。
如果能帮助解决这个问题，我们将不胜感激。我确定我做错了很多其他事情，但我现在只需要导出这个东西。
谢谢，
您正在用 export_params=False 调用 torch.onnx.export，正如 0.3.1 doc 所读，它正在保存没有实际参数张量的模型架构。最近的文档没有具体说明这一点，但我们可以假设由于 Weight tensor not found 您收到的错误。
尝试 export_params=True，您应该会看到保存的模型的大小如何显着增加。
很高兴对您有所帮助！
安德烈斯
我正在尝试通过 ONNX 将 PyTorch 模型转换为 CoreML，但是 ONNX-->CoreML 转换缺少权重向量？
我正在按照教程 here 进行以下声明：
Step 3: Converting the model to CoreML
It's as easy as running the
convertfunction. The resulting object is a coremltools MLModel object that you can save to a file and import in XCode later.
cml = onnx_coreml.convert(model)
不幸的是，当我尝试这样做时，它失败了。
这是我的代码：
# convert.py
import torch
import torch.onnx
from torch.autograd import Variable
import onnx
from onnx_coreml import convert
from hourglass_model import Hourglass
model_no = 1
torch_model = Hourglass(joint_count=14, size=256)
state_dict = torch.load("hourglass_model_{}.model".format(model_no))
torch_model.load_state_dict(state_dict)
torch_model.train(False)
torch_model.eval()
# Dummy Input to the model
x = Variable(torch.randn(1,3,256,256,dtype=torch.float32))
# Export the model
onnx_filename = "test_hourglass.onnx"
torch_out = torch.onnx.export(torch_model, x, onnx_filename, export_params=False)
# Load back in ONNX model
onnx_model = onnx.load(onnx_filename)
# Check that the IR is well formed
onnx.checker.check_model(onnx_model)
# Print a human readable representation of the graph
graph = onnx.helper.printable_graph(onnx_model.graph)
print(graph)
coreml_model = convert(onnx_model,
add_custom_layers=True,
image_input_names=["input"],
image_output_names=["output"])
coreml_model.save('test_hourglass.mlmodel')
这是 print(graph) 行给出的内容。
graph torch-jit-export (
%0[FLOAT, 1x3x256x256]
%1[FLOAT, 64x3x5x5]
%2[FLOAT, 64]
%3[FLOAT, 64x64x5x5]
%4[FLOAT, 64]
%5[FLOAT, 64x64x5x5]
%6[FLOAT, 64]
%7[FLOAT, 64x64x5x5]
%8[FLOAT, 64]
%9[FLOAT, 64x64x5x5]
%10[FLOAT, 64]
%11[FLOAT, 64x64x5x5]
%12[FLOAT, 64]
%13[FLOAT, 64x64x5x5]
%14[FLOAT, 64]
%15[FLOAT, 64x64x1x1]
%16[FLOAT, 64]
%17[FLOAT, 14x64x1x1]
%18[FLOAT, 14]
) {
%19 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%0, %1, %2)
%20 = Relu(%19)
%21 = MaxPool[kernel_shape = [4, 4], pads = [0, 0, 0, 0], strides = [4, 4]](%20)
%22 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%21, %3, %4)
%23 = Relu(%22)
%24 = MaxPool[kernel_shape = [4, 4], pads = [0, 0, 0, 0], strides = [4, 4]](%23)
%25 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%24, %5, %6)
%26 = Relu(%25)
%27 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%26, %7, %8)
%28 = Relu(%27)
%29 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%28, %9, %10)
%30 = Relu(%29)
%31 = Upsample[height_scale = 4, mode = 'nearest', width_scale = 4](%30)
%32 = Add(%31, %23)
%33 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%32, %11, %12)
%34 = Relu(%33)
%35 = Upsample[height_scale = 4, mode = 'nearest', width_scale = 4](%34)
%36 = Add(%35, %20)
%37 = Conv[dilations = [1, 1], group = 1, kernel_shape = [5, 5], pads = [2, 2, 2, 2], strides = [1, 1]](%36, %13, %14)
%38 = Relu(%37)
%39 = Conv[dilations = [1, 1], group = 1, kernel_shape = [1, 1], pads = [0, 0, 0, 0], strides = [1, 1]](%38, %15, %16)
%40 = Relu(%39)
%41 = Conv[dilations = [1, 1], group = 1, kernel_shape = [1, 1], pads = [0, 0, 0, 0], strides = [1, 1]](%40, %17, %18)
%42 = Relu(%41)
return %42
}
这是错误信息：
1/24: Converting Node Type Conv
Traceback (most recent call last):
File "convert.py", line 38, in <module>
image_output_names=["output"])
File "/Users/stephenf/Developer/miniconda3/envs/pytorch/lib/python3.6/site-packages/onnx_coreml/converter.py", line 396, in convert
_convert_node(builder, node, graph, err)
File "/Users/stephenf/Developer/miniconda3/envs/pytorch/lib/python3.6/site-packages/onnx_coreml/_operators.py", line 994, in _convert_node
return converter_fn(builder, node, graph, err)
File "/Users/stephenf/Developer/miniconda3/envs/pytorch/lib/python3.6/site-packages/onnx_coreml/_operators.py", line 31, in _convert_conv
"Weight tensor: {} not found in the graph initializer".format(weight_name,))
File "/Users/stephenf/Developer/miniconda3/envs/pytorch/lib/python3.6/site-packages/onnx_coreml/_error_utils.py", line 71, in missing_initializer
format(node.op_type, node.inputs[0], node.outputs[0], err_message)
ValueError: Missing initializer error in op of type Conv, with input name = 0, output name = 19. Error message: Weight tensor: 1 not found in the graph initializer
据我所知，它说缺少权重张量 %1[FLOAT, 64x3x5x5]。这就是我保存模型的方式：
torch.save(model.state_dict(), "hourglass_model_{}.model".format(epoch))
ONNX 加载正常 - 这只是我从 ONNX 转换为 CoreML 的步骤。
如果能帮助解决这个问题，我们将不胜感激。我确定我做错了很多其他事情，但我现在只需要导出这个东西。
谢谢，
您正在用 export_params=False 调用 torch.onnx.export，正如 0.3.1 doc 所读，它正在保存没有实际参数张量的模型架构。最近的文档没有具体说明这一点，但我们可以假设由于 Weight tensor not found 您收到的错误。
尝试 export_params=True，您应该会看到保存的模型的大小如何显着增加。
很高兴对您有所帮助！
安德烈斯