[参考译文] EDGE-AI-STUDIO：AI 模型用于28P55、但输出不正确

https://e2e.ti.com/support/microcontrollers/c2000-microcontrollers-group/c2000/f/c2000-microcontrollers-forum/1489529/edge-ai-studio-the-ai-model-is-used-for-28p55-but-the-output-is-incorrect

工具/软件：

import torch
import torch.nn as nn
import torch.optim as optim
import onnx
import onnxruntime as ort

torch.manual_seed(42)  
X = torch.linspace(0, 10, 100).reshape(-1, 1) 
y = 2 * X + torch.randn(X.size()) * 0.5  

class LinearRegression(nn.Module):
    def __init__(self):
        super(LinearRegression, self).__init__()
        self.linear = nn.Linear(1, 1)  

    def forward(self, x):
        return self.linear(x)

model = LinearRegression()
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)

epochs = 1000
for epoch in range(epochs):
    outputs = model(X)
    loss = criterion(outputs, y)
    
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
   
    if (epoch+1) % 100 == 0:
        print(f'Epoch [{epoch+1}/{epochs}], Loss: {loss.item():.4f}')

model.eval()

dummy_input = torch.tensor([[3.0]])  

torch.onnx.export(
    model,               
    dummy_input,         
    "linear_model.onnx",
    export_params=True,  
    opset_version=11,    
    input_names=['input'], 
    output_names=['output'],  
    dynamic_axes={       
        'input': {0: 'batch_size'},
        'output': {0: 'batch_size'}
    }
)

我使用 PyTorch 训练了一个线性回归模型(y=2x)、并导出了 onnx 模型。  使用 TVM 工具时、该参数应用于28P55、但在该模型中输入2个时、CCS 的输出与 PyTorch 的结果不一致。  我想问原因是什么？