Pytorch Torch Quantize_Per_Tensor

📅 2026-06-22 | 📂 PyTorch

# Creating Input Tensor input= torch.tensor([[-1.0,0.0],[1.0,2.0]]) # Per-Tensor Quantization # scale: Quantization Scale Factor # zero_point: Zero Point # dtype: Quantized Data Type x = torch.quantize_per_tensor(input, scale=0.1, zero_point=10, dtype=torch.quint8) print("Quantized Tensor:") print(x) print("Original Value Dequantization:") print(x.dequantize())

Pytorch torch Reference Manual

YouTip

Pytorch Torch Quantize_Per_Tensor

📂 Categories