Hi @jerryzh168
Thanks for your answer!
Here is the full quantized model
ResNet(
(quant): Quantize(scale=tensor([1.]), zero_point=tensor([0]), dtype=torch.quint8)
(conv1): QuantizedConv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), scale=1.0, zero_point=0, padding=(3, 3), bias=False)
(bn1): QuantizedBatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(layer1): Sequential(
(0): BasicBlock(
(quant): Quantize(scale=tensor([1.]), zero_point=tensor([0]), dtype=torch.quint8)
(conv1): QuantizedConv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn1): QuantizedBatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): QuantizedConv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn2): QuantizedBatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(dequant): DeQuantize()
)
(1): BasicBlock(
(quant): Quantize(scale=tensor([1.]), zero_point=tensor([0]), dtype=torch.quint8)
(conv1): QuantizedConv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn1): QuantizedBatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): QuantizedConv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn2): QuantizedBatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(dequant): DeQuantize()
)
)
(layer2): Sequential(
(0): BasicBlock(
(quant): Quantize(scale=tensor([1.]), zero_point=tensor([0]), dtype=torch.quint8)
(conv1): QuantizedConv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn1): QuantizedBatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): QuantizedConv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn2): QuantizedBatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): QuantizedConv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), scale=1.0, zero_point=0, bias=False)
(1): QuantizedBatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(dequant): DeQuantize()
)
(1): BasicBlock(
(quant): Quantize(scale=tensor([1.]), zero_point=tensor([0]), dtype=torch.quint8)
(conv1): QuantizedConv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn1): QuantizedBatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): QuantizedConv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn2): QuantizedBatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(dequant): DeQuantize()
)
)
(layer3): Sequential(
(0): BasicBlock(
(quant): Quantize(scale=tensor([1.]), zero_point=tensor([0]), dtype=torch.quint8)
(conv1): QuantizedConv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn1): QuantizedBatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): QuantizedConv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn2): QuantizedBatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): QuantizedConv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), scale=1.0, zero_point=0, bias=False)
(1): QuantizedBatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(dequant): DeQuantize()
)
(1): BasicBlock(
(quant): Quantize(scale=tensor([1.]), zero_point=tensor([0]), dtype=torch.quint8)
(conv1): QuantizedConv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn1): QuantizedBatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): QuantizedConv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn2): QuantizedBatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(dequant): DeQuantize()
)
)
(layer4): Sequential(
(0): BasicBlock(
(quant): Quantize(scale=tensor([1.]), zero_point=tensor([0]), dtype=torch.quint8)
(conv1): QuantizedConv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn1): QuantizedBatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): QuantizedConv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn2): QuantizedBatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(downsample): Sequential(
(0): QuantizedConv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), scale=1.0, zero_point=0, bias=False)
(1): QuantizedBatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(dequant): DeQuantize()
)
(1): BasicBlock(
(quant): Quantize(scale=tensor([1.]), zero_point=tensor([0]), dtype=torch.quint8)
(conv1): QuantizedConv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn1): QuantizedBatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): QuantizedConv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), scale=1.0, zero_point=0, padding=(1, 1), bias=False)
(bn2): QuantizedBatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(dequant): DeQuantize()
)
)
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
(fc): QuantizedLinear(in_features=512, out_features=2, scale=1.0, zero_point=0, qscheme=torch.per_channel_affine)
(dequant): DeQuantize()
)
You can find some additional inputs on my issue in here