|
About the quantization category
|
|
0
|
565
|
October 2, 2019
|
|
Save and load model.state_dict() successfully, but with the same input, the outputs ars differnt
|
|
0
|
20
|
June 24, 2021
|
|
Saving Quantized model
|
|
4
|
382
|
June 24, 2021
|
|
I quantized input tensor and all layers except last layer, but got RuntimeError: Could not run 'quantized::conv2d.new' with arguments from the 'CPU' backend
|
|
4
|
324
|
June 23, 2021
|
|
How to make quantized and float tensors on same device?
|
|
0
|
12
|
June 23, 2021
|
|
Quantization scales and bias
|
|
1
|
41
|
June 21, 2021
|
|
ONNX export of quantized model
|
|
21
|
3779
|
June 16, 2021
|
|
Export fp16 model to ONNX
|
|
1
|
428
|
June 17, 2021
|
|
Size of exported onnx model
|
|
1
|
113
|
June 17, 2021
|
|
Onnx export failed int8 model
|
|
19
|
1712
|
June 17, 2021
|
|
`torch.mean(keepdim=True)` with `quint8` tensor does not work with qnnpack backend
|
|
3
|
88
|
June 15, 2021
|
|
Dynamic Quantization of finetuned T5 model
|
|
0
|
24
|
June 11, 2021
|
|
RuntimeError: Could not run 'aten::add_.Tensor' with arguments from the 'QuantizedCPU' backend
|
|
2
|
686
|
June 11, 2021
|
|
Using quantized addition
|
|
1
|
28
|
June 11, 2021
|
|
Is it possible to quantize model have more than one input?
|
|
3
|
113
|
June 10, 2021
|
|
Strange behaviour with qnnpack accuracy
|
|
6
|
80
|
June 10, 2021
|
|
`Expected self.scalar_type() == ScalarType::Float to be true, but got false.` when doing quantization aware training?
|
|
4
|
267
|
June 9, 2021
|
|
Strange latency behavior
|
|
3
|
39
|
June 9, 2021
|
|
Fbgemm not available
|
|
0
|
23
|
June 8, 2021
|
|
Static quantization for YOLOv5 model
|
|
5
|
375
|
June 7, 2021
|
|
Quantized Conv2d bug
|
|
15
|
862
|
June 7, 2021
|
|
RuntimeError: Could not run 'aten::thnn_conv2d_forward' with arguments from the 'QuantizedCPUTensorId' backend. 'aten::thnn_conv2d_forward' is only available for these backends: [CPUTensorId, VariableTensorId]
|
|
13
|
1978
|
June 6, 2021
|
|
Slower quantization on linux systems
|
|
0
|
49
|
June 5, 2021
|
|
First forward pass in quantized model takes long time
|
|
0
|
37
|
June 4, 2021
|
|
Maintaining sparsity when quantizing
|
|
1
|
46
|
June 3, 2021
|
|
How to multiply by a scalar with quantization observers
|
|
2
|
69
|
June 3, 2021
|
|
Purpose of scale and zero point for layer
|
|
4
|
490
|
June 3, 2021
|
|
Cannot create weak reference to 'numpy.ufunc' object
|
|
2
|
60
|
June 2, 2021
|
|
How to get around `'Proxy' object does not support item assignment`
|
|
4
|
62
|
May 31, 2021
|
|
Serialize quantized model with external libraries with TorchScript
|
|
6
|
102
|
May 28, 2021
|
