quantization


Topic Replies Activity
About the quantization category 1 October 2, 2019
Static quantization error 1 November 21, 2019
ConvBnReLU quantized performance 5 November 19, 2019
Quantized model consists of ReLU6 5 November 18, 2019
Quantization aware training, extremely slow on GPU 6 November 15, 2019
Quantized Conv2d gives different result from the Caffe2's Int8Conv with the same weights 7 November 13, 2019
Scalar operation observers 1 November 13, 2019
Best way to quantize Transformer architecture 1 November 12, 2019
Per Tensor/Channel quantization equivalents in PyTorch/Caffe2 1 November 10, 2019
Matrix quantization while training 1 November 10, 2019
Quantization Error During Concat -- RuntimeError: Didn't find kernel to dispatch to for operator 'aten::_cat' 29 November 7, 2019
Test_adaptive_avg_pool2d_nhwc deadline in test_quantized.py 3 November 6, 2019
Very Bad Bounding Boxes After Quantization of Model 4 November 5, 2019
RuntimeError: No function is registered for schema aten::thnn_conv2d_forward(Tensor self, Tensor weight, int[2] kernel_size, Tensor? 5 November 5, 2019
Dynamic Quantization not reducing model size 3 November 2, 2019
Pytorch1.3 Quantization error in Resnet50 7 November 1, 2019
Static quantization returning torch.float32 parameters 4 November 1, 2019
RuntimeError: No function is registered for schema aten::thnn_conv2d_forward 2 November 1, 2019
RuntimeError: lhs of assignment must be a variable, subscript, or starred expression: 5 November 1, 2019
[Quantization] (Error): No function is registered for schema aten 4 November 1, 2019
Onnx export failed int8 model 2 November 1, 2019
Quantize conv layer with bias 2 October 31, 2019
PyTorch 1.3 wheels for Raspberry Pi (Python 3.7) 2 October 30, 2019
Error when converting quantization aware trained model for evaluation 5 October 28, 2019
Where is the Dataset and model file 6 October 27, 2019
Quantized hard sigmoid 2 October 23, 2019
AssertionError: min nan should be less than max nan 2 October 23, 2019