|
About the quantization category
|
|
0
|
341
|
October 2, 2019
|
|
RuntimeError: Could not run 'aten::empty.memory_format' with arguments from the 'QuantizedCPU' backend
|
|
2
|
71
|
October 27, 2020
|
|
Question about how to load quantized model
|
|
0
|
11
|
October 27, 2020
|
|
Quantisation aware training LSTM with pack_padded_sequences?
|
|
4
|
132
|
October 26, 2020
|
|
High Quantization-Aware training memory consumption
|
|
0
|
19
|
October 23, 2020
|
|
Quantization of Reflection Padding?
|
|
0
|
26
|
October 22, 2020
|
|
QuantizedConv2d with stride=(2,2) works extremely slow
|
|
5
|
95
|
October 22, 2020
|
|
Can I perform inference with a quantized model on the GPU in PyTorch 1.6?
|
|
0
|
25
|
October 22, 2020
|
|
Am I correct in concluding that resnet that comes with pytorch can't be quantized by pytorch?
|
|
7
|
413
|
October 21, 2020
|
|
PyTorch quantization resnet50 model
|
|
4
|
112
|
October 20, 2020
|
|
Quantized model of dynamic quantization on BERT tutorial is slower than original model;
|
|
11
|
141
|
October 20, 2020
|
|
Why does the quantization after pruning results in worse performance?
|
|
4
|
112
|
October 19, 2020
|
|
While inferencing a quantized model, RuntimeError occurred at torch.nn.quantized.FloatFunction summation operation
|
|
8
|
115
|
October 18, 2020
|
|
INT8 quantized model is much slower than fp32 model on CPU
|
|
13
|
485
|
October 17, 2020
|
|
Float16 dynamic quantization has no model size benefit
|
|
0
|
25
|
October 17, 2020
|
|
Slow inference on quantized MobileNetV3
|
|
7
|
273
|
October 16, 2020
|
|
How pytorch simulates bias during quantization aware training
|
|
7
|
149
|
October 16, 2020
|
|
torch.nn.MaxPool2d does not need "input" argument run but quantized function torch.nn.quantized.functional.max_pool2d must have it
|
|
2
|
78
|
October 15, 2020
|
|
How to import a quantized TFLite model into PyTorch
|
|
1
|
62
|
October 15, 2020
|
|
Same layer same initialize method same seed differet weights
|
|
1
|
41
|
October 15, 2020
|
|
Is there a way to quantize conv_transpose2d layer?
|
|
16
|
319
|
October 15, 2020
|
|
Graph Mode Quantization Aware Training in PyTorch
|
|
4
|
63
|
October 15, 2020
|
|
Dynamic Quantization not reducing model size
|
|
8
|
903
|
October 14, 2020
|
|
QAT doesn't quantize bias?
|
|
7
|
104
|
October 14, 2020
|
|
Is there an alternative to do batched matrix multiplication on Quantized Tensors?
|
|
5
|
181
|
October 12, 2020
|
|
Qnnpack accuracy very poor on unet model
|
|
8
|
194
|
October 9, 2020
|
|
Qnnpack vs. fbgemm
|
|
7
|
208
|
October 9, 2020
|
|
Performance drop when quantizing Efficientnet
|
|
14
|
383
|
October 9, 2020
|
|
Bfloat16 + transformers
|
|
1
|
150
|
October 9, 2020
|
|
How to use quantize_per_tensor
|
|
5
|
145
|
October 9, 2020
|
