|
About the quantization category
|
|
1
|
278
|
October 2, 2019
|
|
Convert floating point 32 bit of input and pretrained weight to 8bit
|
|
2
|
43
|
August 12, 2020
|
|
Simple quantized model doesn't export to ONNX
|
|
8
|
142
|
August 12, 2020
|
|
Layer wise quantization
|
|
3
|
40
|
August 12, 2020
|
|
Quantization/QAT causing jit.script to fail
|
|
12
|
168
|
August 12, 2020
|
|
Quantizing Transformer Architecture Below 8-bit (post training quantization)
|
|
4
|
78
|
August 11, 2020
|
|
Reduction in performance of quantized bert model
|
|
9
|
167
|
August 6, 2020
|
|
Initializing QAT with pre-trained quantization parameters
|
|
1
|
27
|
August 6, 2020
|
|
The results of torch.profiler() and time.time() do not match
|
|
5
|
60
|
August 5, 2020
|
|
Quantisation aware training LSTM with pack_padded_sequences?
|
|
1
|
26
|
August 4, 2020
|
|
Slow quantization
|
|
7
|
156
|
August 4, 2020
|
|
[Nightly] Packed params no longer returned via state_dict() method
|
|
8
|
117
|
August 3, 2020
|
|
How to freeze the FakeQuantize zero_point during train
|
|
4
|
68
|
August 3, 2020
|
|
Performance drop when quantizing Efficientnet
|
|
5
|
123
|
July 31, 2020
|
|
Not able to run quantized model on android
|
|
2
|
75
|
July 30, 2020
|
|
Onnx export failed int8 model
|
|
18
|
761
|
July 30, 2020
|
|
[ONNX] Quantized fused Conv2d won't trace
|
|
19
|
352
|
July 30, 2020
|
|
nn.MultiheadAttention fails after quantization
|
|
7
|
103
|
July 29, 2020
|
|
Variation of results
|
|
2
|
37
|
July 28, 2020
|
|
Error in inference phase, after loading quantized model
|
|
5
|
153
|
July 27, 2020
|
|
Bottleneck on data loading
|
|
2
|
47
|
July 26, 2020
|
|
RuntimeError: Could not run 'aten::native_batch_norm' with arguments from the 'QuantizedCPUTensorId' backend. 'aten::native_batch_norm' is only available for these backends: [CPUTensorId, MkldnnCPUTensorId, VariableTensorId]
|
|
17
|
218
|
July 25, 2020
|
|
Quantized model inference error related to Mish activation function
|
|
3
|
57
|
July 24, 2020
|
|
The packing format of quantized parameters after jitting
|
|
5
|
248
|
July 22, 2020
|
|
Understand the usage of quantized weights from quantized model
|
|
11
|
200
|
July 22, 2020
|
|
_combine_histograms histogram_with_output_range = torch.zeros((Nbins * downsample_rate), device=orig_hist.device) RuntimeError: Trying to create tensor with negative dimension -4398046511104: [-4398046511104]
|
|
9
|
103
|
July 22, 2020
|
|
ONNX export of quantized model
|
|
15
|
793
|
July 22, 2020
|
|
Quantized model not provide performance improvements
|
|
4
|
81
|
July 21, 2020
|
|
Converting quantized models from PyTorch to ONNX
|
|
5
|
307
|
July 21, 2020
|
|
Loading Quantized Model from State_Dict with Version==None
|
|
3
|
50
|
July 20, 2020
|
