|
Not able to run quantized model on android
|
|
1
|
152
|
July 30, 2020
|
|
Onnx export failed int8 model
|
|
17
|
980
|
July 30, 2020
|
|
[ONNX] Quantized fused Conv2d won't trace
|
|
18
|
539
|
July 30, 2020
|
|
nn.MultiheadAttention fails after quantization
|
|
6
|
150
|
July 29, 2020
|
|
Variation of results
|
|
1
|
70
|
July 28, 2020
|
|
Error in inference phase, after loading quantized model
|
|
4
|
190
|
July 27, 2020
|
|
Bottleneck on data loading
|
|
1
|
100
|
July 26, 2020
|
|
Quantized model inference error related to Mish activation function
|
|
2
|
115
|
July 24, 2020
|
|
The packing format of quantized parameters after jitting
|
|
4
|
320
|
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]
|
|
8
|
239
|
July 22, 2020
|
|
ONNX export of quantized model
|
|
14
|
1422
|
July 22, 2020
|
|
Quantized model not provide performance improvements
|
|
3
|
119
|
July 21, 2020
|
|
Converting quantized models from PyTorch to ONNX
|
|
4
|
674
|
July 21, 2020
|
|
Loading Quantized Model from State_Dict with Version==None
|
|
2
|
118
|
July 20, 2020
|
|
Network pruning error
|
|
12
|
154
|
July 18, 2020
|
|
Extending Quantization-Aware Training
|
|
4
|
251
|
July 17, 2020
|
|
Output tensor type is lost after serializing and loading back a quantized model
|
|
5
|
112
|
July 16, 2020
|
|
Static quantizing and batch norm error (could not run aten::native_batch_norm with args from QuantCPUTensorid backend')
|
|
4
|
168
|
July 16, 2020
|
|
Backward prop per Batch of data or backward prop after one epoch
|
|
4
|
105
|
July 15, 2020
|
|
Prediction , objective function and optimization in Python - AI
|
|
1
|
51
|
July 15, 2020
|
|
Is it planned to support nn.Embeddings quantization?
|
|
1
|
69
|
July 14, 2020
|
|
How can I incorporate PReLU in a quantized model?
|
|
3
|
159
|
July 14, 2020
|
|
QuantStub/DeQuantStubs for QAT confusion
|
|
2
|
139
|
July 9, 2020
|
|
Loading of Quantized Model
|
|
4
|
643
|
July 9, 2020
|
|
The accuracy after int8 is higher than before quantization
|
|
5
|
145
|
July 9, 2020
|
|
Quantization.convert after QAT pickling issue
|
|
2
|
110
|
July 8, 2020
|
|
Quantization awareness training multi-gpu suport?
|
|
17
|
718
|
July 8, 2020
|
|
No Difference in Model size of BERT fine-tuned with amp and without amp
|
|
8
|
150
|
July 7, 2020
|
|
Quantization not Decreasing Model Size (Static and QAT)
|
|
7
|
265
|
July 6, 2020
|
|
How to convert a 32-bit operation to a 4-bit or 8-bit operation on cpu?
|
|
1
|
102
|
July 6, 2020
|
