OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-06 12:20:52 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity
50,180 Commits 8,304 Branches 150 Tags 1.5 GiB
13ad4739a6
Commit Graph

9 Commits

Author SHA1 Message Date
asl3
13ad4739a6 [quant] Implement PTQ for APoT FakeQuant (#81040) 
### Summary:
This PR implements PTQ for APoT FakeQuant. It runs models (Resnet-18 pre-trained model, ImageNet dataset) to compare accuracy metrics for different qconfig settings of uniform vs. APoT quantized activation and weight.

According to the collected accuracy stats, model #2 (uniform activation and APoT weight) appears to have a slight improvement in accuracy compared to model #1 (uniform activation and uniform weight) for 8-bit and significant improvement for 4-bit (see "Accuracy Stats" section below).

### Test Plan:
Run models with: `python test/quantization/core/experimental/fx_graph_mode_apot.py`

### Accuracy Stats:
8-bit (Uniform int8, APoT b = 8 k = 2)

**Model #1:** Uniform activation, uniform weight (FX Graph Mode quantized)
Evaluation accuracy on test dataset: 64.43% (Top-1), 85.62% (Top-5)

**Model #2:** Uniform activation, APoT weight (FX Graph Mode quantized)
Evaluation accuracy on test dataset: 64.51% (Top-1), 85.78% (Top-5)

**Model #3:** APoT activation, APoT weight (FX Graph Mode quantized)
Evaluation accuracy on test dataset: 64.32% (Top-1), 85.78% (Top-5)

4-bit (Uniform int4, APoT b = 4 k = 2)

**Model #1:** Uniform activation, uniform weight (FX Graph Mode quantized)
Evaluation accuracy on test dataset: 45.63% (Top-1), 71.96% (Top-5)

**Model #2:** Uniform activation, APoT weight (FX Graph Mode quantized)
Evaluation accuracy on test dataset: 64.24% (Top-1), 85.56% (Top-5)

**Model #3:** APoT activation, APoT weight (FX Graph Mode quantized)
Evaluation accuracy on test dataset: 45.40% (Top-1), 76.21% (Top-5)

**Full Precision model (FX Graph Mode quantized)**
Evaluation accuracy on test dataset: 69.76% (Top-1), 89.08% (Top-5)

**Eager mode quantized model**
Evaluation accuracy on test dataset: 69.49% (Top-1), 88.90% (Top-5)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/81040
Approved by: https://github.com/jerryzh168
 2022-07-28 07:21:31 +00:00
asl3
a01fb5392f Modify APoT dequantize method (#82126) 
### Summary
Modify APoT dequantize method to correctly add dequantized values to result numpy array and retain original tensor dimensions

### Test Plan
Run unit tests with: `python test/quantization/core/experimental/test_quantizer.py`
Pull Request resolved: https://github.com/pytorch/pytorch/pull/82126
Approved by: https://github.com/HDCharles
 2022-07-26 20:26:51 +00:00
asl3
368018530e [quant] Implement forward and backward autograd functions for fake quantize (#81438) 
### Summary:
This PR implements custom autograd functions for forward and backward to be used in APoT fake quantization. The implementation follows this doc about custom autograd functions: https://pytorch.org/tutorials/beginner/examples_autograd/polynomial_custom_function.html

### Test Plan:
Run tests with: `python test/quantization/core/experimental/test_fake_quantize.py`
Pull Request resolved: https://github.com/pytorch/pytorch/pull/81438
Approved by: https://github.com/jerryzh168
 2022-07-19 02:15:30 +00:00
asl3
5b493ba18b [quant] Refactor quantize clamping into float_to_apot util function (#80885) 
### Summary:
This PR moves the clamping functionality from `quantize` to `float_to_apot` util function to align with the uniform quantize workflow in the codebase.

### Test Plan:
Run unit tests with:
python pytorch/test/quantization/core/experimental/test_quantizer.py
Pull Request resolved: https://github.com/pytorch/pytorch/pull/80885
Approved by: https://github.com/dzdang
 2022-07-05 19:28:37 +00:00
asl3
2727d88569 [quant] Modify APoT global methods to align with uniform API (#80364) 
### Summary:
This PR updates the APoT global API method signatures and parameters for `dequantize_APoT` and `calculate_qparams` to align with their uniform counterparts in the codebase.

### Test Plan:
Run unit tests with:
`python pytorch/test/quantization/core/experimental/test_nonuniform_observer.py`
`python pytorch/test/quantization/core/experimental/test_quantizer.py`
Pull Request resolved: https://github.com/pytorch/pytorch/pull/80364
Approved by: https://github.com/jerryzh168
 2022-06-27 22:48:09 +00:00
asl3
777c12f2df [quant] Modify APoT nonuniform quantization workflow (#80075) 
### Summary:
This PR updates the design of APoT Observer, Quantizer, and Tensor to be more consistent with their uniform counterparts in the PyTorch framework. APoT Observer now calculates alpha as the max between the absolute values of the max and min values in the input tensor. APoT Quantizer is modified so its instance methods quantize_APoT and dequantize_APoT are called by their global method counterparts. APoT Tensor is modified to account for the new method definition of the `quantize_APoT` from APoT Quantizer.

### Test Plan:
Run APoT Observer class unit tests with: `python pytorch/test/quantization/core/experimental/test_nonuniform_observer.py`
Run APoT Quantize class unit tests with: `python pytorch/test/quantization/core/experimental/test_quantizer.py`
Run APoT Tensor class unit tests with: `python pytorch/test/quantization/core/experimental/test_quantized_tensor.py`
Pull Request resolved: https://github.com/pytorch/pytorch/pull/80075
Approved by: https://github.com/jerryzh168
 2022-06-27 14:54:06 +00:00
asl3
0b349f7e69 [quant] Dequantize apot tensor 
Pull Request resolved: https://github.com/pytorch/pytorch/pull/79530

Approved by: https://github.com/dzdang, https://github.com/jerryzh168
 2022-06-22 05:15:06 +00:00
asl3
d6ec8398a9 [quant] Implement quantize APoT method 
Pull Request resolved: https://github.com/pytorch/pytorch/pull/79499

Approved by: https://github.com/dzdang, https://github.com/jerryzh168
 2022-06-22 05:15:06 +00:00
asl3
f89e640810 [quant] Add quantizer class skeleton 
Pull Request resolved: https://github.com/pytorch/pytorch/pull/79936

Approved by: https://github.com/jerryzh168
 2022-06-22 05:11:15 +00:00