pytorch/test/quantization
Jerry Zhang 542ac74987 [quant][graphmode][fix] Fold conv bn (#40865)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/40865

1. applied filter for the module types
2. removed the assumption that the conv bn are immediate child of parent module

Test Plan:
python test/test_quantization.py TestQuantizeJitPasses

Imported from OSS

Differential Revision: D22338074

fbshipit-source-id: 64739a5e56c0a74249a1dbc2c8454b88ec32aa9e
2020-07-03 00:01:04 -07:00
..
serialized [quant] Add save/load state_dict to quantized dynamic RNNs (#39105) 2020-05-28 10:37:38 -07:00
__init__.py
test_backward_compatibility.py [quant] Add save/load state_dict to quantized dynamic RNNs (#39105) 2020-05-28 10:37:38 -07:00
test_fusion_passes.py Add JIT fusion pass to fuse quantized add and relu. (#38897) 2020-05-27 14:16:57 -07:00
test_numeric_suite.py [PyTorch Numeric Suite] Add support for dynamic LSTM (#40065) 2020-06-20 07:00:13 -07:00
test_qat_module.py Updates assertEqual to require atol and rtol, removes positional atol (#38872) 2020-05-27 06:31:07 -07:00
test_quantize.py qat eager: remove unneeded modules (#40396) 2020-06-22 17:45:51 -07:00
test_quantize_jit.py [quant][graphmode][fix] Fold conv bn (#40865) 2020-07-03 00:01:04 -07:00
test_quantized_functional.py Enabled per channel quantized static linear/conv (#37622) 2020-05-20 14:01:37 -07:00
test_quantized_module.py Add state dict for LSTM and RNNCell and helper functions for accessing weights and bias (#40333) 2020-06-22 17:41:07 -07:00
test_quantized_op.py Fix batch size zero for QNNPACK linear_dynamic (#40588) 2020-06-29 16:31:11 -07:00
test_quantized_tensor.py [quant] aten::repeat work for quantized tensor (#40644) 2020-06-26 22:54:19 -07:00
test_workflow_module.py [quant][bug] Histogram observer bug fix with min == max (#40310) 2020-06-22 10:05:10 -07:00