pytorch/test/quantization
Angela Yi e574c2c025 [quant][fx] Validate qconfig_dict keys (#58566)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/58566

Validates the keys of the qconfig_dict, prepare_custom_config_dict, convert_custom_config_dict, and
fuse_custom_config_dict. If the user passes in an invalid key or makes a type, we will throw and error and let the user know what keys are supported.

Test Plan:
Imported from OSS

python test/test_quantization.py

Reviewed By: jerryzh168

Differential Revision: D28540923

fbshipit-source-id: 5958c32017b7d16abd219aefc8e92c42543897c2
2021-05-21 15:20:05 -07:00
..
serialized Adding a version serialization type to ConvPackedParam (#43086) 2020-08-28 15:41:30 -07:00
__init__.py remediation of S205607 2020-07-17 17:19:47 -07:00
test_backward_compatibility.py Adding a version serialization type to ConvPackedParam (#43086) 2020-08-28 15:41:30 -07:00
test_bias_correction.py Numeric Suite: Swap with shadow modules only for quantized part of model (#51052) 2021-02-04 11:40:30 -08:00
test_equalize.py cross_layer_equalization (#41685) 2020-07-22 08:39:23 -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_fx.py ns for fx: clean up manual string names of related ops (#57210) 2021-05-05 06:30:32 -07:00
test_numeric_suite.py Numeric Suite: Swap with shadow modules only for quantized part of model (#51052) 2021-02-04 11:40:30 -08:00
test_qat_module.py Remove legacy constructor calls from pytorch codebase. (#54142) 2021-04-11 15:45:17 -07:00
test_quantize_fx.py [quant][fx] Validate qconfig_dict keys (#58566) 2021-05-21 15:20:05 -07:00
test_quantize_jit.py Add padding_idx argument to EmbeddingBag (#49237) 2021-04-14 09:38:01 -07:00
test_quantize.py quant: fix conv transpose with qconfig == None (#52844) 2021-02-25 11:52:30 -08:00
test_quantized_functional.py [reland][quant] Remove nn.quantized.ReLU module and nn.quantized.functional.relu (#47415) (#48038) 2020-11-17 09:52:21 -08:00
test_quantized_module.py [quantization] Fix deepcopy on quantized ConvNd (#56154) 2021-04-15 15:18:22 -07:00
test_quantized_op.py make quantizeable MHA work with torch.jit.script (#57774) 2021-05-07 08:40:49 -07:00
test_quantized_tensor.py Fixing quantize_per_tensor on cuda (#57703) 2021-05-07 12:26:19 -07:00
test_workflow_module.py per_channel fake quant fp16 and fp64 support (#56894) 2021-04-30 13:52:45 -07:00