| .. |
|
calibration
|
Allow update for min/max values in calibrator.
|
2019-07-12 14:58:04 -07:00 |
|
g3doc
|
Fix broken path in lite docs
|
2018-11-28 18:37:28 +00:00 |
|
testdata
|
Add support for partially quantizing models.
|
2019-04-26 14:38:08 -07:00 |
|
BUILD
|
Use tflite::SafeCast when casting float to int32.
|
2019-06-04 20:57:48 -07:00 |
|
model_utils_test.cc
|
Strengthen IsQuantized rule to actually check quantization params rather than just looking at the type.
|
2019-06-17 09:55:06 -07:00 |
|
model_utils.cc
|
Strengthen IsQuantized rule to actually check quantization params rather than just looking at the type.
|
2019-06-17 09:55:06 -07:00 |
|
model_utils.h
|
Add support for partially quantizing models.
|
2019-04-26 14:38:08 -07:00 |
|
operator_property.cc
|
Bump required conv2d version.
|
2019-07-18 13:45:50 -07:00 |
|
operator_property.h
|
Make quantization properties per-tensor.
|
2019-06-06 10:29:36 -07:00 |
|
quantization_utils_test.cc
|
Remove a wrong check.
|
2019-06-05 12:09:07 -07:00 |
|
quantization_utils.cc
|
Make quantization properties per-tensor.
|
2019-06-06 10:29:36 -07:00 |
|
quantization_utils.h
|
Remove a wrong check.
|
2019-06-05 12:09:07 -07:00 |
|
quantize_model_test.cc
|
Bump required conv2d version.
|
2019-07-18 13:45:50 -07:00 |
|
quantize_model.cc
|
Format a message
|
2019-06-19 20:25:11 -07:00 |
|
quantize_model.h
|
Add support for partially quantizing models.
|
2019-04-26 14:38:08 -07:00 |
|
quantize_weights_test.cc
|
Support quantization to float16
|
2019-05-17 14:57:42 -07:00 |
|
quantize_weights.cc
|
Inserting de-quantization input for hybrid ops inputs that doesn't support
|
2019-07-30 08:35:34 -07:00 |
|
quantize_weights.h
|
Support quantization to float16
|
2019-05-17 14:57:42 -07:00 |
|
test_util.cc
|
Add support for partially quantizing models.
|
2019-04-26 14:38:08 -07:00 |
|
test_util.h
|
Add support for partially quantizing models.
|
2019-04-26 14:38:08 -07:00 |
