- Sort Score
- Result 10 results
- Languages All
Results 1 - 1 of 1 for Atol (0.04 sec)
-
tensorflow/compiler/mlir/quantization/tensorflow/python/integration_test/quantize_model_test.py
# expected to be small. # The atol value is arbitrary. if not enable_per_channel_quantization: expected_outputs = model.conv(input_data) target_outputs = converted_model.signatures['serving_default']( input_tensor=ops.convert_to_tensor(input_data) ) self.assertAllClose(target_outputs, expected_outputs, atol=0.06) if target_opset == quant_opts_pb2.XLA:
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 03:36:50 UTC 2024 - 235.6K bytes - Viewed (0)