- Sort Score
- Result 10 results
- Languages All
Results 1 - 3 of 3 for quantize_axis (0.13 sec)
-
tensorflow/compiler/mlir/lite/quantization/quantization_info.proto
message Metadata { // Bit number of fixed-point data the target kernel supports. int32 num_bits = 1; // The quantized axis index if it is per-axis quantization. int32 quantize_axis = 2; // The minimum allowed value of the fixed-point data range. // This can also be used to derive the sign of storage type. int32 range_min = 3; // The minimum allowed value of the fixed-point data range.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Oct 08 03:45:04 UTC 2019 - 2.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/quantization/import_quant_stats_pass.cc
axis_stats = DenseFPElementsAttr::get( RankedTensorType::get(axis_stats_shape, b.getF32Type()), min_maxs); axis = b.getI64IntegerAttr(info.meta().quantize_axis()); } b.setInsertionPointAfter(op); if (IsQuantizableResult(op, index)) { InsertStatsOpAtResult(b, op->getResult(index), layer_stats, axis_stats, axis); } else {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Mar 08 10:41:08 UTC 2024 - 9.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/integration_test/quantize_model_test.py
tensor_shape_pb2.TensorShapeProto.Dim( size=filter_shape[quantized_axis] ) ] ) ] ) ) else: quantized_axis = -1 # Empty dimension. Per-tensor quantization has singular channel.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 17 03:36:50 UTC 2024 - 235.6K bytes - Viewed (0)