- Sort Score
- Result 10 results
- Languages All
Results 61 - 70 of 185 for Axis (0.06 sec)
-
tensorflow/compiler/mlir/lite/utils/lstm_utils.cc
} LogicalResult CreateEqualSizeSplitVOp(Value input, int axis, int splits, Location loc, OpBuilder* builder, Operation** result) { auto input_type = mlir::cast<RankedTensorType>(input.getType()); SmallVector<int64_t, 4> output_shape; int size_of_splits; if (input_type.getRank() < axis || axis < 0) return failure();
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 36.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/convert_custom_aggregation_op_to_quant_stats.cc
{static_cast<float>(min.getValueAsDouble()), static_cast<float>(max.getValueAsDouble())}); ElementsAttr axis_stats; IntegerAttr axis; quantfork::StatisticsOp stats_op = rewriter.create<quantfork::StatisticsOp>( op->getLoc(), op.getInput(), layer_stats, axis_stats, axis); op.getOutput().replaceAllUsesWith(stats_op.getResult()); return success(); } };
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 4.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/common/quantization_lib/quantization_traits.h
} }; }; // The trait to specify the operand index of the coefficient for an affine op // and also the quantization dimension if per-axis quantization is support. // If the quantization dimension is -1, per-axis quantization isn't supported. // // class Conv2DOp // : public Op<Conv2DOp, OpTrait::quant::AffineOpCoefficient<0>::Impl> // template <int QuantDim, int OperandIndex = 1>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 05 07:39:40 UTC 2024 - 5.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/tests/flatbuffer2mlir/quantization.mlir
%cst = "tfl.pseudo_qconst"() {qtype = tensor<1x2x!quant.uniform<u8:f32, 1.0>>, value = dense<-76> : tensor<1x2xi8>} : () -> tensor<1x2x!quant.uniform<u8:f32, 1.0>> %2 = "tfl.concatenation"(%1, %cst) {axis = 0 : i32, fused_activation_function = "NONE"} : (tensor<1x2x!quant.uniform<u8:f32, 1.0>>, tensor<1x2x!quant.uniform<u8:f32, 1.0>>) -> tensor<2x2x!quant.uniform<u8:f32, 1.0>>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 4.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/transforms/device_transform_patterns.cc
new_shape, &rewriter); reshape_ops.push_back(reshape_op.getResult()); } // Deal with the axis. // We don't need to handle axis < 0, since it's counting reversely. int32_t axis = concat_op.getAxis(); if (axis >= 0) { axis += (4 - rank); } // Replace with the new concat op. SmallVector<int64_t, 4> new_output_shape; for (int i = 0; i < 4 - rank; ++i) {
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 25.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/experimental/tac/tests/pick-subgraphs.mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 02 09:41:17 UTC 2024 - 24.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/ir/tfl_ops.td
The new axis is created at dimension `axis` (default: the new axis is appended at the end). }]; let arguments = (ins TFL_TensorOf<[I32, I64]>:$indices, TFL_I32Tensor:$depth, TFL_TensorOf<[F32, I32, I64, I1, I8, UI8]>:$on_value, TFL_TensorOf<[F32, I32, I64, I1, I8, UI8]>:$off_value, I32Attr:$axis ); let results = (outs
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Jun 06 19:09:08 UTC 2024 - 186K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/common/uniform_quantized_types.h
} // Returns true iff `type` is a uniform quantized type whose storage type is // 8-bit integer and expressed type is f32. bool IsI8F32UniformQuantizedType(Type type); // Returns true iff `type` is a uniform quantized per-axis (per-channel) type // whose storage type is 8-bit integer and expressed type is f32. bool IsI8F32UniformQuantizedPerAxisType(Type type); // Returns true iff `type` is a uniform quantized type whose storage type is
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 5.7K bytes - Viewed (0) -
tensorflow/compiler/mlir/tfr/examples/mnist/mnist_train.py
train_step, args=(dist_inputs,)) accuracy = strategy.reduce( tf.distribute.ReduceOp.MEAN, per_replica_accuracy, axis=None) loss_value = strategy.reduce( tf.distribute.ReduceOp.MEAN, per_replica_losses, axis=None) return accuracy, loss_value iterator = iter(ds_train) accuracy = 0.0 for step in range(flags.FLAGS.train_steps):
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Oct 20 03:05:18 UTC 2021 - 6.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_ops_n_z.cc
int64_t value_rank = value_type.getRank(); int64_t axis = op.getAxis(); if (axis < -value_rank || axis >= value_rank) return op.emitOpError("axis attribute must be in the range of [-") << value_rank << ", " << value_rank << ')'; axis = GetDimForAxis(axis, value_rank); int64_t dim_size = value_type.getDimSize(axis); if (ShapedType::isDynamic(dim_size)) return success();
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu May 09 22:07:10 UTC 2024 - 170.8K bytes - Viewed (0)