- Sort Score
- Result 10 results
- Languages All
Results 61 - 70 of 91 for conv_2d (0.35 sec)
-
tensorflow/compiler/mlir/lite/transforms/prepare_patterns.td
(UpdateShapeWithAxis<-1> $qtype, $old_value))), [(CanUpdateShapeWithAxis<-1> $qtype, $old_value)]>; // The axis is set to 0 because the transpose is from the legalization of // tf.conv2d and the new channel axis is the first dimension. def ReorderTransposeDequantQuantUsedByConv : Pat<(TF_TransposeOp:$old_value (TFL_DequantizeOp (TFL_QuantizeOp $input, $qtype)), $perm),
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Apr 30 00:40:15 UTC 2024 - 10.5K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/utils/arithmetic_count_util.h
if (!input_type || !input_type.hasStaticShape()) { return false; } total_count += input_type.getNumElements(); } *count = total_count; return true; } // For conv2d/depthwise_conv/fully_connected ops. // This algorithm actually comes from TOCO tooling_util.cc static bool GetArithmeticCountForConvAndFullyconnectedOp(mlir::Operation* op,
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 25 16:01:03 UTC 2024 - 3.1K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/python/integration_test/quantize_model_test_base.py
def body(self, x, w): z = nn_ops.conv2d(x, w, padding='SAME') return z, w @def_function.function( input_signature=[ tensor_spec.TensorSpec( shape=input_shape, dtype=dtypes.float32, name='input_tensor' ) ] ) def main(self, x): x1 = nn_ops.conv2d(x, self.w, padding='SAME')
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Mar 21 08:51:46 UTC 2024 - 51.2K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/quantize_xla.mlir
%dq_bias = "quantfork.dcast"(%q_bias) : (tensor<2x!quant.uniform<i32:f32, 0.044022349891595126>>) -> tensor<2xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 19:32:28 UTC 2024 - 11.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/shape_inference.mlir
func.return %arg0 : tensor<*xi32> } // Test conv2d inferReturnTypes can infer some information when input or // filter does not have fully static shape. // CHECK-LABEL: func @conv2d_unranked_input_and_filter func.func @conv2d_unranked_input_and_filter(%arg0: tensor<*xf32>, %arg1: tensor<*xf32>) -> tensor<*xf32> { // CHECK: "tf.Conv2D" // CHECK-SAME: -> tensor<?x?x?x?xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jan 23 17:24:10 UTC 2024 - 167.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/stablehlo/tests/passes/insert_calibration_statistics_saver_with_skipping.mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue May 14 06:31:57 UTC 2024 - 6.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/passes/prepare_lifting.td
def MultiplyFakeQuantValue : NativeCodeCall< "MultiplyFakeQuantValue($_builder, $_loc, $0...)">; // Convert AddV2Op following an AffineOp to BiasAddOp. // For Conv3D, even though the Conv3D op has "NDHWC" data format, the BiasAdd // will still has the data format of "NHWC". def ConvertAddToBiasAdd : Pat< (TF_AddV2Op (SupportedAffineOpMatcher $conv_out, $input, $weight),
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Feb 14 03:24:59 UTC 2024 - 8.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/quantization/tensorflow/tests/quantize.mlir
%dq_bias = "quantfork.dcast"(%q_bias) : (tensor<2x!quant.uniform<i32:f32, 0.044022349891595126>>) -> tensor<2xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 19:32:28 UTC 2024 - 6.4K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/tests/legalize-tf-prefer-tf2xla.mlir
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Sat Apr 06 15:32:52 UTC 2024 - 15.8K bytes - Viewed (0) -
tensorflow/compiler/mlir/tfrt/tests/tf_to_corert/tf_to_corert_pipeline.mlir
%outputs_6, %control_7 = tf_executor.island wraps "tf.Const"() {device = "", value = dense<[-1, 16384]> : tensor<2xi32>} : () -> tensor<2xi32> %outputs_8, %control_9 = tf_executor.island wraps "tf.Conv2D"(%arg0, %outputs_0) {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 2, 2, 1], use_cudnn_on_gpu = true} : (tensor<16x224x224x3xf32>, tensor<*xf32>) -> tensor<16x112x112x?xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed May 08 00:18:59 UTC 2024 - 7.7K bytes - Viewed (0)