- Sort Score
- Result 10 results
- Languages All
Results 1 - 6 of 6 for argmax (0.53 sec)
-
tensorflow/compiler/mlir/lite/quantization/lite/BUILD
], data = [ "//tensorflow/lite/tools/optimize:testdata/add_with_const_input.bin", "//tensorflow/lite/tools/optimize:testdata/argmax.bin", "//tensorflow/lite/tools/optimize:testdata/broadcast_to.bin", "//tensorflow/lite/tools/optimize:testdata/concat.bin", "//tensorflow/lite/tools/optimize:testdata/fc.bin",
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 12 23:15:24 UTC 2024 - 8.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/quantization/lite/quantize_model_test.cc
auto float_op = float_graph->operators()->Get(0); // Verify ArgMax input is quantized. ASSERT_THAT(float_graph->tensors()->Get(float_op->inputs()->Get(0))->type(), Eq(TensorType_FLOAT32)); EXPECT_THAT(subgraph->tensors[op->inputs[0]].get()->type, Eq(TensorType_INT8)); // Verify ArgMax input axis should still be the same type.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Wed Jun 12 23:15:24 UTC 2024 - 73.9K bytes - Viewed (0) -
tensorflow/compiler/mlir/tf2xla/transforms/legalize_tf.cc
} }; // Converts tensorflow ArgMin or ArgMax op to mhlo operations that perform // a reduction on the original input and the corresponding index. The reduction // sub-computation selects the max (or min) value and the index for the value. // Derived: is the resulting derived class of this class. // OpTy: is TF::ArgMaxOp or TF::ArgMinOp. template <typename Derived, typename OpTy>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 20:00:43 UTC 2024 - 291.8K bytes - Viewed (0) -
RELEASE.md
for more details about DTensor. * `tf.lite`: * Added TFLite builtin op support for the following TF ops: * `tf.math.argmin`/`tf.math.argmax` for input data type `tf.bool` on CPU. * `tf.nn.gelu` op for output data type `tf.float32` and quantization on CPU.
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 730.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_generated_ops.td
} def TF_ArgMaxOp : TF_Op<"ArgMax", [Pure]> { let summary = [{ Returns the index with the largest value across dimensions of a tensor. }]; let description = [{ Note that in case of ties the identity of the return value is not guaranteed. Usage: ```python import tensorflow as tf a = [1, 10, 26.9, 2.8, 166.32, 62.3] b = tf.math.argmax(input = a) c = tf.keras.backend.eval(b)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 793K bytes - Viewed (0) -
CHANGELOG/CHANGELOG-1.28.md
- Fixed a bug where pv recycler failed to scrub volume with too many files in the directory due to hitting ARG_MAX limit with rm command (#117189). ([#117283](https://github.com/kubernetes/kubernetes/pull/117283), [@defo89](https://github.com/defo89)) [SIG Cloud Provider and Storage]
Registered: Sat Jun 15 01:39:40 UTC 2024 - Last Modified: Tue Jun 11 23:47:59 UTC 2024 - 408.3K bytes - Viewed (0)