- Sort Score
- Result 10 results
- Languages All
Results 11 - 20 of 102 for backprop (0.12 sec)
-
tensorflow/compiler/mlir/tensorflow/transforms/lower_tf.td
// computes loss and backprop of the loss with respect to 'features'. // // Softmax cross entropy loss is defined as follows: // // loss = Sum(-labels * Log(Exp(features) / Sum(Exp(features))) // loss = Sum(-labels * LogSoftmax(features)) // // Computing gradient of the loss with respect to features gives us, // // backprop = (Exp(features) / Sum(Exp(features))) - labels
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 04 13:30:42 UTC 2024 - 24.7K bytes - Viewed (0) -
tensorflow/c/eager/tape.h
// any gradients to be computed). // // Finally, we start a backprop stack with a set of tape entries for which we // have all gradients available. This set usually is a subset of the set of // targets (not all since targets which have outputs in the tape will not have // gradients available initially). // // Then we repeatedly pop an entry from the stack, run its backprop, and update
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Apr 02 12:40:29 UTC 2024 - 47.2K bytes - Viewed (0) -
tensorflow/cc/gradients/nn_grad.cc
// We multiply the backprop for cost with the gradients - op.output[1]. // There is no gradient for labels. // The outputs of the network are at input index 0. auto logits = op.input(0); // The "truth" labels are at index 1. auto softmax_grad = op.output(1); // The loss is the output at index 0, and backprop is the output at index 1. auto grad_loss = grad_inputs[0];
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri May 27 23:34:33 UTC 2022 - 24.5K bytes - Viewed (0) -
tensorflow/cc/gradients/nn_grad_test.cc
auto y = tensorflow::ops::SoftmaxCrossEntropyWithLogits(scope_, logits, labels); // Note the reversal of the backprop and loss orders. Issue #18734 has been // opened for this. RunTest({logits, labels}, {logits_shape, logits_shape}, {y.backprop, y.loss}, {logits_shape, loss_shape}); } TEST_F(NNGradTest, LogSoftmaxGrad) { TensorShape shape({5, 3});
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Mar 22 20:45:22 UTC 2022 - 15K bytes - Viewed (0) -
tensorflow/compiler/mlir/lite/stablehlo/transforms/fuse_convolution_pass.cc
}); } filter_value = filter.getValue(); mul_value = multiplier.getValue(); // In MHLO, Conv filter is in HWIO format, Depthwise conv filter is in HW1O // format and backprop input conv filter is in HWOI format. // Only fuses multiplier if all dimensions other than the out channel // dimension are equal to 1. if (!TFL::IsDimensionsDegenerateExceptLastOne(
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Feb 22 22:21:19 UTC 2024 - 8.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/tpu_space_to_depth_pass.mlir
// CHECK: %[[BACKPROP:.*]] = "tf.Conv2DBackpropFilter" // CHECK-SAME: strides = [1, 1, 1, 1] // CHECK-SAME: (tensor<2x115x115x12xf32>, tensor<4xi32>, tensor<2x112x112x64xf32>) -> tensor<4x4x12x64xf32>
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Mon Oct 30 06:52:55 UTC 2023 - 37.4K bytes - Viewed (0) -
tensorflow/cc/framework/gradients_test.cc
{dx, dy, dz}, &grad_outputs)); } } CompareTestAndExpectedGraphs(); } TEST_F(GradientsTest, StackUnstack_StopBackprop) { // Tests that backprop stops before calculating gradients for Stack (because // only gradients w.r.t the output of Stack are requested). for (const bool expected : {false, true}) { const Scope& scope = expected ? scope_expected_ : scope_test_;
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Sat Apr 15 15:13:38 UTC 2023 - 25K bytes - Viewed (0) -
tensorflow/c/while_loop_test.cc
Add(params_->body_inputs[0], {one, 0}, params_->body_graph, s_); ASSERT_EQ(TF_OK, TF_GetCode(s_)) << TF_Message(s_); params_->body_outputs[0] = {add, 0}; ExpectOK(); // Create backprop graph TF_Output grad_output; TF_AddGradients(graph_, outputs_.data(), outputs_.size(), inputs_.data(), 1, nullptr, s_, &grad_output); ASSERT_EQ(TF_OK, TF_GetCode(s_)) << TF_Message(s_);
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Thu Apr 11 06:05:56 UTC 2024 - 15.3K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/tests/lower_tf.mlir
// CHECK-DAG: %[[SOFTMAX:.*]] = "tf.Div"(%[[SOFTMAX_EXP]], %[[SOFTMAX_SUM]]) : (tensor<2x3xf32>, tensor<2x1xf32>) -> tensor<2x3xf32> // CHECK-DAG: %[[BACKPROP:.*]] = "tf.Sub"(%[[SOFTMAX]], %[[LABELS]]) : (tensor<2x3xf32>, tensor<2x3xf32>) -> tensor<2x3xf32> // CHECK: return %[[LOSS]], %[[BACKPROP]] %0:2 = "tf.SoftmaxCrossEntropyWithLogits"(%features, %labels) : (tensor<2x3xf32>, tensor<2x3xf32>) -> (tensor<2xf32>, tensor<2x3xf32>)
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Fri Jan 05 18:35:42 UTC 2024 - 92K bytes - Viewed (0) -
tensorflow/compiler/mlir/tensorflow/ir/tf_generated_ops.td
example, suppose y = f(x) and we wish to apply a custom function g for backprop such that dx = g(dy). In Python, ```python with tf.get_default_graph().gradient_override_map( {'IdentityN': 'OverrideGradientWithG'}): y, _ = identity_n([f(x), x]) @tf.RegisterGradient('OverrideGradientWithG') def ApplyG(op, dy, _): return [None, g(dy)] # Do not backprop to f(x). ``` }]; let arguments = (ins
Registered: Sun Jun 16 05:45:23 UTC 2024 - Last Modified: Tue Jun 11 23:24:08 UTC 2024 - 793K bytes - Viewed (0)