Dropout - 6 vs 10#
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text. Green means an addition to the newer version, red means a deletion. Anything else is unchanged.
- Dropout6 → Dropout10 +10 -11
Dropout6 → Dropout10
RENAMED
@@ -1 +1 @@
|
|
1
|
-
Dropout takes one input
|
1
|
+
Dropout takes one input data (Tensor<float>) and produces two Tensor outputs,
|
2
|
-
output (
|
2
|
+
output (Tensor<float>) and mask (Tensor<bool>). Depending on whether it is in
|
3
|
-
|
3
|
+
test mode or not, the output Y will either be a random dropout, or a simple
|
4
4
|
copy of the input. Note that our implementation of Dropout does scaling in
|
5
5
|
the training phase, so during testing nothing needs to be done.
|
6
|
-
This operator has **optional** inputs/outputs. See ONNX <https://github.com/onnx/onnx/blob/master/docs/IR.md>_ for more details about the representation of optional arguments. An empty string may be used in the place of an actual argument's name to indicate a missing argument. Trailing optional arguments (those not followed by an argument that is present) may also be simply omitted.
|
7
6
|
**Attributes**
|
7
|
+
* **is_test**:
|
8
|
+
(int, default 0) if nonzero, run dropout in test mode where the
|
9
|
+
output is simply Y = X.
|
8
10
|
* **ratio**:
|
9
|
-
|
11
|
+
(float, default 0.5) the ratio of random dropout
|
10
12
|
**Inputs**
|
11
13
|
* **data** (heterogeneous) - **T**:
|
12
14
|
The input data as Tensor.
|
13
15
|
**Outputs**
|
14
16
|
Between 1 and 2 outputs.
|
15
17
|
* **output** (heterogeneous) - **T**:
|
16
18
|
The output.
|
17
|
-
* **mask** (optional, heterogeneous) - **
|
19
|
+
* **mask** (optional, heterogeneous) - **T**:
|
18
|
-
The output mask.
|
20
|
+
The output mask. If is_test is nonzero, this output is not filled.
|
19
21
|
**Type Constraints**
|
20
22
|
* **T** in (
|
21
23
|
tensor(double),
|
22
24
|
tensor(float),
|
23
25
|
tensor(float16)
|
24
26
|
):
|
25
|
-
Constrain input and output types to float tensors
|
27
|
+
Constrain input and output types to float tensors.- * **T1** in (
|
26
|
-
tensor(bool)
|
27
|
-
):
|
28
|
-
Constrain output mask types to boolean tensors.
|