---
name: TensorFlow Lite Op Request
about: Use this template for reporting Lite ops you are using or missing
labels: 'comp:lite'

---

**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
- TensorFlow installed from (source or binary):
- TensorFlow version (or github SHA if from source):


**Provide the text output from tflite_convert**

```
# Copy and paste here
```

autogenerated from the registered Op and API definitions.

To regenerate them, run the script in this directory, `update_cpp_ops.sh`, with
no arguments. This script will overwrite the existing ops in-place at
***tensorflow/c/experimental/ops/\*_ops.{cc,h}***.

Run this `update_cpp_ops.sh` script when Op definitions change in the registry.

de
en
van
ik
te
dat
die
in
een
hij
het
niet
zijn
is
was
op
aan
met
als
voor
had
er
maar
om
hem
dan
zou
of
wat
mijn
men
dit
zo
door
over
ze
zich
bij
ook
tot
je
mij
uit
der
daar
haar

til
er
som
på
de
med
han
af
for
ikke
der
var
mig
sig
men
et
har
om
vi
min
havde
ham
hun
nu
over
da
fra
du
ud
sin
dem
os
op
man
hans
hvor
eller
hvad
skal
selv
her
alle
vil
blev
kunne
ind
når
være
dog
noget
ville
jo
deres
efter
ned
skulle
denne
end
dette
mit

    val socket = delegate.createSocket(host, port, localAddress, localPort)
    return configureSocket(socket)
  }

  @Throws(IOException::class)
  protected open fun configureSocket(socket: Socket): Socket {
    // No-op by default.
    return socket
  }

    return configureSocket(sslSocket)
  }

  @Throws(IOException::class)
  protected open fun configureSocket(sslSocket: SSLSocket): SSLSocket {
    // No-op by default.
    return sslSocket
  }

[gradle_verification]: https://docs.gradle.org/current/userguide/dependency_verification.html#sec:signature-verification

    return configureServerSocket(serverSocket)
  }

  @Throws(IOException::class)
  protected open fun configureServerSocket(serverSocket: ServerSocket): ServerSocket {
    // No-op by default.
    return serverSocket
  }

inspected and debugged and it is intended to be used during the development
phase.

As part of the differences that make Eager mode easier to debug, the [shape
inference
functions](https://www.tensorflow.org/guide/create_op#define_the_op_interface)
are skipped, and any checks implemented inside the shape inference code are not
executed.

The security impact of skipping those checks should be low, since the attack

         * It would perhaps be better to do this more selectively instead of applying this transform so broadly and having
         * it just no-op in most cases.
         */
        registerTransform(Minify::class) {
            from.attribute(minified, false).attribute(artifactType, "jar")
            to.attribute(minified, true).attribute(artifactType, "jar")