|
1 | 1 | ---
|
2 |
| -name: TensorFlow Lite New Converter Issue |
| 2 | +name: TensorFlow Lite Converter Issue |
3 | 3 | about: Use this template for reporting issues during model conversion to TFLite
|
4 | 4 | labels: 'TFLiteConverter'
|
5 | 5 |
|
6 | 6 | ---
|
7 | 7 |
|
| 8 | +### 1. System information |
8 | 9 |
|
9 |
| -**System information** |
10 | 10 | - OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
|
11 |
| -- TensorFlow installed from (source or binary): |
12 |
| -- TensorFlow version (or github SHA if from source): |
| 11 | +- TensorFlow installation (pip package or built from source): |
| 12 | +- TensorFlow library (version, if pip package or github SHA, if built from source): |
13 | 13 |
|
| 14 | +### 2. Code |
14 | 15 |
|
15 |
| -**Command used to run the converter or code if you’re using the Python API** |
16 |
| -If possible, please share a link to Colab/Jupyter/any notebook. |
| 16 | +Provide code to help us reproduce your issues using one of the following options: |
17 | 17 |
|
18 |
| -``` |
19 |
| -# Copy and paste here the exact command |
20 |
| -``` |
| 18 | +#### Option A: Reference colab notebooks |
21 | 19 |
|
22 |
| -**The output from the converter invocation** |
| 20 | +1) Reference [TensorFlow Model Colab](https://colab.research.google.com/gist/ymodak/e96a4270b953201d5362c61c1e8b78aa/tensorflow-datasets.ipynb?authuser=1): Demonstrate how to build your TF model. |
| 21 | +2) Reference [TensorFlow Lite Model Colab](https://colab.research.google.com/gist/ymodak/0dfeb28255e189c5c48d9093f296e9a8/tensorflow-lite-debugger-colab.ipynb): Demonstrate how to convert your TF model to a TF Lite model (with quantization, if used) and run TFLite Inference (if possible). |
23 | 22 |
|
24 | 23 | ```
|
25 |
| -# Copy and paste the output here. |
| 24 | +(You can paste links or attach files by dragging & dropping them below) |
| 25 | +- Provide links to your updated versions of the above two colab notebooks. |
| 26 | +- Provide links to your TensorFlow model and (optionally) TensorFlow Lite Model. |
26 | 27 | ```
|
27 | 28 |
|
28 |
| -**Also, please include a link to the saved model or GraphDef** |
| 29 | +#### Option B: Paste your code here or provide a link to a custom end-to-end colab |
29 | 30 |
|
30 | 31 | ```
|
31 |
| -# Put link here or attach to the issue. |
| 32 | +(You can paste links or attach files by dragging & dropping them below) |
| 33 | +- Include code to invoke the TFLite Converter Python API and the errors. |
| 34 | +- Provide links to your TensorFlow model and (optionally) TensorFlow Lite Model. |
32 | 35 | ```
|
33 | 36 |
|
34 |
| -**Failure details** |
35 |
| -If the conversion is successful, but the generated model is wrong, |
36 |
| -state what is wrong: |
37 |
| -- Producing wrong results and/or decrease in accuracy |
38 |
| -- Producing correct results, but the model is slower than expected (model generated from old converter) |
| 37 | +### 3. Failure after conversion |
| 38 | +If the conversion is successful, but the generated model is wrong, then state what is wrong: |
39 | 39 |
|
| 40 | +- Model produces wrong results and/or has lesser accuracy. |
| 41 | +- Model produces correct results, but it is slower than expected. |
40 | 42 |
|
41 |
| -**RNN conversion support** |
| 43 | +### 4. (optional) RNN conversion support |
42 | 44 | If converting TF RNN to TFLite fused RNN ops, please prefix [RNN] in the title.
|
43 | 45 |
|
44 |
| -**Any other info / logs** |
45 |
| - |
| 46 | +### 5. (optional) Any other info / logs |
46 | 47 | Include any logs or source code that would be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached.
|
0 commit comments