Gwena Cunha

QAT model saving bug: Unable to save function b'__inference_separable_conv2d_layer_call_fn_961'

15

**Describe the bug** I have a simple model with input layer and a `SeparableConv2D` layer (note that this issue also happens with `Conv2DTranspose`). I'm quantizing this model by adding `quantize_and_dequantize_v2`...

ResNeXt-50 accuracy is 0%

10

## About ResNeXt-50 accuracy is 0% instead of 77.36%. Are the pre-trained weights [here](https://github.com/qubvel/classification_models/blob/a0f006e05485a34ccf871c421279864b0ccd220b/classification_models/weights.py#L193) updated? ## Steps to reproduce 1. Install requirements: ``` pip install tensorflow-gpu==2.8.0 pip install git+https://github.com/qubvel/classification_models.git ```...

How to use: ```python evaluate.py -hyp pred_en-de.txt -ref data/multi30k/test.de -out scores_en-de.txt``` Included metrics: GLEU and WER (check out [NLPMetrics](https://github.com/gcunhase/NLPMetrics) for more evaluation metrics)

Example ONNX model (mnist.onnx) fails to compile in FP16 precision

1

## How to reproduce 1. Download `mnist.onnx` model at https://github.com/onnx/onnx-mlir/blob/main/docs/mnist_example/mnist.onnx 2. Install ONNX-MLIR: ``` # Pull the latest docker image: $ docker pull onnxmlirczar/onnx-mlir # Test that it's working $...

How to generate PyRuntime.cpython-38-x86_64-linux-gnu.so?

4

I'm using ONNX_MLIR's Docker installation as follows: ``` # Pull the latest docker image: $ docker pull onnxmlirczar/onnx-mlir # Test that it's working $ git clone https://github.com/onnx/onnx-mlir.git $ cd onnx-mlir/docker...

Failed to compile ONNX to .so file: "Assertion `map.getNumInputs() == mapOperands.size() && "inconsistent index info"' failed."

1

## How to reproduce error 1. Download onnx file here: https://drive.google.com/file/d/1b1Zq2EJ0KWyCUu3L1XCSDtRdjwYIBq77/view?usp=sharing 2. Install ONNX-MLIR: ``` # Pull the latest docker image: $ docker pull onnxmlirczar/onnx-mlir # Test that it's working...

Issue converting ONNX to TF2 SavedModel

7

**TLDR;** How can I convert an ONNX file into a TF2 SavedModel using `onnx_tf`? ## Issue I'm trying to load an exported model but it's loading as `_UserObject` instead of...

Meaning of emotion labels

2

In your [dataset with 5 emotions](https://github.com/tlkh/text-emotion-classification/blob/master/dataset/data.bak.csv), what do each of the labels represent? Is the following correct? ``` 0: neutral 1: happy 2: sad 3: hate 4: anger ```

Pre-trained weights for BertSumAbs

1

Thank you for your hard work and for releasing the code and some pre-trained weights. I was wondering where I could find the pre-trained weights for the `BertSumAbs` model. Thank...

How to get the mean Average Performance (mAP) in Segmentation models?

4

1. What is the difference between the following scripts: ```bash python main.py eval python scripts/evaluate.py --log_file=./mrcnn-dll_evaluate.json python scripts/inference.py --log_file=./mrcnn-dll_inference.json python scripts/benchmark_inference.py --batch_size 4 --log_file=./mrcnn-dll_benchmark_inference.json ``` 2. The above scripts return...