models
models copied to clipboard
onnx
A collection of pre-trained, state-of-the-art models in the ONNX format
Hi, thank you for your great framework. I am trying to convert Huggingface GPT-2 model to ONNX format using [this script](https://github.com/onnx/models/blob/6ab957a2fe61f34a76c670946f7cbd806d2cacca/text/machine_comprehension/gpt-2/dependencies/GPT2-export.py) but it doesn't work. Here is the error: ```...
# Ask a Question ### Question There is a CI job to test new models by onnxruntime, the job only test models with CPU execution provider, but there are many...
# Bug Report ### Which model does this pertain to? Any Onnx Model Zoo model inside classification/vision path ### Describe the bug I'm trying to use test data files with...
### Problem How do I extract the prediction probability values from the result OnnxTensor after we use session.run() in Java? ### Question I am taking a string as in input...
Hi teams, The YoloV4 model at [here](https://github.com/onnx/models/tree/main/vision/object_detection_segmentation/yolov4) is too complicated and hard to be optimized. And I have generated a new [YoloV4 model](https://drive.google.com/file/d/1HRv5lrnd0qJIMxdEnE118TMlSh3Xj2Ht/view?usp=sharing) by `onnx-simplifier` based on your Yolov4. Is...
Traceback (most recent call last): File "app.py", line 20, in sym, arg_params, aux_params = import_model('mobilenetv2-7.onnx') File "/home/user/.local/lib/python3.8/site-packages/mxnet/contrib/onnx/onnx2mx/import_model.py", line 60, in import_model sym, arg_params, aux_params = graph.from_onnx(model_proto.graph, opset_version=model_opset_version) File "/home/user/.local/lib/python3.8/site-packages/mxnet/contrib/onnx/onnx2mx/import_onnx.py", line...
# Model Request ### Which model would you like to see in the model zoo? [text/machine_comprehension/bidirectional_attention_flow/model/bidaf-9.onnx](https://github.com/onnx/models/blob/main/text/machine_comprehension/bidirectional_attention_flow/model/bidaf-9.onnx) ### Describe why newer opset of this model is relevant The model's opset is...
The Readme says that `The output is a (125x13x13) tensor...`, which is correct for the downloaded model. However all references and examples I found have a different output shape `(13x13x125)`....
# Ask a Question ### Question Hello, I tried [MNIST Handwritten digit recognition](https://github.com/onnx/models/tree/main/vision/classification/mnist) in Java( and Scala). I guessed test_dataset_0/input_0.pb contains sample data of type float array, but I didn't...
# Feature Request ### What is the problem that this feature solves? When I use the Isaac SDK TensorRT inference using the onnx file from the current SSD-mobilenet onnx file,...
