nngen

nngen copied to clipboard

Error while running nngen.from_onnx() Download the onnx file: https://github.com/onnx/models/blob/master/vision/classification/mnist/model/mnist-1.onnx And run Python code: ```python import os import sys sys.path.insert(0, os.path.dirname(os.path.dirname( os.path.dirname(os.path.abspath(__file__))))) import nngen as ng act_dtype=ng.int16 weight_dtype=ng.int8 bias_dtype=ng.int32 scale_dtype=ng.int8 disable_fusion=False...

pbelecky

It is not able to embed yolov3-tiny to ultra96 due to that model require large RAM at slice operator near by yolo layer. Verbose log when executing example/yolov3-tiny. ``` ======================================================...

RyusukeYamano

`Width of bit range is huge; vector of over 1billion bits: 0x40000000` occured in torchvision_onnx_resnet18 example

2

Hello. I'm very interested in inference on FPGA. Found nngen and trying out some examples. `cnn.py` and `mlp.py` examples can be run without any problem, but an error, which is...

in-die-nibelungen

Hello. Is there detailed documentation on the verification environment, including RTL simulations? If not, can you prepare a new document?

oimasa5

ValueError: shape contains '0': (0,) at fasterrcnn_resnet50_fpn

1

I tried Faster-RCNN(ResNet50) model. ```python model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True) # Pytorch to ONNX onnx_filename = 'fasterrcnn_resnet50_fpn_imagenet.onnx' dummy_input = torch.randn(1, 3, 224, 224) input_names = ['act'] output_names = ['out'] model.eval() torch.onnx.export(model, dummy_input,...

Kocha

If par_ich is greater than 32 and there are layers with less than 32 input channels, an error occurs during synthesis using Vivado. The description causing the error is as...

kmichikura

[ONNX spec](https://github.com/onnx/onnx/blob/master/docs/IR.md#nodes) states that node name is diagnostic purposes only. While reading onnx file, [nngen looks up nodes by their names](https://github.com/NNgen/nngen/blob/develop/nngen/onnx/util.py#L19). This could be a bug, I think nngen should...

m1kit

Hi, thank you for making this great work open source. Is there any documentation of resource usage and latency for some arbitrary FPGA? If not, it would be good to...

marph91

shtaxxx

shtaxxx