samexporter

samexporter copied to clipboard

How to export decoder for mobile net model?

1

I've exported a mobile net model using the export_encoder script using mobilenet weights for mobilenet model. Now how do I export decoder for this? I cannot see a mobile type...

kgeorge-fission

How to export a fully segmented model

1

LsyAi

Where does the 684 height size comes from?

3

Not an issue. The code works perfectly for me. I saw the original code expects 1024x1024 image size. So, I was just wondering where the 684 fixed size for height...

simoneorlando

onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Invalid rank for input: input_image Got: 3 Expected: 4 Please fix either the inputs or the model.

2

I had this type of error what can I do ?

rushiksoftvan

New SAM derivatives

4

There are three interesting projects: - https://github.com/SysCV/sam-hq for HQ segmenting - https://github.com/ChaoningZhang/MobileSAM for fast & lightweight segmenting - https://github.com/CASIA-IVA-Lab/FastSAM also for fast & lightweight segmenting It would be fantastic if...

twardoch

use single point prompt mask decoder slow than pytorch, how to solve this problem?

1

stihuangyuan

Running converters it returns me this error : ValueError: Unsupported ONNX opset version: 17

SalvoPisciotta

hussainfolio3

Encoder only exports for vit_h

1

Great job on this, exactly what I was looking for! However, when I attempt to export the encoder using: python -m samexporter.export_encoder --checkpoint original_models/sam_vit_l_0b3195.pth --output output_models/sam_vit_l_0b3195.encoder/model.onnx --model-type vit_l --quantize-out output_models/sam_vit_l_0b3195.encoder.quant.onnx...

steven-cerebralfix

After converting the SAM2 model to ONNX , the inference results are significantly worse than the original model.

7

lhz123