codylcs

Results 11 comments of codylcs

https://blog.csdn.net/weixin_41449637/article/details/90645584 hope this can help u

> > > “adaptive_avg_pool2d” not support in onnx > > > > > > how to convert to onnx? > > same problem cause by pool ops, > some solution:[pytorch/pytorch#34743...

> > > > > “adaptive_avg_pool2d” not support in onnx > > > > > > > > > > > > how to convert to onnx? > > >...

i have upload lite_hrnet.py, it can get onnx model but with some warnings ,maybe not influence final result ,[link](https://github.com/codylcs/lite_hrnet_onnx/blob/main/litehrnet.py)

my gar, i have to turn to other code with pytorch

安装步骤最好说明下,先安装detectron2,因为安装步骤没写,默认./detectron2/model_zoo/也没有configs文件夹,还有模型路径不支持”\“,只认"/“,模型的命令也是需要严格对上的,我后面贴下,希望帮助到其他人吧 你们的工作很辛苦,这些东西如果不做好,会影响你们的start数量的 `python demo/demo.py --config-file projects/ISTR/configs/ISTR-PCA-R50-3x.yaml --input F:/vv/vv.jpg --output ./output --confidence-threshold 0.4 --opts MODEL.WEIGHTS E:/pycharmpro/Myseg/ISTR/output-ISTR-PCA-R50/model_final_istr_pca_r50.pth`

reading ckpt from reference_model ...found checkpoint reference_model\model-000200000.pth Traceback (most recent call last): File "F:\pycharmProjs\pips-main\chain_demo.py", line 195, in main() File "F:\pycharmProjs\pips-main\chain_demo.py", line 151, in main _ = saverloader.load(init_dir, model) File "F:\pycharmProjs\pips-main\saverloader.py",...

> Ok! 715 is the right number of channels there, so I don't know where 1038 is coming from. Can you add these prints to the `forward` function of `DeltaBlock`...

> 715 i print k and relative shape, ...found checkpoint reference_model\model-000200000.pth delta_block.to_delta.0.weight torch.Size([512, 519]) model k: torch.Size([512, 715]) as u see,mode net shapes are not same as parameters shape

> Hi @codylcs, sorry, I am updating the repo a bit tonight, and I added a new model ckpt. Can you pull again? I think your issue will disappear. yeah...