aidevmin

When I run inference for tensorrt model, I checked that x1 and y1 are negative, x2 can be greater than width of image and y2 can be greater then height...

Comparison exception: The values for attribute 'shape' do not match: torch.Size([]) != torch.Size([1, 1, 40, 40, 2]).

7

**Describe the issue**: I prune yolov7 model with L1Pruner. I followed this guide https://github.com/microsoft/nni/blob/master/examples/compression/pruning/norm_pruning.py . I added this code after this line https://github.com/WongKinYiu/yolov7/blob/84932d70fb9e2932d0a70e4a1f02a1d6dd1dd6ca/train.py#L100 ``` from nni.compression.pruning import L1NormPruner, L2NormPruner, FPGMPruner...

Yolov7 pruned model does not detect anything?

15

@VainF Thanks for amazing repo. I tried to run inference for yolov7 pruned model on one image, **but pruned model did not detect anything** (output image without bboxes) https://github.com/VainF/Torch-Pruning/blob/master/benchmarks/prunability/readme.md#3-yolo-v7 ```...

How to choose layers to NOT prune?

2

@VainF I want to specify layers that is not pruned. Beside the last layer that related to number of classes, do you have any recommend of not-pruned layers? As my...

Something is confused with high level pruners?

3

Thanks @VainF for amazing repo. I read your paper and see some API pruner, but something is confused with pruner. 1. In this link, you said that [BNScalePruner](https://github.com/VainF/Torch-Pruning/blob/dd59921365d72acb2857d3d74f75c03e477060fb/torch_pruning/pruner/algorithms/batchnorm_scale_pruner.py#L45) and [GroupNormPruner](https://github.com/VainF/Torch-Pruning/blob/dd59921365d72acb2857d3d74f75c03e477060fb/torch_pruning/pruner/algorithms/group_norm_pruner.py#L53)...

Dynamic batch size for Yolov4

3

Until now, code to convert from darket Yolov4 weight to engine does not support dynamic batch size. I tried with dynamic batch size to measure inference time by using trtexec,...

Where can I find preprocessing and postprocessing code?

6

@marcoslucianops Where can I find preprocessing and postprocessing code in your repo? I want to know exactly how image is processed before put to model and NMS source code from...

How to scale ground-truth to the feature layers?

3

@twangnh In the paper you wrote `The very simple setting (0.25×-G) of directly scaling ground truth boxes with same stride on the feature layer and applying imitation on those areas...

Can I change a NVME with different installed JP after switching?

1

Thanks for greate repo. I flashed JP4.6 on EMMC, after that I switched roofs from EMMC to NVME. Now I have a new NVME with installed JP5.1. Can put the...

Thanks a lot for amazing repo. I read your source code but something is not cleared about how to calculate ground-truth mask. https://github.com/ggjy/DeFeat.pytorch/blob/c46a793df414a42f64f9fad9c7106ee60b44c9b3/mmdet/models/dense_heads/anchor_head.py#L168 ``` def _map_roi_levels(self, rois, num_levels): scale =...