Hello,

Could you help me to fix the issues in the below script to be able to check YOLO results instead of (Faster/Mask R-CNN)?

I want to check YOLO-V5 which is developed using this community: https://pytorch.org/hub/ultralytics_yolov5/

Start from a Python>=3.8 environment with PyTorch>=1.7 installed.
Install Dependences pip install -qr https://raw.githubusercontent.com/ultralytics/yolov5/master/requirements.txt
Model: model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)

So, I tried to replace the model in the script of torchbench_coco-posit.py but it gives me some errors.

Could you help me regarding this if the code needs to customize for this model. I thought as mentioned in the Qtorch+ paper that I can do this as simple as switching between the Pytorch models?

The used Script:

`from torchbench.object_detection import COCO from torchbench.utils import send_model_to_device from torchbench.object_detection.transforms import Compose, ConvertCocoPolysToMask, ToTensor import torchvision import PIL

import torch.nn as nn import qtorch_plus from qtorch_plus.quant import configurable_table_quantize, posit_quantize

import torch

model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)

def coco_data_to_device(input, target, device: str = "cuda", non_blocking: bool = True): input = list(inp.to(device=device, non_blocking=non_blocking) for inp in input) target = [{k: v.to(device=device, non_blocking=non_blocking) for k, v in t.items()} for t in target] return input, target

def coco_collate_fn(batch): return tuple(zip(*batch))

def coco_output_transform(output, target): output = [{k: v.to("cpu") for k, v in t.items()} for t in output] return output, target

transforms = Compose([ConvertCocoPolysToMask(), ToTensor()])

model_name = 'fasterrcnn_resnet50_fpn'

model_name = 'maskrcnn_resnet50_fpn'

model = torchvision.models.detection.dict[model_name](num_classes=91, pretrained=True)

def other_weight(input): input = posit_quantize(input, nsize=16, es=1) return input

def other_activation(input):

input = posit_quantize(input, nsize=16, es=1)
return input

def linear_weight(input): input = posit_quantize(input, nsize=8, es=1, scale= 4.0) return input def linear_activation(input): global act_data input = posit_quantize(input, nsize=8, es=1, scale= 0.5) return input

def forward_pre_hook_other(m, input): return (other_activation(input[0]),)

def forward_pre_hook_linear(m, input):

return (linear_activation(input[0]),)

layer_count = 0 total_layer = 0

for name, module in model.named_modules(): if isinstance(module, nn.Conv2d) or isinstance(module, nn.Linear) : module.weight.data = linear_weight(module.weight.data) module.register_forward_pre_hook(forward_pre_hook_linear)

    total_layer+=1
    layer_count +=1

else: #should use fixedpoint or posit 16 for other layers 'weight
    if hasattr(module, 'weight'):
        total_layer +=1
        module.weight.data = other_weight(module.weight.data)
        module.register_forward_pre_hook(forward_pre_hook_other)

        #pass

print ("total %d layers ; using posit on %d conv/linear layers"%(total_layer, layer_count))

Run the benchmark

"""COCO.benchmark( model=model, paper_model_name='Mask R-CNN (ResNet-50-FPN)', paper_arxiv_id='1703.06870', transforms=transforms, model_output_transform=coco_output_transform, send_data_to_device=coco_data_to_device, collate_fn=coco_collate_fn, batch_size=4, num_gpu=1 )"""

COCO.benchmark( model=model, paper_model_name='Yolo', transforms=transforms, model_output_transform=coco_output_transform, send_data_to_device=coco_data_to_device, collate_fn=coco_collate_fn, batch_size=4, num_gpu=1 )`

The appeared ERROR: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) ninja: no work to do. Loading extension module quant_cpu... Using /home/hanysalah/.cache/torch_extensions/py310_cu117 as PyTorch extensions root... Detected CUDA files, patching ldflags Emitting ninja build file /home/hanysalah/.cache/torch_extensions/py310_cu117/quant_cuda/build.ninja... Building extension module quant_cuda... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) ninja: no work to do. Loading extension module quant_cuda... Using cache found in /home/hanysalah/.cache/torch/hub/ultralytics_yolov5_master YOLOv5 🚀 2023-1-23 Python-3.10.6 torch-1.13.0+cu117 CUDA:0 (NVIDIA GeForce GTX 1650, 4096MiB)

Fusing layers... YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients Adding AutoShape... total 60 layers ; using posit on 60 conv/linear layers loading annotations into memory... Done (t=0.74s) creating index... index created! Evaluation: 0%| | 0/1250 [00:00<?, ?it/s] Traceback (most recent call last): File "/home/hanysalah/technical/posits/conga2022/torchbench_coco-posit.py", line 83, in COCO.benchmark( File "/home/hanysalah/technical/posits/torchbench/torchbench/object_detection/coco.py", line 220, in benchmark test_results, speed_mem_metrics, run_hash = evaluate_detection_coco( File "/home/hanysalah/technical/posits/torchbench/torchbench/object_detection/utils.py", line 209, in evaluate_detection_coco original_output = model(input) File "/home/hanysalah/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(*input, *kwargs) File "/home/hanysalah/.local/lib/python3.10/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(args, **kwargs) File "/home/hanysalah/.cache/torch/hub/ultralytics_yolov5_master/models/common.py", line 690, in forward im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1) TypeError: transpose() received an invalid combination of arguments - got (tuple), but expected one of:

(int dim0, int dim1)
(name dim0, name dim1)

Thanks in advance.

Best Regards, Mohammed Essam

minhhn2910 / conga2022

YOLO v5 model is not working with Qtorch+ when replacing the object detection used models (Faster/Mask R-CNN) #2

model_name = 'fasterrcnn_resnet50_fpn'

model_name = 'maskrcnn_resnet50_fpn'

model = torchvision.models.detection.dict[model_name](num_classes=91, pretrained=True)

Run the benchmark