shayanalibhatti / retail-store-item-detection-using-yolov5 Goto Github PK

How can i show the number of objects detected when training on a single object

Am trying to convert the last_yolov5s_results.pt to tflite using the official Yolov5 suggested method to convert .pt weights to tflite
https://github.com/ultralytics/yolov5/blob/master/export.py

But I get the below error in fusing layers step
Please let me know if there is an alternative way to convert last_yolov5s_results.pt to tflite.

Fusing layers... Model summary: 199 layers, 6853110 parameters, 0 gradients Traceback (most recent call last): File "/content/yolov5/export.py", line 653, in <module> main(opt) File "/content/yolov5/export.py", line 648, in main run(**vars(opt)) File "/usr/local/lib/python3.8/dist-packages/torch/autograd/grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "/content/yolov5/export.py", line 549, in run y = model(im) # dry runs File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(*input, **kwargs) File "/content/yolov5/models/yolo.py", line 209, in forward return self._forward_once(x, profile, visualize) # single-scale inference, train File "/content/yolov5/models/yolo.py", line 121, in _forward_once x = m(x) # run File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl return forward_call(*input, **kwargs) File "/content/yolov5/models/yolo.py", line 59, in forward x[i] = self.m[i](x[i]) # conv File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1265, in __getattr__ raise AttributeError("'{}' object has no attribute '{}'".format( AttributeError: 'Detect' object has no attribute 'm'

Little confused about this. What URL to use?

Hello Shayan,

Thanks for sharing this amazing project.

I realized that are missing some box in this image, how can I improve the accuracy in this case? (img attached)

Hi, Shayan

Nice project!! Do you mind sharing the last_yolov5_results.pt with me? I'd like to do some tests before I train my own model.

Thanks,