custom model inference without using detect.py #6460

memelvin99 · 2022-01-28T05:58:16Z

Search before asking

I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Hi,
I would like to use a custom inference code other than "detect.py". Here is the code I am trying, but not working.

Additional

No response

github-actions · 2022-01-28T05:58:51Z

👋 Hello @memelvin99, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://ultralytics.com or email support@ultralytics.com.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

Google Colab and Kaggle notebooks with free GPU:
Google Cloud Deep Learning VM. See GCP Quickstart Guide
Amazon Deep Learning AMI. See AWS Quickstart Guide
Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

glenn-jocher · 2022-01-28T06:04:36Z

@memelvin99 👋 Hello! Thanks for asking about handling inference results. YOLOv5 🚀 PyTorch Hub models allow for simple model loading and inference in a pure python environment without using detect.py.

Simple Inference Example

This example loads a pretrained YOLOv5s model from PyTorch Hub as model and passes an image for inference. 'yolov5s' is the YOLOv5 'small' model. For details on all available models please see the README. Custom models can also be loaded, including custom trained PyTorch models and their exported variants, i.e. ONNX, TensorRT, TensorFlow, OpenVINO YOLOv5 models.

import torch

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, etc.
# model = torch.hub.load('ultralytics/yolov5', 'custom', 'path/to/best.pt')  # custom trained model

# Images
im = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, URL, PIL, OpenCV, numpy, list

# Inference
results = model(im)

# Results
results.print()  # or .show(), .save(), .crop(), .pandas(), etc.

results.xyxy[0]  # im predictions (tensor)
results.pandas().xyxy[0]  # im predictions (pandas)
#      xmin    ymin    xmax   ymax  confidence  class    name
# 0  749.50   43.50  1148.0  704.5    0.874023      0  person
# 2  114.75  195.75  1095.0  708.0    0.624512      0  person
# 3  986.00  304.00  1028.0  420.0    0.286865     27     tie

See YOLOv5 PyTorch Hub Tutorial for details.

Good luck 🍀 and let us know if you have any other questions!

memelvin99 · 2022-01-28T06:49:35Z

Thanks for the quick reply.

I have trained a custom model and saved best.pt locally.
I have loaded the model using below code:
"model = torch.hub.load('C:/AI_Projects/fan_engine/yolo', 'custom', path='best.pt', source='local')"
But this code is giving me the error:
"raise URLError('unknown url type: %s' % type)
urllib.error.URLError: "

Here is the complete code:

import torch
path='/content/drive/MyDrive/Volvo/FANCASE/yolo/best.pt') # or yolov5m, yolov5l, yolov5x, custom
model = torch.hub.load('C:/AI_Projects/fan_engine/yolo', 'custom', path='best.pt', source='local')
img = 'C:/AI_Projects/fan_engine/yolo/images/data/11110731_wrong.png'
results = model(img)
results.print()

glenn-jocher · 2022-01-28T07:12:28Z

@memelvin99 see Colab notebook for example:
https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb#scrollTo=GMusP4OAxFu6&line=2&uniqifier=1

memelvin99 · 2022-01-28T07:40:38Z

The above colab sample code is working for me. But the issue is when I am loading my custom model locally. I am getting error:

Exception: Invalid --device 0 request, valid devices are 0 - -1. The cache may be out of date, try force_reload=True

I have also tried model = torch.hub.load('', 'custom', path='best.pt', source='local',force_reload=True)
Still getting the same error.

mx2013713828 · 2022-01-28T09:34:52Z

model = torch.hub.load('../yolov5/','custom',path='Yourpath/best.pt',source='local').
try this.

glenn-jocher · 2022-01-28T12:27:19Z

@memelvin99 your code is out of date

wisplite · 2022-01-30T19:35:48Z

I'm getting the same error with a similar setup. If the code is out of date, what is the correct way to do this? I'm pulling the line of code from the official tutorials for yolov5.

Edit: for additional clarity, I am running locally on Windows 10, and I am using PyTorch with CUDA. Detect.py works perfectly, but for my use case I am going to need to write my own code, and it keeps failing.

glenn-jocher · 2022-01-30T19:57:26Z

@Thebombuknow error has been fixed earlier in #6461. To receive this update:

Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
PyTorch Hub – Force-reload model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
Notebooks – View updated notebooks
Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!

wisplite · 2022-01-30T22:08:12Z

Thanks! That fixed it! I just got extremely unlucky, as I happened to pull the repo mere hours before the bug was fixed.

github-actions · 2022-03-02T00:21:26Z

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

Wiki – https://github.com/ultralytics/yolov5/wiki
Tutorials – https://docs.ultralytics.com/yolov5
Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

Ultralytics HUB – https://ultralytics.com/hub
Vision API – https://ultralytics.com/yolov5
About Us – https://ultralytics.com/about
Join Our Team – https://ultralytics.com/work
Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

Symbadian · 2022-08-21T09:49:13Z

@memelvin99 👋 Hello! Thanks for asking about handling inference results. YOLOv5 🚀 PyTorch Hub models allow for simple model loading and inference in a pure python environment without using detect.py.

Simple Inference Example

This example loads a pretrained YOLOv5s model from PyTorch Hub as model and passes an image for inference. 'yolov5s' is the YOLOv5 'small' model. For details on all available models please see the README. Custom models can also be loaded, including custom trained PyTorch models and their exported variants, i.e. ONNX, TensorRT, TensorFlow, OpenVINO YOLOv5 models.
import torch

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, etc.
# model = torch.hub.load('ultralytics/yolov5', 'custom', 'path/to/best.pt')  # custom trained model

# Images
im = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, URL, PIL, OpenCV, numpy, list

# Inference
results = model(im)

# Results
results.print()  # or .show(), .save(), .crop(), .pandas(), etc.

results.xyxy[0]  # im predictions (tensor)
results.pandas().xyxy[0]  # im predictions (pandas)
#      xmin    ymin    xmax   ymax  confidence  class    name
# 0  749.50   43.50  1148.0  704.5    0.874023      0  person
# 2  114.75  195.75  1095.0  708.0    0.624512      0  person
# 3  986.00  304.00  1028.0  420.0    0.286865     27     tie
See YOLOv5 PyTorch Hub Tutorial for details.

Good luck 🍀 and let us know if you have any other questions!

Hi @glenn-jocher,

I have been following your instructions above to get the best results for the custom model.
I followed the instructions and git pulled the clone model again but somehow this option is throwing an error and I am not sure how to interpret the meaning of it to move forward.

Can you help me understand what is happening within the error prompt and how do I proceed to solve this challenge?
THANK YOU LOADS in advance for all of your guidance and efforts.......

WHEN I: try it this way it works:
python3 detect.py --weights /Users/symbadian/Desktop/LIRIS_new_dataset/Old_WorkingYOLOv5/yolov5/runs/train/Pre-Trained-weights/WithAUGS_Better_Perfor/exp_yolov5s/weights/best.pt --source /Users/symbadian/Desktop/LIRIS_new_dataset/Old_WorkingYOLOv5/yolov5/data/images --conf 0.6

BUT I would like to get the results printed

xmin ymin xmax ymax confidence class name

My code:

import torchvision
import torch

# Model
model = torch.hub.load('./new_dataset/yolov5/models/hub/', 'yolov5m6.yaml')

# Images
dir = './new_dataset/yolov5/data/images/'
imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')]  # batch of images

# Inference
results = model(imgs)
results.print()  # or .show(), .save() 

***ERROR***********

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 537, in load
    repo_or_dir = _get_cache_or_reload(repo_or_dir, force_reload, trust_repo, "load",
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 180, in _get_cache_or_reload
    repo_owner, repo_name, ref = _parse_repo_info(github)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 126, in _parse_repo_info
    repo_owner, repo_name = repo_info.split('/')
ValueError: too many values to unpack (expected 2)
>>> model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 1348, in do_open
    h.request(req.get_method(), req.selector, req.data, headers,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1282, in request
    self._send_request(method, url, body, headers, encode_chunked)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1328, in _send_request
    self.endheaders(body, encode_chunked=encode_chunked)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1277, in endheaders
    self._send_output(message_body, encode_chunked=encode_chunked)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1037, in _send_output
    self.send(msg)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 975, in send
    self.connect()
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1454, in connect
    self.sock = self._context.wrap_socket(self.sock,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py", line 513, in wrap_socket
    return self.sslsocket_class._create(
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py", line 1071, in _create
    self.do_handshake()
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py", line 1342, in do_handshake
    self._sslobj.do_handshake()
ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:997)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 537, in load
    repo_or_dir = _get_cache_or_reload(repo_or_dir, force_reload, trust_repo, "load",
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 180, in _get_cache_or_reload
    repo_owner, repo_name, ref = _parse_repo_info(github)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 133, in _parse_repo_info
    with urlopen(f"https://github.com/{repo_owner}/{repo_name}/tree/main/"):
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 216, in urlopen
    return opener.open(url, data, timeout)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 519, in open
    response = self._open(req, data)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 536, in _open
    result = self._call_chain(self.handle_open, protocol, protocol +
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 496, in _call_chain
    result = func(*args)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 1391, in https_open
    return self.do_open(http.client.HTTPSConnection, req,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 1351, in do_open
    raise URLError(err)
urllib.error.URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:997)>
``

glenn-jocher · 2022-08-21T13:15:40Z

@Symbadian you don't load yamls, you load models, i.e.

model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, etc.
model = torch.hub.load('ultralytics/yolov5', 'custom', 'path/to/best.pt')  # custom trained model

Symbadian · 2022-08-21T13:44:13Z

model = torch.hub.load('ultralytics/yolov5', 'custom', 'path/to/best.pt')

Hi @glenn-jocher,

I tried that as well and got the same error hence me reaching out to you...

I also tried:

import torch
import torchvision
model = torch.hub.load('ultralytics/yolov5', 'yolov5m6.pt', '/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_WITHAUGs/yolov5b/runs/train/Pre-Trained-weights/exp_yolov5m/weights/best.pt')

 model = torch.hub.load('/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_WITHAUGs/yolov5', 'yolov5m6.pt', '/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_WITHAUGs/yolov5b/runs/train/Pre-Trained-weights/exp_yolov5m/weights/best.pt')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 537, in load
    repo_or_dir = _get_cache_or_reload(repo_or_dir, force_reload, trust_repo, "load",
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 180, in _get_cache_or_reload
    repo_owner, repo_name, ref = _parse_repo_info(github)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 126, in _parse_repo_info
    repo_owner, repo_name = repo_info.split('/')
ValueError: too many values to unpack (expected 2)
>>>

please assist!?
Your guidance is crucial at this stage

Python 3.10.6 (v3.10.6:9c7b4bd164, Aug  1 2022, 17:13:48) [Clang 13.0.0 (clang-1300.0.29.30)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> import torchvision
>>>  model = torch.hub.load('ultralytics/yolov5', 'custom', '/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_WITHAUGs/yolov5b/runs/train/Pre-Trained-weights/exp_yolov5m/weights/best.pt')
  File "<stdin>", line 1
    model = torch.hub.load('ultralytics/yolov5', 'custom', '/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_WITHAUGs/yolov5b/runs/train/Pre-Trained-weights/exp_yolov5m/weights/best.pt')
IndentationError: unexpected indent
>>> model = torch.hub.load('ultralytics/yolov5', 'custom', '/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_WITHAUGs/yolov5b/runs/train/Pre-Trained-weights/exp_yolov5m/weights/best.pt')
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 1348, in do_open
    h.request(req.get_method(), req.selector, req.data, headers,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1282, in request
    self._send_request(method, url, body, headers, encode_chunked)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1328, in _send_request
    self.endheaders(body, encode_chunked=encode_chunked)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1277, in endheaders
    self._send_output(message_body, encode_chunked=encode_chunked)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1037, in _send_output
    self.send(msg)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 975, in send
    self.connect()
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1454, in connect
    self.sock = self._context.wrap_socket(self.sock,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py", line 513, in wrap_socket
    return self.sslsocket_class._create(
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py", line 1071, in _create
    self.do_handshake()
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py", line 1342, in do_handshake
    self._sslobj.do_handshake()
ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:997)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 537, in load
    repo_or_dir = _get_cache_or_reload(repo_or_dir, force_reload, trust_repo, "load",
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 180, in _get_cache_or_reload
    repo_owner, repo_name, ref = _parse_repo_info(github)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 133, in _parse_repo_info
    with urlopen(f"https://github.com/{repo_owner}/{repo_name}/tree/main/"):
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 216, in urlopen
    return opener.open(url, data, timeout)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 519, in open
    response = self._open(req, data)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 536, in _open
    result = self._call_chain(self.handle_open, protocol, protocol +
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 496, in _call_chain
    result = func(*args)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 1391, in https_open
    return self.do_open(http.client.HTTPSConnection, req,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 1351, in do_open
    raise URLError(err)
urllib.error.URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:997

glenn-jocher · 2022-08-21T13:57:11Z

@Symbadian just read your error and fix this yourself. It says unexpected indent. This is user error.

Symbadian · 2022-08-21T14:10:33Z

model = torch.hub.load('ultralytics/yolov5', 'custom', '/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_WITHAUGs/yolov5b/runs/train/Pre-Trained-weights/exp_yolov5m/weights/best.pt')

Hi @glenn-jocher and thanks so much for your swift response and your time, I really really appreciate this..

I am trying to interpret these errors so I realized that there was an indentation error so I fixed it, but that was not the real issue,

and I tried yours to see if it would the model from the link automatically, but that did not work as well..

import torch
>>> import torchvision
>>> model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 1348, in do_open
    h.request(req.get_method(), req.selector, req.data, headers,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1282, in request
    self._send_request(method, url, body, headers, encode_chunked)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1328, in _send_request
    self.endheaders(body, encode_chunked=encode_chunked)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1277, in endheaders
    self._send_output(message_body, encode_chunked=encode_chunked)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1037, in _send_output
    self.send(msg)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 975, in send
    self.connect()
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/http/client.py", line 1454, in connect
    self.sock = self._context.wrap_socket(self.sock,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py", line 513, in wrap_socket
    return self.sslsocket_class._create(
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py", line 1071, in _create
    self.do_handshake()
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/ssl.py", line 1342, in do_handshake
    self._sslobj.do_handshake()
ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:997)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 537, in load
    repo_or_dir = _get_cache_or_reload(repo_or_dir, force_reload, trust_repo, "load",
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 180, in _get_cache_or_reload
    repo_owner, repo_name, ref = _parse_repo_info(github)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 133, in _parse_repo_info
    with urlopen(f"https://github.com/{repo_owner}/{repo_name}/tree/main/"):
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 216, in urlopen
    return opener.open(url, data, timeout)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 519, in open
    response = self._open(req, data)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 536, in _open
    result = self._call_chain(self.handle_open, protocol, protocol +
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 496, in _call_chain
    result = func(*args)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 1391, in https_open
    return self.do_open(http.client.HTTPSConnection, req,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py", line 1351, in do_open
    raise URLError(err)
urllib.error.URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:997)>
>>>

please see below

forgive my persistence but I am really really trying to get this right

(/Users/symbadian/miniforge3/ml) Matthews-MacBook-Pro:yolov5 symbadian$ python3
Python 3.10.6 (v3.10.6:9c7b4bd164, Aug  1 2022, 17:13:48) [Clang 13.0.0 (clang-1300.0.29.30)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> import torchvision
>>> model = torch.hub.load('/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_WITHAUGs/yolov5/models/hub/yolov5m6.yaml', '/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_WITHAUGs/yolov5b/runs/train/Pre-Trained-weights/exp_yolov5m/weights/best.pt')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 537, in load
    repo_or_dir = _get_cache_or_reload(repo_or_dir, force_reload, trust_repo, "load",
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 180, in _get_cache_or_reload
    repo_owner, repo_name, ref = _parse_repo_info(github)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/hub.py", line 126, in _parse_repo_info
    repo_owner, repo_name = repo_info.split('/')
ValueError: too many values to unpack (expected 2)
>>>

glenn-jocher · 2022-08-21T14:23:58Z

@Symbadian I've already told you above not to load YAMLs. Please don't waste my time, I'm extremely busy.

Symbadian · 2022-08-21T14:41:00Z

@Symbadian I've already told you above not to load YAMLs. Please don't waste my time, I'm extremely busy.

forgive my lapse in understanding @glenn-jocher, I am really trying to get this going, please see below:

This worked for me:

Thanx for your patience and time, your efforts and guidance is highly valued!!

import torch
import torchvision
model = torch.hub.load('.', 'custom', path='/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_NoAUGs/yolov5/runs/train/From_Scratch/WITH_BG_NoAUGs/exp_yolov5m/weights/best.pt', source='local')
img = '/Users/symbadian/Desktop/LIRIS_new_dataset/WITH_BG_NoAUGs/yolov5/data/images/zidane.jpg'
results = model(img)
results.show()

ashishupadhyaa · 2023-07-11T11:52:05Z

@memelvin99 wave Hello! Thanks for asking about handling inference results. YOLOv5 rocket PyTorch Hub models allow for simple model loading and inference in a pure python environment without using detect.py.

Simple Inference Example

This example loads a pretrained YOLOv5s model from PyTorch Hub as model and passes an image for inference. 'yolov5s' is the YOLOv5 'small' model. For details on all available models please see the README. Custom models can also be loaded, including custom trained PyTorch models and their exported variants, i.e. ONNX, TensorRT, TensorFlow, OpenVINO YOLOv5 models.
import torch

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, etc.
# model = torch.hub.load('ultralytics/yolov5', 'custom', 'path/to/best.pt')  # custom trained model

# Images
im = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, URL, PIL, OpenCV, numpy, list

# Inference
results = model(im)

# Results
results.print()  # or .show(), .save(), .crop(), .pandas(), etc.

results.xyxy[0]  # im predictions (tensor)
results.pandas().xyxy[0]  # im predictions (pandas)
#      xmin    ymin    xmax   ymax  confidence  class    name
# 0  749.50   43.50  1148.0  704.5    0.874023      0  person
# 2  114.75  195.75  1095.0  708.0    0.624512      0  person
# 3  986.00  304.00  1028.0  420.0    0.286865     27     tie
See YOLOv5 PyTorch Hub Tutorial for details.

Good luck four_leaf_clover and let us know if you have any other questions!

It is not working. Can you please look into it.

glenn-jocher · 2023-07-11T15:32:09Z

@ashishupadhyaa hello! Thank you for reaching out and sharing your concern about the YOLOv5 PyTorch Hub model. I apologize for the inconvenience you are facing.

To better assist you, could you please provide more details about the specific issue you are encountering? Are you experiencing any error messages or unexpected behavior?

Once we have more information, we will be able to investigate the issue and provide a solution or further guidance. Looking forward to hearing from you.

memelvin99 added the question Further information is requested label Jan 28, 2022

github-actions bot added the Stale Stale and schedule for closing soon label Mar 2, 2022

github-actions bot closed this as completed Mar 8, 2022

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

custom model inference without using detect.py #6460

custom model inference without using detect.py #6460

memelvin99 commented Jan 28, 2022

github-actions bot commented Jan 28, 2022 •

edited by UltralyticsAssistant

Loading

glenn-jocher commented Jan 28, 2022 •

edited

Loading

memelvin99 commented Jan 28, 2022 •

edited

Loading

glenn-jocher commented Jan 28, 2022

memelvin99 commented Jan 28, 2022

mx2013713828 commented Jan 28, 2022

glenn-jocher commented Jan 28, 2022

wisplite commented Jan 30, 2022 •

edited

Loading

glenn-jocher commented Jan 30, 2022 •

edited by UltralyticsAssistant

Loading

wisplite commented Jan 30, 2022

github-actions bot commented Mar 2, 2022 •

edited by glenn-jocher

Loading

Symbadian commented Aug 21, 2022 •

edited by glenn-jocher

Loading

Simple Inference Example

glenn-jocher commented Aug 21, 2022 •

edited

Loading

Symbadian commented Aug 21, 2022 •

edited

Loading

glenn-jocher commented Aug 21, 2022

Symbadian commented Aug 21, 2022 •

edited

Loading

glenn-jocher commented Aug 21, 2022

Symbadian commented Aug 21, 2022 •

edited

Loading

ashishupadhyaa commented Jul 11, 2023

Simple Inference Example

glenn-jocher commented Jul 11, 2023

custom model inference without using detect.py #6460

custom model inference without using detect.py #6460

Comments

memelvin99 commented Jan 28, 2022

Search before asking

Question

Additional

github-actions bot commented Jan 28, 2022 • edited by UltralyticsAssistant Loading

Requirements

Environments

Status

glenn-jocher commented Jan 28, 2022 • edited Loading

Simple Inference Example

memelvin99 commented Jan 28, 2022 • edited Loading

glenn-jocher commented Jan 28, 2022

memelvin99 commented Jan 28, 2022

mx2013713828 commented Jan 28, 2022

glenn-jocher commented Jan 28, 2022

wisplite commented Jan 30, 2022 • edited Loading

glenn-jocher commented Jan 30, 2022 • edited by UltralyticsAssistant Loading

wisplite commented Jan 30, 2022

github-actions bot commented Mar 2, 2022 • edited by glenn-jocher Loading

Symbadian commented Aug 21, 2022 • edited by glenn-jocher Loading

Simple Inference Example

xmin ymin xmax ymax confidence class name

glenn-jocher commented Aug 21, 2022 • edited Loading

Symbadian commented Aug 21, 2022 • edited Loading

glenn-jocher commented Aug 21, 2022

Symbadian commented Aug 21, 2022 • edited Loading

glenn-jocher commented Aug 21, 2022

Symbadian commented Aug 21, 2022 • edited Loading

ashishupadhyaa commented Jul 11, 2023

Simple Inference Example

glenn-jocher commented Jul 11, 2023

github-actions bot commented Jan 28, 2022 •

edited by UltralyticsAssistant

Loading

glenn-jocher commented Jan 28, 2022 •

edited

Loading

memelvin99 commented Jan 28, 2022 •

edited

Loading

wisplite commented Jan 30, 2022 •

edited

Loading

glenn-jocher commented Jan 30, 2022 •

edited by UltralyticsAssistant

Loading

github-actions bot commented Mar 2, 2022 •

edited by glenn-jocher

Loading

Symbadian commented Aug 21, 2022 •

edited by glenn-jocher

Loading

glenn-jocher commented Aug 21, 2022 •

edited

Loading

Symbadian commented Aug 21, 2022 •

edited

Loading

Symbadian commented Aug 21, 2022 •

edited

Loading

Symbadian commented Aug 21, 2022 •

edited

Loading