How to load custom yolo v-7 trained model

Question

How do I load a custom yolo v-7 model.

This is how I know to load a yolo v-5 model :

model = torch.hub.load('ultralytics/yolov5', 'custom', path='yolov5/runs/train/exp15/weights/last.pt', force_reload=True)

I saw videos online and they suggested to use this :

!python detect.py --weights runs/train/yolov7x-custom/weights/best.pt --conf 0.5 --img-size 640 --source final_test_v1.mp4

But I want it to be loaded like a normal model and give me the bounding box co-ordinates of where ever it found the objects.

This is how I did it in yolo v-5:

from models.experimental import attempt_load
yolov5_weight_file = r'weights/rider_helmet_number_medium.pt' # ... may need full path
model = attempt_load(yolov5_weight_file, map_location=device)

def object_detection(frame):
    img = torch.from_numpy(frame)
    img = img.permute(2, 0, 1).float().to(device)  #convert to required shape based on index
    img /= 255.0  
    if img.ndimension() == 3:
        img = img.unsqueeze(0)

    pred = model(img, augment=False)[0]
    pred = non_max_suppression(pred, conf_set, 0.20) # prediction, conf, iou
    # print(pred)
    detection_result = []
    for i, det in enumerate(pred):
        if len(det): 
            for d in det: # d = (x1, y1, x2, y2, conf, cls)
                x1 = int(d[0].item())
                y1 = int(d[1].item())
                x2 = int(d[2].item())
                y2 = int(d[3].item())
                conf = round(d[4].item(), 2)
                c = int(d[5].item())
                
                detected_name = names[c]

                # print(f'Detected: {detected_name} conf: {conf}  bbox: x1:{x1}    y1:{y1}    x2:{x2}    y2:{y2}')
                detection_result.append([x1, y1, x2, y2, conf, c])
                
                frame = cv2.rectangle(frame, (x1, y1), (x2, y2), (255,0,0), 1) # box
                if c!=1: # if it is not head bbox, then write use putText
                    frame = cv2.putText(frame, f'{names[c]} {str(conf)}', (x1, y1), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,0,255), 1, cv2.LINE_AA)

    return (frame, detection_result)

Asked By: pavan

||

Source

Answer 1

You cannot use attempt_load from the Yolov5 repo as this method is pointing to the ultralytics release files. You need to use attempt_load from Yolov7 repo as this one is pointing to the right files.

# yolov7
def attempt_download(file, repo='WongKinYiu/yolov7'):
    # Attempt file download if does not exist
    file = Path(str(file).strip().replace("'", '').lower())
...

# yolov5
def attempt_download(file, repo='ultralytics/yolov5', release='v6.2'):
    # Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.2', etc.
    from utils.general import LOGGER

    def github_assets(repository, version='latest'):
...

Then you can download it like this:

# load yolov7 method
from models.experimental import attempt_load

model = attempt_load('yolov7.pt', map_location='cuda:0')  # load FP32 model

Answered By: Mike B

Answer 2

import torch as th

def loadModel(path:str):
    model = th.hub.load("WongKinYiu/yolov7","custom",f{path}",trust_repo=True)

This will work. trust_repo = True will not ask to to say y or n.
In path you can just add your custom train model like ./best.pt

Answered By: Yameen899

Answer 3

Make prediction with yolov7 using torch.hub

!# Download YOLOv7 code
!git clone https://github.com/WongKinYiu/yolov7
%cd yolov7
from pathlib import Path

import torch

from models.yolo import Model
from utils.general import check_requirements, set_logging
from utils.google_utils import attempt_download
from utils.torch_utils import select_device

dependencies = ['torch', 'yaml']
check_requirements(Path("/content/yolov7/").parent / 'requirements.txt', exclude=('pycocotools', 'thop'))
set_logging()

def custom(path_or_model='path/to/model.pt', autoshape=True):
    """custom mode

    Arguments (3 options):
        path_or_model (str): 'path/to/model.pt'
        path_or_model (dict): torch.load('path/to/model.pt')
        path_or_model (nn.Module): torch.load('path/to/model.pt')['model']

    Returns:
        pytorch model
    """
    model = torch.load(path_or_model, map_location=torch.device('cpu')) if isinstance(path_or_model, str) else path_or_model  # load checkpoint
    if isinstance(model, dict):
        model = model['ema' if model.get('ema') else 'model']  # load model

    hub_model = Model(model.yaml).to(next(model.parameters()).device)  # create
    hub_model.load_state_dict(model.float().state_dict())  # load state_dict
    hub_model.names = model.names  # class names
    if autoshape:
        hub_model = hub_model.autoshape()  # for file/URI/PIL/cv2/np inputs and NMS
    device = select_device('0' if torch.cuda.is_available() else 'cpu')  # default to GPU if available
    return hub_model.to(device)

model = custom(path_or_model='yolov7.pt')  # custom example
# model = create(name='yolov7', pretrained=True, channels=3, classes=80, autoshape=True)  # pretrained example

# Verify inference
import numpy as np
from PIL import Image

imgs = [np.zeros((640, 480, 3))]

results = model(imgs)  # batched inference
results.print()
results.save()
df_prediction = results.pandas().xyxy
df_prediction

link to colab

https://colab.research.google.com/drive/1nKoC-_areXmc_20Xn7z6kcqHEKU7SJsX#scrollTo=yyB_MQW1OWhZ

Answered By: Chafik Boulealam

Answer 4

You can do that with:

import torch

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
path = '/path/to/your/file.pt'
model = torch.hub.load("WongKinYiu/yolov7","custom",f"{path}",trust_repo=True)

To get results you can run

results = model("/path/to/your/photo")

To get bbox you can use:

results.pandas().xyxy

Answered By: Tlaloc-ES

How to load custom yolo v-7 trained model

Question:

Answers: