The simplified code for Yolov5 model loading and inference only requires one file and does not depend on other files.
If the following error is reported, please download the simplified version of the models folder. Download address: Yolov5 simplest inference code-deep learning document resources-CSDN download .
File "D:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 853, in _load
result = unpickler.load()
ModuleNotFoundError: No module named 'models'
This error is because torch saves the model storage path and structure, but does not save the calculation process. Therefore, the definition of the model in the models file is required.
File "D:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 853, in _load
result = unpickler.load()
ModuleNotFoundError: No module named 'models'
The simplest inference code of Yolov5 is as follows:
# -*- coding: utf-8 -*-
"""
Created on Fri Apr 1 16:12:34 2022
@author: suiyingy
"""
import cv2
import torch
import torchvision
import numpy as np
import time
import os
def xywh2xyxy(x):
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
return y
def xyxy2xywh(x):
# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center
y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center
y[:, 2] = x[:, 2] - x[:, 0] # width
y[:, 3] = x[:, 3] - x[:, 1] # height
return y
def box_iou(box1, box2):
# https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
"""
Return intersection-over-union (Jaccard index) of boxes.
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
Arguments:
box1 (Tensor[N, 4])
box2 (Tensor[M, 4])
Returns:
iou (Tensor[N, M]): the NxM matrix containing the pairwise
IoU values for every element in boxes1 and boxes2
"""
def box_area(box):
# box = 4xn
return (box[2] - box[0]) * (box[3] - box[1])
area1 = box_area(box1.T)
area2 = box_area(box2.T)
# inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter)
def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
labels=(), max_det=300):
"""Runs Non-Maximum Suppression (NMS) on inference results
Returns:
list of detections, on (n,6) tensor per image [xyxy, conf, cls]
"""
nc = prediction.shape[2] - 5 # number of classes
xc = prediction[..., 4] > conf_thres # candidates
# Checks
assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
# Settings
min_wh, max_wh = 2, 7680 # (pixels) minimum and maximum box width and height
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
time_limit = 10.0 # seconds to quit after
redundant = True # require redundant detections
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
merge = False # use merge-NMS
t = time.time()
output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
for xi, x in enumerate(prediction): # image index, image inference
# Apply constraints
x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
x = x[xc[xi]] # confidence
# Cat apriori labels if autolabelling
if labels and len(labels[xi]):
lb = labels[xi]
v = torch.zeros((len(lb), nc + 5), device=x.device)
v[:, :4] = lb[:, 1:5] # box
v[:, 4] = 1.0 # conf
v[range(len(lb)), lb[:, 0].long() + 5] = 1.0 # cls
x = torch.cat((x, v), 0)
# If none remain process next image
if not x.shape[0]:
continue
# Compute conf
x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf
# Box (center x, center y, width, height) to (x1, y1, x2, y2)
box = xywh2xyxy(x[:, :4])
# Detections matrix nx6 (xyxy, conf, cls)
if multi_label:
i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
else: # best class only
conf, j = x[:, 5:].max(1, keepdim=True)
x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
# Filter by class
if classes is not None:
x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
# Apply finite constraint
# if not torch.isfinite(x).all():
# x = x[torch.isfinite(x).all(1)]
# Check shape
n = x.shape[0] # number of boxes
if not n: # no boxes
continue
elif n > max_nms: # excess boxes
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
# Batched NMS
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
if i.shape[0] > max_det: # limit detections
i = i[:max_det]
if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
weights = iou * scores[None] # box weights
x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
if redundant:
i = i[iou.sum(1) > 1] # require redundancy
output[xi] = x[i]
if (time.time() - t) > time_limit:
break # time limit exceeded
return output
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
# Rescale coords (xyxy) from img1_shape to img0_shape
if ratio_pad is None: # calculate from img0_shape
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
else:
gain = ratio_pad[0][0]
pad = ratio_pad[1]
coords[:, [0, 2]] -= pad[0] # x padding
coords[:, [1, 3]] -= pad[1] # y padding
coords[:, :4] /= gain
clip_coords(coords, img0_shape)
return coords
def clip_coords(boxes, shape):
# Clip bounding xyxy bounding boxes to image shape (height, width)
if isinstance(boxes, torch.Tensor): # faster individually
boxes[:, 0].clamp_(0, shape[1]) # x1
boxes[:, 1].clamp_(0, shape[0]) # y1
boxes[:, 2].clamp_(0, shape[1]) # x2
boxes[:, 3].clamp_(0, shape[0]) # y2
else: # np.array (faster grouped)
boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1]) # x1, x2
boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0]) # y1, y2
def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
# Resize and pad image while meeting stride-multiple constraints
shape = im.shape[:2] # current shape [height, width]
if isinstance(new_shape, int):
new_shape = (new_shape, new_shape)
# Scale ratio (new / old)
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
if not scaleup: # only scale down, do not scale up (for better val mAP)
r = min(r, 1.0)
# Compute padding
ratio = r, r # width, height ratios
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
if auto: # minimum rectangle
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
elif scaleFill: # stretch
dw, dh = 0.0, 0.0
new_unpad = (new_shape[1], new_shape[0])
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
dw /= 2 # divide padding into 2 sides
dh /= 2
if shape[::-1] != new_unpad: # resize
im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
return im, ratio, (dw, dh)
def preprocess(path, img_size, stride, auto):
img_bgr = cv2.imread(path) # BGR
assert img_bgr is not None, f'Image Not Found {path}'
# Padded resize
img_rgb = letterbox(img_bgr, img_size, stride=stride, auto=auto)[0]
# Convert
img_rgb = img_rgb.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
img_rgb = np.ascontiguousarray(img_rgb)
return img_rgb, img_bgr
class Detect():
def __init__(self, weights='yolov5s.pt'):
self.device = 'cpu'
self.weights = weights
self.model = None
self.imgsz = (640, 640)
self.conf_thres=0.25
self.iou_thres=0.45
self.save_txt=True
self.save_conf=True
self.save_dir = './detect/'
if not os.path.exists(self.save_dir):
os.makedirs(self.save_dir)
if torch.cuda.is_available() and torch.cuda.device_count() > 1:
self.device = torch.device('cuda:0')
self.init_model()
self.stride = max(int(self.model.stride.max()), 32)
def init_model(self):
ckpt = torch.load(self.weights, map_location=self.device) # load
ckpt = (ckpt.get('ema') or ckpt['model']).float() # FP32 model
fuse = True
self.model = ckpt.fuse().eval() if fuse else ckpt.eval() # fused or un-fused model in eval mode
self.model.float()
def infer_image(self, image_path):
im, im0 = preprocess(image_path, img_size=self.imgsz, stride=self.stride, auto=True)
im = torch.from_numpy(im).to(self.device).float() / 255
if len(im.shape) == 3:
im = im[None] # expand for batch dim
# Inference
pred = self.model(im, augment=False, visualize=False)[0]
# NMS
pred = non_max_suppression(pred, self.conf_thres, self.iou_thres, None, False, max_det=1000)
det = pred[0]
fn = image_path.rsplit('/', 1)[-1]
txt_path = self.save_dir + fn.split('.', 1)[0] + '.txt'
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
# Write results
for *xyxy, conf, cls in reversed(det):
if self.save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if self.save_conf else (cls, *xywh) # label format
with open(txt_path, 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if __name__ == "__main__":
detect = Detect('best.pt')
detect.infer_image('test.png')
The simplified code for Yolov5 model loading and inference only requires one file and does not depend on other files.
If the following error is reported, please download the simplified version of the models folder. Download address: Yolov5 simplest inference code-deep learning document resources-CSDN download .
File "D:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 853, in _load
result = unpickler.load()
ModuleNotFoundError: No module named 'models'
This error is because torch saves the model storage path and structure, but does not save the calculation process. Therefore, the definition of the model in the models file is required.
File "D:\ProgramData\Anaconda3\lib\site-packages\torch\serialization.py", line 853, in _load
result = unpickler.load()
ModuleNotFoundError: No module named 'models'
For more three-dimensional and two-dimensional perception algorithms and financial quantitative analysis algorithms, please pay attention to the " Lele Perception Academy " WeChat official account, which will be continuously updated.