mdz/paddle/ppyolov5/1_scripts/2_save_infer.py

492 lines
16 KiB
Python

import sys
sys.path.append(R"../0_ppyolov5")
import numpy as np
import torch
import cv2
import onnxruntime
import onnx
import paddle
def vis(img, boxes, scores, cls_ids, conf=0.5, class_names=None):
for i in range(len(boxes)):
box = boxes[i]
cls_id = int(cls_ids[i])
score = scores[i]
if score < conf:
continue
x0 = int(box[0])
y0 = int(box[1])
x1 = int(box[2])
y1 = int(box[3])
color = (_COLORS[cls_id] * 255).astype(np.uint8).tolist()
text = '{}:{:.1f}%'.format(class_names[cls_id], score * 100)
txt_color = (0, 0, 0) if np.mean(_COLORS[cls_id]) > 0.5 else (255, 255, 255)
font = cv2.FONT_HERSHEY_SIMPLEX
txt_size = cv2.getTextSize(text, font, 0.4, 1)[0]
cv2.rectangle(img, (x0, y0), (x1, y1), color, 2)
txt_bk_color = (_COLORS[cls_id] * 255 * 0.7).astype(np.uint8).tolist()
cv2.rectangle(
img,
(x0, y0 + 1),
(x0 + txt_size[0] + 1, y0 + int(1.5*txt_size[1])),
txt_bk_color,
-1
)
cv2.putText(img, text, (x0, y0 + txt_size[1]), font, 0.4, txt_color, thickness=1)
return img
_COLORS = np.array(
[
0.000, 0.447, 0.741,
0.850, 0.325, 0.098,
0.929, 0.694, 0.125,
0.494, 0.184, 0.556,
0.466, 0.674, 0.188,
0.301, 0.745, 0.933,
0.635, 0.078, 0.184,
0.300, 0.300, 0.300,
0.600, 0.600, 0.600,
1.000, 0.000, 0.000,
1.000, 0.500, 0.000,
0.749, 0.749, 0.000,
0.000, 1.000, 0.000,
0.000, 0.000, 1.000,
0.667, 0.000, 1.000,
0.333, 0.333, 0.000,
0.333, 0.667, 0.000,
0.333, 1.000, 0.000,
0.667, 0.333, 0.000,
0.667, 0.667, 0.000,
0.667, 1.000, 0.000,
1.000, 0.333, 0.000,
1.000, 0.667, 0.000,
1.000, 1.000, 0.000,
0.000, 0.333, 0.500,
0.000, 0.667, 0.500,
0.000, 1.000, 0.500,
0.333, 0.000, 0.500,
0.333, 0.333, 0.500,
0.333, 0.667, 0.500,
0.333, 1.000, 0.500,
0.667, 0.000, 0.500,
0.667, 0.333, 0.500,
0.667, 0.667, 0.500,
0.667, 1.000, 0.500,
1.000, 0.000, 0.500,
1.000, 0.333, 0.500,
1.000, 0.667, 0.500,
1.000, 1.000, 0.500,
0.000, 0.333, 1.000,
0.000, 0.667, 1.000,
0.000, 1.000, 1.000,
0.333, 0.000, 1.000,
0.333, 0.333, 1.000,
0.333, 0.667, 1.000,
0.333, 1.000, 1.000,
0.667, 0.000, 1.000,
0.667, 0.333, 1.000,
0.667, 0.667, 1.000,
0.667, 1.000, 1.000,
1.000, 0.000, 1.000,
1.000, 0.333, 1.000,
1.000, 0.667, 1.000,
0.333, 0.000, 0.000,
0.500, 0.000, 0.000,
0.667, 0.000, 0.000,
0.833, 0.000, 0.000,
1.000, 0.000, 0.000,
0.000, 0.167, 0.000,
0.000, 0.333, 0.000,
0.000, 0.500, 0.000,
0.000, 0.667, 0.000,
0.000, 0.833, 0.000,
0.000, 1.000, 0.000,
0.000, 0.000, 0.167,
0.000, 0.000, 0.333,
0.000, 0.000, 0.500,
0.000, 0.000, 0.667,
0.000, 0.000, 0.833,
0.000, 0.000, 1.000,
0.000, 0.000, 0.000,
0.143, 0.143, 0.143,
0.286, 0.286, 0.286,
0.429, 0.429, 0.429,
0.571, 0.571, 0.571,
0.714, 0.714, 0.714,
0.857, 0.857, 0.857,
0.000, 0.447, 0.741,
0.314, 0.717, 0.741,
0.50, 0.5, 0
]
).astype(np.float32).reshape(-1, 3)
COCO_CLASSES = (
"person",
"bicycle",
"car",
"motorcycle",
"airplane",
"bus",
"train",
"truck",
"boat",
"traffic light",
"fire hydrant",
"stop sign",
"parking meter",
"bench",
"bird",
"cat",
"dog",
"horse",
"sheep",
"cow",
"elephant",
"bear",
"zebra",
"giraffe",
"backpack",
"umbrella",
"handbag",
"tie",
"suitcase",
"frisbee",
"skis",
"snowboard",
"sports ball",
"kite",
"baseball bat",
"baseball glove",
"skateboard",
"surfboard",
"tennis racket",
"bottle",
"wine glass",
"cup",
"fork",
"knife",
"spoon",
"bowl",
"banana",
"apple",
"sandwich",
"orange",
"broccoli",
"carrot",
"hot dog",
"pizza",
"donut",
"cake",
"chair",
"couch",
"potted plant",
"bed",
"dining table",
"toilet",
"tv",
"laptop",
"mouse",
"remote",
"keyboard",
"cell phone",
"microwave",
"oven",
"toaster",
"sink",
"refrigerator",
"book",
"clock",
"vase",
"scissors",
"teddy bear",
"hair drier",
"toothbrush",
)
class Colors:
# Ultralytics color palette https://ultralytics.com/
def __init__(self):
# hex = matplotlib.colors.TABLEAU_COLORS.values()
hexs = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB',
'2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7')
self.palette = [self.hex2rgb(f'#{c}') for c in hexs]
self.n = len(self.palette)
self.pose_palette = np.array([[255, 128, 0], [255, 153, 51], [255, 178, 102], [230, 230, 0], [255, 153, 255],
[153, 204, 255], [255, 102, 255], [255, 51, 255], [102, 178, 255], [51, 153, 255],
[255, 153, 153], [255, 102, 102], [255, 51, 51], [153, 255, 153], [102, 255, 102],
[51, 255, 51], [0, 255, 0], [0, 0, 255], [255, 0, 0], [255, 255, 255]],
dtype=np.uint8)
def __call__(self, i, bgr=False):
c = self.palette[int(i) % self.n]
return (c[2], c[1], c[0]) if bgr else c
@staticmethod
def hex2rgb(h): # rgb order (PIL)
return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4))
colors = Colors() # create instance for 'from utils.plots import colors'
skeleton = [[16, 14], [14, 12], [17, 15], [15, 13], [12, 13], [6, 12], [7, 13], [6, 7], [6, 8], [7, 9],
[8, 10], [9, 11], [2, 3], [1, 2], [1, 3], [2, 4], [3, 5], [4, 6], [5, 7]]
limb_color = colors.pose_palette[[9, 9, 9, 9, 7, 7, 7, 0, 0, 0, 0, 0, 16, 16, 16, 16, 16, 16, 16]]
kpt_color = colors.pose_palette[[16, 16, 16, 16, 16, 0, 0, 0, 0, 0, 0, 9, 9, 9, 9, 9, 9]]
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)
bottom = int(round(dh + 0.1))
right = int(round(dw + 0.1))
im = cv2.copyMakeBorder(im, 0, bottom, 0, right, cv2.BORDER_CONSTANT, value=color) # add border
return im, ratio, (dw, dh)
import time
import torchvision
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 box_iou(box1, box2, eps=1e-7):
# 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
"""
# inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
(a1, a2), (b1, b2) = box1.unsqueeze(1).chunk(2, 2), box2.unsqueeze(0).chunk(2, 2)
inter = (torch.min(a2, b2) - torch.max(a1, b1)).clamp(0).prod(2)
# IoU = inter / (area1 + area2 - inter)
return inter / ((a2 - a1).prod(2) + (b2 - b1).prod(2) - inter + eps)
def non_max_suppression(
prediction,
conf_thres=0.25,
iou_thres=0.45,
classes=None,
agnostic=False,
multi_label=False,
labels=(),
max_det=300,
nm=0, # number of masks
):
"""Non-Maximum Suppression (NMS) on inference results to reject overlapping detections
Returns:
list of detections, on (n,6) tensor per image [xyxy, conf, cls]
"""
# 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'
if isinstance(prediction, (list, tuple)): # YOLOv3 model in validation model, output = (inference_out, loss_out)
prediction = prediction[0] # select only inference output
device = prediction.device
mps = 'mps' in device.type # Apple MPS
if mps: # MPS not fully supported yet, convert tensors to CPU before NMS
prediction = prediction.cpu()
bs = prediction.shape[0] # batch size
nc = prediction.shape[2] - nm - 5 # number of classes
xc = prediction[..., 4] > conf_thres # candidates
# Settings
# min_wh = 2 # (pixels) minimum box width and height
max_wh = 7680 # (pixels) maximum box width and height
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
time_limit = 0.5 + 0.05 * bs # 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()
mi = 5 + nc # mask start index
output = [torch.zeros((0, 6 + nm), device=prediction.device)] * bs
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 + nm + 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/Mask
box = xywh2xyxy(x[:, :4]) # center_x, center_y, width, height) to (x1, y1, x2, y2)
mask = x[:, mi:] # zero columns if no masks
# Detections matrix nx6 (xyxy, conf, cls)
if multi_label:
i, j = (x[:, 5:mi] > conf_thres).nonzero(as_tuple=False).T
x = torch.cat((box[i], x[i, 5 + j, None], j[:, None].float(), mask[i]), 1)
else: # best class only
conf, j = x[:, 5:mi].max(1, keepdim=True)
x = torch.cat((box, conf, j.float(), mask), 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
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence and remove excess boxes
# 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
i = i[:max_det] # limit detections
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 mps:
output[xi] = output[xi].to(device)
if (time.time() - t) > time_limit:
break # time limit exceeded
return output
stride = [8, 16, 32]
anchors = torch.tensor([[[10,13], [16,30], [33,23]], [[30,61], [62,45], [59,119]], [[116,90], [156,198], [373,326]]])
def make_grid(nx=20, ny=20, i=0):
shape = 1, 3, ny, nx, 2 # grid shape
y, x = torch.arange(ny), torch.arange(nx)
# if check_version(torch.__version__, '1.10.0'): # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
# yv, xv = torch.meshgrid(y, x, indexing='ij')
# else:
yv, xv = torch.meshgrid(y, x)
grid = torch.stack((xv, yv), 2).expand(shape) - 0.5 # add grid offset, i.e. y = 2.0 * x - 0.5
anchor_grid = anchors[i].view((1, 3, 1, 1, 2)).expand(shape)
return grid, anchor_grid
onnx_model = onnxruntime.InferenceSession("../2_compile/fmodel/ppyolov5s-640x640.onnx")
img_path = '../2_compile/qtset/coco/bus.jpg'
net_size = (640,640)
N_CLASS = 80
img_raw = cv2.imread(img_path)
img = letterbox(img_raw, new_shape=net_size, stride=32, auto=False)[0]
# cv2.imshow("",img)
# cv2.waitKey()
img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
img = np.ascontiguousarray(img)
im = torch.from_numpy(img).float().unsqueeze(0)
im /= 255
input = im.numpy()
out1 = onnx_model.run([onnx_model.get_outputs()[0].name], {onnx_model.get_inputs()[0].name: input})
out2 = onnx_model.run([onnx_model.get_outputs()[1].name], {onnx_model.get_inputs()[0].name: input})
out3 = onnx_model.run([onnx_model.get_outputs()[2].name], {onnx_model.get_inputs()[0].name: input})
outputs = [torch.from_numpy(out1[0]),torch.from_numpy(out2[0]),torch.from_numpy(out3[0])]
# 后处理
z = []
grid = [torch.zeros(1)] * 3
anchor_grid = [torch.zeros(1)] * 3
for i in range(3):
bs, _ , ny, nx = outputs[i].shape
outputs[i] = outputs[i].view(bs, 3, N_CLASS+5, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
grid[i], anchor_grid[i] = make_grid(nx, ny, i)
y = outputs[i].sigmoid()
y[..., 0:2] = (y[..., 0:2] * 2 + grid[i]) * stride[i] # xy
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * anchor_grid[i] # wh
z.append(y.view(bs, -1, N_CLASS+5))
pred = torch.cat(z, 1) #torch.size([1, 25200, 85])
# NMS
conf_thres = 0.25
iou_thres = 0.45
pred = non_max_suppression(pred, conf_thres, iou_thres, classes=None, agnostic=False, max_det=1000)
# 结果显示
det = pred[0]
ratio = min(net_size[0] / img_raw.shape[0], net_size[1] / img_raw.shape[1])
det[:, :4] /= ratio
result_image = vis(img_raw, boxes=det[:,:4], scores=det[:,4], cls_ids=det[:,5], conf=conf_thres, class_names=COCO_CLASSES)
cv2.imshow(" ", result_image)
cv2.waitKey()