dev yolov3 (train and validate)

Vision/detection/yolov3/detect.py

@@ -0,0 +1,187 @@
+import ctypes
+import argparse
+import time
+from pathlib import Path
+
+import cv2
+import numpy as np
+import oneflow as flow
+
+from models.experimental import attempt_load
+from utils.datasets import LoadImages, CLASS_NAMES
+from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
+    scale_coords, scale_coords_np, xyxy2xywh, strip_optimizer, set_logging, increment_path, save_one_box
+from utils.plots import colors, plot_one_box
+from utils.flow_utils import select_device, load_classifier, time_synchronized
+from ops import lib_path
+
+
+def detect(opt):
+    # p = ctypes.CDLL(lib_path())
+    source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
+    save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
+    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
+        ('rtsp://', 'rtmp://', 'http://', 'https://'))
+
+    # Directories
+    save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)  # increment run
+    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+    # Initialize
+    set_logging()
+    device = select_device(opt.device)
+    #half = device.type != 'cpu'  # half precision only supported on CUDA
+
+    # Load model
+    model = attempt_load(weights, opt.cfg, device)  # load FP32 model
+    stride = int(model.stride.max().numpy())  # model stride
+    imgsz = check_img_size(imgsz, s=stride)  # check img_size
+    names = CLASS_NAMES
+
+    # Second-stage classifier
+    classify = False
+    if classify:
+        modelc = load_classifier(name='resnet101', n=2)  # initialize
+        modelc.load_state_dict(flow.load('weights/resnet101_ckpt'))
+
+    # Set Dataloader
+    vid_path, vid_writer = None, None
+    if webcam:
+        view_img = check_imshow()
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride)
+    else:
+        dataset = LoadImages(source, img_size=imgsz, stride=stride)
+
+    # Run inference
+    if device.type != 'cpu':
+        with flow.no_grad():
+            model(flow.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
+    t0 = time.time()
+    with flow.no_grad():
+        for path, img, im0s, vid_cap in dataset:
+            img = flow.tensor(img).to(device)
+            img = img.to(dtype=flow.float)
+            img /= 255.0  # 0 - 255 to 0.0 - 1.0
+            if img.ndimension() == 3:
+                img = img.unsqueeze(0)
+
+            # Inference
+            t1 = time_synchronized()
+            pred = model(img, opt.augment)[0]
+            np.save("output_oneflow.npy", pred.cpu().numpy())
+
+            # Apply NMS
+            pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, opt.classes, opt.agnostic_nms,
+                                    max_det=opt.max_det)
+            t2 = time_synchronized()
+
+            # Apply Classifier
+            if classify:
+                pred = apply_classifier(pred, modelc, img, im0s)
+
+            # Process detections
+            for i, det in enumerate(pred):  # detections per image
+                if webcam:  # batch_size >= 1
+                    p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
+                else:
+                    p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)
+
+                p = Path(p)  # to Path
+                save_path = str(save_dir / p.name)  # img.jpg
+                txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt
+                s += '%gx%g ' % img.numpy().shape[2:]  # print string
+                gn = flow.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+                imc = im0.copy() if opt.save_crop else im0  # for opt.save_crop
+                if len(det):
+                    # Rescale boxes from img_size to im0 size
+                    det[:, :4] = scale_coords_np(img.shape[2:], det[:, :4], im0.shape).round()
+
+                    # Print results
+                    for c in np.unique(det[:, -1]):
+                        n = (det[:, -1] == c).sum()  # detections per class
+                        s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+
+                    # Write results
+                    for *xyxy, conf, cls in reversed(det):
+                        if save_txt:  # Write to file
+                            xywh = (xyxy2xywh(flow.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+                            line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)  # label format
+                            with open(txt_path + '.txt', 'a') as f:
+                                f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+                        if save_img or opt.save_crop or view_img:  # Add bbox to image
+                            c = int(cls)  # integer class
+                            label = None if opt.hide_labels else (names[c] if opt.hide_conf else f'{names[c]} {conf:.2f}')
+                            plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=opt.line_thickness)
+                            if opt.save_crop:
+                                save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
+
+                # Print time (inference + NMS)
+                print(f'{s}Done. ({t2 - t1:.3f})')
+
+                # Stream results
+                if view_img:
+                    cv2.imshow(str(p), im0)
+                    cv2.waitKey(1)  # 1 millisecond
+
+                # Save results (image with detections)
+                if save_img:
+                    if dataset.mode == 'image':
+                        cv2.imwrite(save_path, im0)
+                    else:  # 'video' or 'stream'
+                        if vid_path != save_path:  # new video
+                            vid_path = save_path
+                            if isinstance(vid_writer, cv2.VideoWriter):
+                                vid_writer.release()  # release previous video writer
+                            if vid_cap:  # video
+                                fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                                w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                                h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                            else:  # stream
+                                fps, w, h = 30, im0.shape[1], im0.shape[0]
+                                save_path += '.mp4'
+                            vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                        vid_writer.write(im0)
+
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        print(f"Results saved to {save_dir}{s}")
+
+    print(f'Done. ({time.time() - t0:.3f}s)')
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', nargs='+', type=str, default='yolov3_ckpt', help='model path(s)')
+    parser.add_argument('--cfg', type=str, default='models/yolov3.yaml', help='model.yaml path')
+    parser.add_argument('--source', type=str, default='dataset/images', help='source')  # file/folder, 0 for webcam
+    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
+    parser.add_argument('--max-det', type=int, default=1000, help='maximum number of detections per image')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--view-img', action='store_true', help='display results')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
+    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
+    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--update', action='store_true', help='update all models')
+    parser.add_argument('--project', default='runs/detect', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save results to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
+    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
+    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
+    opt = parser.parse_args()
+    print(opt)
+    check_requirements(exclude=('pycocotools',))
+
+    if opt.update:  # update all models (to fix SourceChangeWarning)
+        for opt.weights in ['yolov3_ckpt', 'yolov3-spp_ckpt', 'yolov3-tiny_ckpt']:
+            detect(opt=opt)
+            strip_optimizer(opt.weights)
+    else:
+        detect(opt=opt)

Vision/detection/yolov3/models/common.py

@@ -0,0 +1,150 @@
+# YOLOv3 common modules
+
+import math
+from copy import copy
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+import requests
+import oneflow as flow
+import oneflow.nn as nn
+
+from utils.general import make_divisible
+
+
+def autopad(k, p=None):  # kernel, padding
+    # Pad to 'same'
+    if p is None:
+        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
+    return p
+
+
+def DWConv(c1, c2, k=1, s=1, act=True):
+    # Depthwise convolution
+    return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
+
+
+class Conv(nn.Module):
+    # Standard convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Conv, self).__init__()
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.LeakyReLU(0.1, inplace=False) if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+
+    def forward(self, x):
+        return self.act(self.bn(self.conv(x)))
+
+    def fuseforward(self, x):
+        return self.act(self.conv(x))
+
+
+class Bottleneck(nn.Module):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super(Bottleneck, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c2, 3, 1, g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class BottleneckCSP(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(BottleneckCSP, self).__init__()
+        c_ = int(c2 * e)
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
+        self.act = nn.LeakyReLU(0.1, inplace=False)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(self.act(self.bn(flow.cat((y1, y2), dim=1))))
+
+
+class C3(nn.Module):
+    # CSP bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(C3, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        return self.cv3(flow.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
+
+
+class SPP(nn.Module):
+    # Spatial pyramid pooling layer used in YOLOv3-SPP
+    def __init__(self, c1, c2, k=(5, 9, 13)):
+        super(SPP, self).__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+    def forward(self, x):
+        x = self.cv1(x)
+        return self.cv2(flow.cat([x] + [m(x) for m in self.m], 1))
+
+
+class Contract(nn.Module):
+    # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        N, C, H, W = x.size()  # assert (H / s == 0) and (W / s == 0), 'Indivisible gain'
+        s = self.gain
+        x = x.view(N, C, H // s, s, W // s, s)  # x(1,64,40,2,40,2)
+        x = x.permute(0, 3, 5, 1, 2, 4)  # x(1,2,2,64,40,40)
+        return x.view(N, C * s * s, H // s, W // s)  # x(1,256,40,40)
+
+
+class Focus(nn.Module):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Focus, self).__init__()
+        self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
+        # self.contract = Contract(gain=2)
+
+    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+        return self.conv(flow.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
+        # return self.conv(self.contract(x))
+
+
+class Expand(nn.Module):
+    # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        N, C, H, W = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
+        s = self.gain
+        x = x.view(N, s, s, C // s ** 2, H, W)  # x(1,2,2,16,80,80)
+        x = x.permute(0, 3, 4, 1, 5, 2)  # x(1,16,80,2,80,2)
+        return x.view(N, C // s ** 2, H * s, W * s)  # x(1,16,160,160)
+
+
+class Concat(nn.Module):
+    # Concatenate a list of tensors along dimension
+    def __init__(self, dimension=1):
+        super(Concat, self).__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        return flow.cat(x, self.d)