Changes

detect.py

@@ -0,0 +1,195 @@
+import argparse
+import time
+from pathlib import Path
+
+import cv2
+import torch
+import torch.backends.cudnn as cudnn
+from numpy import random
+
+from models.experimental import attempt_load
+from utils.datasets import LoadStreams, LoadImages
+from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
+    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
+from utils.plots import plot_one_box
+from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel
+
+
+def detect(save_img=False):
+    source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace
+    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 = Path(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, map_location=device)  # load FP32 model
+    stride = int(model.stride.max())  # model stride
+    imgsz = check_img_size(imgsz, s=stride)  # check img_size
+
+    if trace:
+        model = TracedModel(model, device, opt.img_size)
+
+    if half:
+        model.half()  # to FP16
+
+    # Second-stage classifier
+    classify = False
+    if classify:
+        modelc = load_classifier(name='resnet101', n=2)  # initialize
+        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
+
+    # Set Dataloader
+    vid_path, vid_writer = None, None
+    if webcam:
+        view_img = check_imshow()
+        cudnn.benchmark = True  # set True to speed up constant image size inference
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride)
+    else:
+        dataset = LoadImages(source, img_size=imgsz, stride=stride)
+
+    # Get names and colors
+    names = model.module.names if hasattr(model, 'module') else model.names
+    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
+
+    # Run inference
+    if device.type != 'cpu':
+        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
+    old_img_w = old_img_h = imgsz
+    old_img_b = 1
+
+    t0 = time.time()
+    for path, img, im0s, vid_cap in dataset:
+        img = torch.from_numpy(img).to(device)
+        img = img.half() if half else img.float()  # uint8 to fp16/32
+        img /= 255.0  # 0 - 255 to 0.0 - 1.0
+        if img.ndimension() == 3:
+            img = img.unsqueeze(0)
+
+        # Warmup
+        if device.type != 'cpu' and (old_img_b != img.shape[0] or old_img_h != img.shape[2] or old_img_w != img.shape[3]):
+            old_img_b = img.shape[0]
+            old_img_h = img.shape[2]
+            old_img_w = img.shape[3]
+            for i in range(3):
+                model(img, augment=opt.augment)[0]
+
+        # Inference
+        t1 = time_synchronized()
+        pred = model(img, augment=opt.augment)[0]
+        t2 = time_synchronized()
+
+        # Apply NMS
+        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
+        t3 = 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], '%g: ' % i, im0s[i].copy(), dataset.count
+            else:
+                p, s, im0, frame = path, '', im0s, 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
+            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(img.shape[2:], det[:, :4], im0.shape).round()
+
+                # Print results
+                for c in det[:, -1].unique():
+                    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(torch.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 view_img:  # Add bbox to image
+                        label = f'{names[int(cls)]} {conf:.2f}'
+                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=1)
+
+            # Print time (inference + NMS)
+            print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS')
+
+            # 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)
+                    print(f" The image with the result is saved in: {save_path}")
+                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='yolov7.pt', help='model.pt path(s)')
+    parser.add_argument('--source', type=str, default='inference/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('--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('--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('--no-trace', action='store_true', help='don`t trace model')
+    opt = parser.parse_args()
+    print(opt)
+    #check_requirements(exclude=('pycocotools', 'thop'))
+
+    with torch.no_grad():
+        if opt.update:  # update all models (to fix SourceChangeWarning)
+            for opt.weights in ['yolov7.pt']:
+                detect()
+                strip_optimizer(opt.weights)
+        else:
+            detect()

export.py

@@ -0,0 +1,205 @@
+import argparse
+import sys
+import time
+import warnings
+
+sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+
+import torch
+import torch.nn as nn
+from torch.utils.mobile_optimizer import optimize_for_mobile
+
+import models
+from models.experimental import attempt_load, End2End
+from utils.activations import Hardswish, SiLU
+from utils.general import set_logging, check_img_size
+from utils.torch_utils import select_device
+from utils.add_nms import RegisterNMS
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default='./yolor-csp-c.pt', help='weights path')
+    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size')  # height, width
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes')
+    parser.add_argument('--dynamic-batch', action='store_true', help='dynamic batch onnx for tensorrt and onnx-runtime')
+    parser.add_argument('--grid', action='store_true', help='export Detect() layer grid')
+    parser.add_argument('--end2end', action='store_true', help='export end2end onnx')
+    parser.add_argument('--max-wh', type=int, default=None, help='None for tensorrt nms, int value for onnx-runtime nms')
+    parser.add_argument('--topk-all', type=int, default=100, help='topk objects for every images')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='iou threshold for NMS')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='conf threshold for NMS')
+    parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--simplify', action='store_true', help='simplify onnx model')
+    parser.add_argument('--include-nms', action='store_true', help='export end2end onnx')
+    parser.add_argument('--fp16', action='store_true', help='CoreML FP16 half-precision export')
+    parser.add_argument('--int8', action='store_true', help='CoreML INT8 quantization')
+    opt = parser.parse_args()
+    opt.img_size *= 2 if len(opt.img_size) == 1 else 1  # expand
+    opt.dynamic = opt.dynamic and not opt.end2end
+    opt.dynamic = False if opt.dynamic_batch else opt.dynamic
+    print(opt)
+    set_logging()
+    t = time.time()
+
+    # Load PyTorch model
+    device = select_device(opt.device)
+    model = attempt_load(opt.weights, map_location=device)  # load FP32 model
+    labels = model.names
+
+    # Checks
+    gs = int(max(model.stride))  # grid size (max stride)
+    opt.img_size = [check_img_size(x, gs) for x in opt.img_size]  # verify img_size are gs-multiples
+
+    # Input
+    img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device)  # image size(1,3,320,192) iDetection
+
+    # Update model
+    for k, m in model.named_modules():
+        m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
+        if isinstance(m, models.common.Conv):  # assign export-friendly activations
+            if isinstance(m.act, nn.Hardswish):
+                m.act = Hardswish()
+            elif isinstance(m.act, nn.SiLU):
+                m.act = SiLU()
+        # elif isinstance(m, models.yolo.Detect):
+        #     m.forward = m.forward_export  # assign forward (optional)
+    model.model[-1].export = not opt.grid  # set Detect() layer grid export
+    y = model(img)  # dry run
+    if opt.include_nms:
+        model.model[-1].include_nms = True
+        y = None
+
+    # TorchScript export
+    try:
+        print('\nStarting TorchScript export with torch %s...' % torch.__version__)
+        f = opt.weights.replace('.pt', '.torchscript.pt')  # filename
+        ts = torch.jit.trace(model, img, strict=False)
+        ts.save(f)
+        print('TorchScript export success, saved as %s' % f)
+    except Exception as e:
+        print('TorchScript export failure: %s' % e)
+
+    # CoreML export
+    try:
+        import coremltools as ct
+
+        print('\nStarting CoreML export with coremltools %s...' % ct.__version__)
+        # convert model from torchscript and apply pixel scaling as per detect.py
+        ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
+        bits, mode = (8, 'kmeans_lut') if opt.int8 else (16, 'linear') if opt.fp16 else (32, None)
+        if bits < 32:
+            if sys.platform.lower() == 'darwin':  # quantization only supported on macOS
+                with warnings.catch_warnings():
+                    warnings.filterwarnings("ignore", category=DeprecationWarning)  # suppress numpy==1.20 float warning
+                    ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
+            else:
+                print('quantization only supported on macOS, skipping...')
+
+        f = opt.weights.replace('.pt', '.mlmodel')  # filename
+        ct_model.save(f)
+        print('CoreML export success, saved as %s' % f)
+    except Exception as e:
+        print('CoreML export failure: %s' % e)
+                     
+    # TorchScript-Lite export
+    try:
+        print('\nStarting TorchScript-Lite export with torch %s...' % torch.__version__)
+        f = opt.weights.replace('.pt', '.torchscript.ptl')  # filename
+        tsl = torch.jit.trace(model, img, strict=False)
+        tsl = optimize_for_mobile(tsl)
+        tsl._save_for_lite_interpreter(f)
+        print('TorchScript-Lite export success, saved as %s' % f)
+    except Exception as e:
+        print('TorchScript-Lite export failure: %s' % e)
+
+    # ONNX export
+    try:
+        import onnx
+
+        print('\nStarting ONNX export with onnx %s...' % onnx.__version__)
+        f = opt.weights.replace('.pt', '.onnx')  # filename
+        model.eval()
+        output_names = ['classes', 'boxes'] if y is None else ['output']
+        dynamic_axes = None
+        if opt.dynamic:
+            dynamic_axes = {'images': {0: 'batch', 2: 'height', 3: 'width'},  # size(1,3,640,640)
+             'output': {0: 'batch', 2: 'y', 3: 'x'}}
+        if opt.dynamic_batch:
+            opt.batch_size = 'batch'
+            dynamic_axes = {
+                'images': {
+                    0: 'batch',
+                }, }
+            if opt.end2end and opt.max_wh is None:
+                output_axes = {
+                    'num_dets': {0: 'batch'},
+                    'det_boxes': {0: 'batch'},
+                    'det_scores': {0: 'batch'},
+                    'det_classes': {0: 'batch'},
+                }
+            else:
+                output_axes = {
+                    'output': {0: 'batch'},
+                }
+            dynamic_axes.update(output_axes)
+        if opt.grid:
+            if opt.end2end:
+                print('\nStarting export end2end onnx model for %s...' % 'TensorRT' if opt.max_wh is None else 'onnxruntime')
+                model = End2End(model,opt.topk_all,opt.iou_thres,opt.conf_thres,opt.max_wh,device)
+                if opt.end2end and opt.max_wh is None:
+                    output_names = ['num_dets', 'det_boxes', 'det_scores', 'det_classes']
+                    shapes = [opt.batch_size, 1, opt.batch_size, opt.topk_all, 4,
+                              opt.batch_size, opt.topk_all, opt.batch_size, opt.topk_all]
+                else:
+                    output_names = ['output']
+            else:
+                model.model[-1].concat = True
+
+        torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
+                          output_names=output_names,
+                          dynamic_axes=dynamic_axes)
+
+        # Checks
+        onnx_model = onnx.load(f)  # load onnx model
+        onnx.checker.check_model(onnx_model)  # check onnx model
+
+        if opt.end2end and opt.max_wh is None:
+            for i in onnx_model.graph.output:
+                for j in i.type.tensor_type.shape.dim:
+                    j.dim_param = str(shapes.pop(0))
+
+        # print(onnx.helper.printable_graph(onnx_model.graph))  # print a human readable model
+
+        # # Metadata
+        # d = {'stride': int(max(model.stride))}
+        # for k, v in d.items():
+        #     meta = onnx_model.metadata_props.add()
+        #     meta.key, meta.value = k, str(v)
+        # onnx.save(onnx_model, f)
+
+        if opt.simplify:
+            try:
+                import onnxsim
+
+                print('\nStarting to simplify ONNX...')
+                onnx_model, check = onnxsim.simplify(onnx_model)
+                assert check, 'assert check failed'
+            except Exception as e:
+                print(f'Simplifier failure: {e}')
+
+        # print(onnx.helper.printable_graph(onnx_model.graph))  # print a human readable model
+        onnx.save(onnx_model,f)
+        print('ONNX export success, saved as %s' % f)
+
+        if opt.include_nms:
+            print('Registering NMS plugin for ONNX...')
+            mo = RegisterNMS(f)
+            mo.register_nms()
+            mo.save(f)
+
+    except Exception as e:
+        print('ONNX export failure: %s' % e)
+
+    # Finish
+    print('\nExport complete (%.2fs). Visualize with https://github.com/lutzroeder/netron.' % (time.time() - t))

hubconf.py

@@ -0,0 +1,97 @@
+"""PyTorch Hub models
+
+Usage:
+    import torch
+    model = torch.hub.load('repo', 'model')
+"""
+
+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(__file__).parent / 'requirements.txt', exclude=('pycocotools', 'thop'))
+set_logging()
+
+
+def create(name, pretrained, channels, classes, autoshape):
+    """Creates a specified model
+
+    Arguments:
+        name (str): name of model, i.e. 'yolov7'
+        pretrained (bool): load pretrained weights into the model
+        channels (int): number of input channels
+        classes (int): number of model classes
+
+    Returns:
+        pytorch model
+    """
+    try:
+        cfg = list((Path(__file__).parent / 'cfg').rglob(f'{name}.yaml'))[0]  # model.yaml path
+        model = Model(cfg, channels, classes)
+        if pretrained:
+            fname = f'{name}.pt'  # checkpoint filename
+            attempt_download(fname)  # download if not found locally
+            ckpt = torch.load(fname, map_location=torch.device('cpu'))  # load
+            msd = model.state_dict()  # model state_dict
+            csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
+            csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape}  # filter
+            model.load_state_dict(csd, strict=False)  # load
+            if len(ckpt['model'].names) == classes:
+                model.names = ckpt['model'].names  # set class names attribute
+            if autoshape:
+                model = 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 model.to(device)
+
+    except Exception as e:
+        s = 'Cache maybe be out of date, try force_reload=True.'
+        raise Exception(s) from e
+
+
+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)
+
+
+def yolov7(pretrained=True, channels=3, classes=80, autoshape=True):
+    return create('yolov7', pretrained, channels, classes, autoshape)
+
+
+if __name__ == '__main__':
+    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()

scripts/get_coco.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+# COCO 2017 dataset http://cocodataset.org
+# Download command: bash ./scripts/get_coco.sh
+
+# Download/unzip labels
+d='./' # unzip directory
+url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
+f='coco2017labels-segments.zip' # or 'coco2017labels.zip', 68 MB
+echo 'Downloading' $url$f ' ...'
+curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
+
+# Download/unzip images
+d='./coco/images' # unzip directory
+url=http://images.cocodataset.org/zips/
+f1='train2017.zip' # 19G, 118k images
+f2='val2017.zip'   # 1G, 5k images
+f3='test2017.zip'  # 7G, 41k images (optional)
+for f in $f1 $f2 $f3; do
+  echo 'Downloading' $url$f '...'
+  curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
+done
+wait # finish background tasks

test.py

@@ -0,0 +1,347 @@
+import argparse
+import json
+import os
+from pathlib import Path
+from threading import Thread
+
+import numpy as np
+import torch
+import yaml
+from tqdm import tqdm
+
+from models.experimental import attempt_load
+from utils.datasets import create_dataloader
+from utils.general import coco80_to_coco91_class, check_dataset, check_file, check_img_size, check_requirements, \
+    box_iou, non_max_suppression, scale_coords, xyxy2xywh, xywh2xyxy, set_logging, increment_path, colorstr
+from utils.metrics import ap_per_class, ConfusionMatrix
+from utils.plots import plot_images, output_to_target, plot_study_txt
+from utils.torch_utils import select_device, time_synchronized, TracedModel
+
+
+def test(data,
+         weights=None,
+         batch_size=32,
+         imgsz=640,
+         conf_thres=0.001,
+         iou_thres=0.6,  # for NMS
+         save_json=False,
+         single_cls=False,
+         augment=False,
+         verbose=False,
+         model=None,
+         dataloader=None,
+         save_dir=Path(''),  # for saving images
+         save_txt=False,  # for auto-labelling
+         save_hybrid=False,  # for hybrid auto-labelling
+         save_conf=False,  # save auto-label confidences
+         plots=True,
+         wandb_logger=None,
+         compute_loss=None,
+         half_precision=True,
+         trace=False,
+         is_coco=False):
+    # Initialize/load model and set device
+    training = model is not None
+    if training:  # called by train.py
+        device = next(model.parameters()).device  # get model device
+
+    else:  # called directly
+        set_logging()
+        device = select_device(opt.device, batch_size=batch_size)
+
+        # Directories
+        save_dir = Path(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
+
+        # Load model
+        model = attempt_load(weights, map_location=device)  # load FP32 model
+        gs = max(int(model.stride.max()), 32)  # grid size (max stride)
+        imgsz = check_img_size(imgsz, s=gs)  # check img_size
+        
+        if trace:
+            model = TracedModel(model, device, opt.img_size)
+
+    # Half
+    half = device.type != 'cpu' and half_precision  # half precision only supported on CUDA
+    if half:
+        model.half()
+
+    # Configure
+    model.eval()
+    if isinstance(data, str):
+        is_coco = data.endswith('coco.yaml')
+        with open(data) as f:
+            data = yaml.load(f, Loader=yaml.SafeLoader)
+    check_dataset(data)  # check
+    nc = 1 if single_cls else int(data['nc'])  # number of classes
+    iouv = torch.linspace(0.5, 0.95, 10).to(device)  # iou vector for mAP@0.5:0.95
+    niou = iouv.numel()
+
+    # Logging
+    log_imgs = 0
+    if wandb_logger and wandb_logger.wandb:
+        log_imgs = min(wandb_logger.log_imgs, 100)
+    # Dataloader
+    if not training:
+        if device.type != 'cpu':
+            model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
+        task = opt.task if opt.task in ('train', 'val', 'test') else 'val'  # path to train/val/test images
+        dataloader = create_dataloader(data[task], imgsz, batch_size, gs, opt, pad=0.5, rect=True,
+                                       prefix=colorstr(f'{task}: '))[0]
+
+    seen = 0
+    confusion_matrix = ConfusionMatrix(nc=nc)
+    names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
+    coco91class = coco80_to_coco91_class()
+    s = ('%20s' + '%12s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95')
+    p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0.
+    loss = torch.zeros(3, device=device)
+    jdict, stats, ap, ap_class, wandb_images = [], [], [], [], []
+    for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
+        img = img.to(device, non_blocking=True)
+        img = img.half() if half else img.float()  # uint8 to fp16/32
+        img /= 255.0  # 0 - 255 to 0.0 - 1.0
+        targets = targets.to(device)
+        nb, _, height, width = img.shape  # batch size, channels, height, width
+
+        with torch.no_grad():
+            # Run model
+            t = time_synchronized()
+            out, train_out = model(img, augment=augment)  # inference and training outputs
+            t0 += time_synchronized() - t
+
+            # Compute loss
+            if compute_loss:
+                loss += compute_loss([x.float() for x in train_out], targets)[1][:3]  # box, obj, cls
+
+            # Run NMS
+            targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device)  # to pixels
+            lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
+            t = time_synchronized()
+            out = non_max_suppression(out, conf_thres=conf_thres, iou_thres=iou_thres, labels=lb, multi_label=True)
+            t1 += time_synchronized() - t
+
+        # Statistics per image
+        for si, pred in enumerate(out):
+            labels = targets[targets[:, 0] == si, 1:]
+            nl = len(labels)
+            tcls = labels[:, 0].tolist() if nl else []  # target class
+            path = Path(paths[si])
+            seen += 1
+
+            if len(pred) == 0:
+                if nl:
+                    stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls))
+                continue
+
+            # Predictions
+            predn = pred.clone()
+            scale_coords(img[si].shape[1:], predn[:, :4], shapes[si][0], shapes[si][1])  # native-space pred
+
+            # Append to text file
+            if save_txt:
+                gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0]]  # normalization gain whwh
+                for *xyxy, conf, cls in predn.tolist():
+                    xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+                    line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
+                    with open(save_dir / 'labels' / (path.stem + '.txt'), 'a') as f:
+                        f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+            # W&B logging - Media Panel Plots
+            if len(wandb_images) < log_imgs and wandb_logger.current_epoch > 0:  # Check for test operation
+                if wandb_logger.current_epoch % wandb_logger.bbox_interval == 0:
+                    box_data = [{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
+                                 "class_id": int(cls),
+                                 "box_caption": "%s %.3f" % (names[cls], conf),
+                                 "scores": {"class_score": conf},
+                                 "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
+                    boxes = {"predictions": {"box_data": box_data, "class_labels": names}}  # inference-space
+                    wandb_images.append(wandb_logger.wandb.Image(img[si], boxes=boxes, caption=path.name))
+            wandb_logger.log_training_progress(predn, path, names) if wandb_logger and wandb_logger.wandb_run else None
+
+            # Append to pycocotools JSON dictionary
+            if save_json:
+                # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
+                image_id = int(path.stem) if path.stem.isnumeric() else path.stem
+                box = xyxy2xywh(predn[:, :4])  # xywh
+                box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
+                for p, b in zip(pred.tolist(), box.tolist()):
+                    jdict.append({'image_id': image_id,
+                                  'category_id': coco91class[int(p[5])] if is_coco else int(p[5]),
+                                  'bbox': [round(x, 3) for x in b],
+                                  'score': round(p[4], 5)})
+
+            # Assign all predictions as incorrect
+            correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device)
+            if nl:
+                detected = []  # target indices
+                tcls_tensor = labels[:, 0]
+
+                # target boxes
+                tbox = xywh2xyxy(labels[:, 1:5])
+                scale_coords(img[si].shape[1:], tbox, shapes[si][0], shapes[si][1])  # native-space labels
+                if plots:
+                    confusion_matrix.process_batch(predn, torch.cat((labels[:, 0:1], tbox), 1))
+
+                # Per target class
+                for cls in torch.unique(tcls_tensor):
+                    ti = (cls == tcls_tensor).nonzero(as_tuple=False).view(-1)  # prediction indices
+                    pi = (cls == pred[:, 5]).nonzero(as_tuple=False).view(-1)  # target indices
+
+                    # Search for detections
+                    if pi.shape[0]:
+                        # Prediction to target ious
+                        ious, i = box_iou(predn[pi, :4], tbox[ti]).max(1)  # best ious, indices
+
+                        # Append detections
+                        detected_set = set()
+                        for j in (ious > iouv[0]).nonzero(as_tuple=False):
+                            d = ti[i[j]]  # detected target
+                            if d.item() not in detected_set:
+                                detected_set.add(d.item())
+                                detected.append(d)
+                                correct[pi[j]] = ious[j] > iouv  # iou_thres is 1xn
+                                if len(detected) == nl:  # all targets already located in image
+                                    break
+
+            # Append statistics (correct, conf, pcls, tcls)
+            stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls))
+
+        # Plot images
+        if plots and batch_i < 3:
+            f = save_dir / f'test_batch{batch_i}_labels.jpg'  # labels
+            Thread(target=plot_images, args=(img, targets, paths, f, names), daemon=True).start()
+            f = save_dir / f'test_batch{batch_i}_pred.jpg'  # predictions
+            Thread(target=plot_images, args=(img, output_to_target(out), paths, f, names), daemon=True).start()
+
+    # Compute statistics
+    stats = [np.concatenate(x, 0) for x in zip(*stats)]  # to numpy
+    if len(stats) and stats[0].any():
+        p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names)
+        ap50, ap = ap[:, 0], ap.mean(1)  # AP@0.5, AP@0.5:0.95
+        mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
+        nt = np.bincount(stats[3].astype(np.int64), minlength=nc)  # number of targets per class
+    else:
+        nt = torch.zeros(1)
+
+    # Print results
+    pf = '%20s' + '%12i' * 2 + '%12.3g' * 4  # print format
+    print(pf % ('all', seen, nt.sum(), mp, mr, map50, map))
+
+    # Print results per class
+    if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats):
+        for i, c in enumerate(ap_class):
+            print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
+
+    # Print speeds
+    t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size)  # tuple
+    if not training:
+        print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t)
+
+    # Plots
+    if plots:
+        confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
+        if wandb_logger and wandb_logger.wandb:
+            val_batches = [wandb_logger.wandb.Image(str(f), caption=f.name) for f in sorted(save_dir.glob('test*.jpg'))]
+            wandb_logger.log({"Validation": val_batches})
+    if wandb_images:
+        wandb_logger.log({"Bounding Box Debugger/Images": wandb_images})
+
+    # Save JSON
+    if save_json and len(jdict):
+        w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else ''  # weights
+        anno_json = '../coco/annotations/instances_val2017.json'  # annotations json
+        pred_json = str(save_dir / f"{w}_predictions.json")  # predictions json
+        print('\nEvaluating pycocotools mAP... saving %s...' % pred_json)
+        with open(pred_json, 'w') as f:
+            json.dump(jdict, f)
+
+        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
+            from pycocotools.coco import COCO
+            from pycocotools.cocoeval import COCOeval
+
+            anno = COCO(anno_json)  # init annotations api
+            pred = anno.loadRes(pred_json)  # init predictions api
+            eval = COCOeval(anno, pred, 'bbox')
+            if is_coco:
+                eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files]  # image IDs to evaluate
+            eval.evaluate()
+            eval.accumulate()
+            eval.summarize()
+            map, map50 = eval.stats[:2]  # update results (mAP@0.5:0.95, mAP@0.5)
+        except Exception as e:
+            print(f'pycocotools unable to run: {e}')
+
+    # Return results
+    model.float()  # for training
+    if not training:
+        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}")
+    maps = np.zeros(nc) + map
+    for i, c in enumerate(ap_class):
+        maps[c] = ap[i]
+    return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(prog='test.py')
+    parser.add_argument('--weights', nargs='+', type=str, default='yolov7.pt', help='model.pt path(s)')
+    parser.add_argument('--data', type=str, default='data/coco.yaml', help='*.data path')
+    parser.add_argument('--batch-size', type=int, default=32, help='size of each image batch')
+    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
+    parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.65, help='IOU threshold for NMS')
+    parser.add_argument('--task', default='val', help='train, val, test, speed or study')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--verbose', action='store_true', help='report mAP by class')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file')
+    parser.add_argument('--project', default='runs/test', help='save to project/name')
+    parser.add_argument('--name', default='exp', help='save to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--trace', action='store_true', help='trace model')
+    opt = parser.parse_args()
+    opt.save_json |= opt.data.endswith('coco.yaml')
+    opt.data = check_file(opt.data)  # check file
+    print(opt)
+    #check_requirements()
+
+    if opt.task in ('train', 'val', 'test'):  # run normally
+        test(opt.data,
+             opt.weights,
+             opt.batch_size,
+             opt.img_size,
+             opt.conf_thres,
+             opt.iou_thres,
+             opt.save_json,
+             opt.single_cls,
+             opt.augment,
+             opt.verbose,
+             save_txt=opt.save_txt | opt.save_hybrid,
+             save_hybrid=opt.save_hybrid,
+             save_conf=opt.save_conf,
+             trace=opt.trace,
+             )
+
+    elif opt.task == 'speed':  # speed benchmarks
+        for w in opt.weights:
+            test(opt.data, w, opt.batch_size, opt.img_size, 0.25, 0.45, save_json=False, plots=False)
+
+    elif opt.task == 'study':  # run over a range of settings and save/plot
+        # python test.py --task study --data coco.yaml --iou 0.65 --weights yolov7.pt
+        x = list(range(256, 1536 + 128, 128))  # x axis (image sizes)
+        for w in opt.weights:
+            f = f'study_{Path(opt.data).stem}_{Path(w).stem}.txt'  # filename to save to
+            y = []  # y axis
+            for i in x:  # img-size
+                print(f'\nRunning {f} point {i}...')
+                r, _, t = test(opt.data, w, opt.batch_size, i, opt.conf_thres, opt.iou_thres, opt.save_json,
+                               plots=False)
+                y.append(r + t)  # results and times
+            np.savetxt(f, y, fmt='%10.4g')  # save
+        os.system('zip -r study.zip study_*.txt')
+        plot_study_txt(x=x)  # plot

train.py

@@ -0,0 +1,702 @@
+import argparse
+import logging
+import math
+import os
+import random
+import time
+from copy import deepcopy
+from pathlib import Path
+from threading import Thread
+
+import numpy as np
+import torch.distributed as dist
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+import torch.optim.lr_scheduler as lr_scheduler
+import torch.utils.data
+import yaml
+from torch.cuda import amp
+from torch.nn.parallel import DistributedDataParallel as DDP
+from torch.utils.tensorboard import SummaryWriter
+from tqdm import tqdm
+
+import test  # import test.py to get mAP after each epoch
+from models.experimental import attempt_load
+from models.yolo import Model
+from utils.autoanchor import check_anchors
+from utils.datasets import create_dataloader
+from utils.general import labels_to_class_weights, increment_path, labels_to_image_weights, init_seeds, \
+    fitness, strip_optimizer, get_latest_run, check_dataset, check_file, check_git_status, check_img_size, \
+    check_requirements, print_mutation, set_logging, one_cycle, colorstr
+from utils.google_utils import attempt_download
+from utils.loss import ComputeLoss, ComputeLossOTA
+from utils.plots import plot_images, plot_labels, plot_results, plot_evolution
+from utils.torch_utils import ModelEMA, select_device, intersect_dicts, torch_distributed_zero_first, is_parallel
+from utils.wandb_logging.wandb_utils import WandbLogger, check_wandb_resume
+
+logger = logging.getLogger(__name__)
+
+
+def train(hyp, opt, device, tb_writer=None):
+    logger.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
+    save_dir, epochs, batch_size, total_batch_size, weights, rank, freeze = \
+        Path(opt.save_dir), opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank, opt.freeze
+
+    # Directories
+    wdir = save_dir / 'weights'
+    wdir.mkdir(parents=True, exist_ok=True)  # make dir
+    last = wdir / 'last.pt'
+    best = wdir / 'best.pt'
+    results_file = save_dir / 'results.txt'
+
+    # Save run settings
+    with open(save_dir / 'hyp.yaml', 'w') as f:
+        yaml.dump(hyp, f, sort_keys=False)
+    with open(save_dir / 'opt.yaml', 'w') as f:
+        yaml.dump(vars(opt), f, sort_keys=False)
+
+    # Configure
+    plots = not opt.evolve  # create plots
+    cuda = device.type != 'cpu'
+    init_seeds(2 + rank)
+    with open(opt.data) as f:
+        data_dict = yaml.load(f, Loader=yaml.SafeLoader)  # data dict
+    is_coco = opt.data.endswith('coco.yaml')
+
+    # Logging- Doing this before checking the dataset. Might update data_dict
+    loggers = {'wandb': None}  # loggers dict
+    if rank in [-1, 0]:
+        opt.hyp = hyp  # add hyperparameters
+        run_id = torch.load(weights, map_location=device).get('wandb_id') if weights.endswith('.pt') and os.path.isfile(weights) else None
+        wandb_logger = WandbLogger(opt, Path(opt.save_dir).stem, run_id, data_dict)
+        loggers['wandb'] = wandb_logger.wandb
+        data_dict = wandb_logger.data_dict
+        if wandb_logger.wandb:
+            weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp  # WandbLogger might update weights, epochs if resuming
+
+    nc = 1 if opt.single_cls else int(data_dict['nc'])  # number of classes
+    names = ['item'] if opt.single_cls and len(data_dict['names']) != 1 else data_dict['names']  # class names
+    assert len(names) == nc, '%g names found for nc=%g dataset in %s' % (len(names), nc, opt.data)  # check
+
+    # Model
+    pretrained = weights.endswith('.pt')
+    if pretrained:
+        with torch_distributed_zero_first(rank):
+            attempt_download(weights)  # download if not found locally
+        ckpt = torch.load(weights, map_location=device)  # load checkpoint
+        model = Model(opt.cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
+        exclude = ['anchor'] if (opt.cfg or hyp.get('anchors')) and not opt.resume else []  # exclude keys
+        state_dict = ckpt['model'].float().state_dict()  # to FP32
+        state_dict = intersect_dicts(state_dict, model.state_dict(), exclude=exclude)  # intersect
+        model.load_state_dict(state_dict, strict=False)  # load
+        logger.info('Transferred %g/%g items from %s' % (len(state_dict), len(model.state_dict()), weights))  # report
+    else:
+        model = Model(opt.cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
+    with torch_distributed_zero_first(rank):
+        check_dataset(data_dict)  # check
+    train_path = data_dict['train']
+    test_path = data_dict['val']
+
+    # Freeze
+    freeze = [f'model.{x}.' for x in (freeze if len(freeze) > 1 else range(freeze[0]))]  # parameter names to freeze (full or partial)
+    for k, v in model.named_parameters():
+        v.requires_grad = True  # train all layers
+        if any(x in k for x in freeze):
+            print('freezing %s' % k)
+            v.requires_grad = False
+
+    # Optimizer
+    nbs = 64  # nominal batch size
+    accumulate = max(round(nbs / total_batch_size), 1)  # accumulate loss before optimizing
+    hyp['weight_decay'] *= total_batch_size * accumulate / nbs  # scale weight_decay
+    logger.info(f"Scaled weight_decay = {hyp['weight_decay']}")
+
+    pg0, pg1, pg2 = [], [], []  # optimizer parameter groups
+    for k, v in model.named_modules():
+        if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):
+            pg2.append(v.bias)  # biases
+        if isinstance(v, nn.BatchNorm2d):
+            pg0.append(v.weight)  # no decay
+        elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):
+            pg1.append(v.weight)  # apply decay
+        if hasattr(v, 'im'):
+            if hasattr(v.im, 'implicit'):           
+                pg0.append(v.im.implicit)
+            else:
+                for iv in v.im:
+                    pg0.append(iv.implicit)
+        if hasattr(v, 'imc'):
+            if hasattr(v.imc, 'implicit'):           
+                pg0.append(v.imc.implicit)
+            else:
+                for iv in v.imc:
+                    pg0.append(iv.implicit)
+        if hasattr(v, 'imb'):
+            if hasattr(v.imb, 'implicit'):           
+                pg0.append(v.imb.implicit)
+            else:
+                for iv in v.imb:
+                    pg0.append(iv.implicit)
+        if hasattr(v, 'imo'):
+            if hasattr(v.imo, 'implicit'):           
+                pg0.append(v.imo.implicit)
+            else:
+                for iv in v.imo:
+                    pg0.append(iv.implicit)
+        if hasattr(v, 'ia'):
+            if hasattr(v.ia, 'implicit'):           
+                pg0.append(v.ia.implicit)
+            else:
+                for iv in v.ia:
+                    pg0.append(iv.implicit)
+        if hasattr(v, 'attn'):
+            if hasattr(v.attn, 'logit_scale'):   
+                pg0.append(v.attn.logit_scale)
+            if hasattr(v.attn, 'q_bias'):   
+                pg0.append(v.attn.q_bias)
+            if hasattr(v.attn, 'v_bias'):  
+                pg0.append(v.attn.v_bias)
+            if hasattr(v.attn, 'relative_position_bias_table'):  
+                pg0.append(v.attn.relative_position_bias_table)
+        if hasattr(v, 'rbr_dense'):
+            if hasattr(v.rbr_dense, 'weight_rbr_origin'):  
+                pg0.append(v.rbr_dense.weight_rbr_origin)
+            if hasattr(v.rbr_dense, 'weight_rbr_avg_conv'): 
+                pg0.append(v.rbr_dense.weight_rbr_avg_conv)
+            if hasattr(v.rbr_dense, 'weight_rbr_pfir_conv'):  
+                pg0.append(v.rbr_dense.weight_rbr_pfir_conv)
+            if hasattr(v.rbr_dense, 'weight_rbr_1x1_kxk_idconv1'): 
+                pg0.append(v.rbr_dense.weight_rbr_1x1_kxk_idconv1)
+            if hasattr(v.rbr_dense, 'weight_rbr_1x1_kxk_conv2'):   
+                pg0.append(v.rbr_dense.weight_rbr_1x1_kxk_conv2)
+            if hasattr(v.rbr_dense, 'weight_rbr_gconv_dw'):   
+                pg0.append(v.rbr_dense.weight_rbr_gconv_dw)
+            if hasattr(v.rbr_dense, 'weight_rbr_gconv_pw'):   
+                pg0.append(v.rbr_dense.weight_rbr_gconv_pw)
+            if hasattr(v.rbr_dense, 'vector'):   
+                pg0.append(v.rbr_dense.vector)
+
+    if opt.adam:
+        optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999))  # adjust beta1 to momentum
+    else:
+        optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
+
+    optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']})  # add pg1 with weight_decay
+    optimizer.add_param_group({'params': pg2})  # add pg2 (biases)
+    logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0)))
+    del pg0, pg1, pg2
+
+    # Scheduler https://arxiv.org/pdf/1812.01187.pdf
+    # https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#OneCycleLR
+    if opt.linear_lr:
+        lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf']  # linear
+    else:
+        lf = one_cycle(1, hyp['lrf'], epochs)  # cosine 1->hyp['lrf']
+    scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
+    # plot_lr_scheduler(optimizer, scheduler, epochs)
+
+    # EMA
+    ema = ModelEMA(model) if rank in [-1, 0] else None
+
+    # Resume
+    start_epoch, best_fitness = 0, 0.0
+    if pretrained:
+        # Optimizer
+        if ckpt['optimizer'] is not None:
+            optimizer.load_state_dict(ckpt['optimizer'])
+            best_fitness = ckpt['best_fitness']
+
+        # EMA
+        if ema and ckpt.get('ema'):
+            ema.ema.load_state_dict(ckpt['ema'].float().state_dict())
+            ema.updates = ckpt['updates']
+
+        # Results
+        if ckpt.get('training_results') is not None:
+            results_file.write_text(ckpt['training_results'])  # write results.txt
+
+        # Epochs
+        start_epoch = ckpt['epoch'] + 1
+        if opt.resume:
+            assert start_epoch > 0, '%s training to %g epochs is finished, nothing to resume.' % (weights, epochs)
+        if epochs < start_epoch:
+            logger.info('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' %
+                        (weights, ckpt['epoch'], epochs))
+            epochs += ckpt['epoch']  # finetune additional epochs
+
+        del ckpt, state_dict
+
+    # Image sizes
+    gs = max(int(model.stride.max()), 32)  # grid size (max stride)
+    nl = model.model[-1].nl  # number of detection layers (used for scaling hyp['obj'])
+    imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size]  # verify imgsz are gs-multiples
+
+    # DP mode
+    if cuda and rank == -1 and torch.cuda.device_count() > 1:
+        model = torch.nn.DataParallel(model)
+
+    # SyncBatchNorm
+    if opt.sync_bn and cuda and rank != -1:
+        model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
+        logger.info('Using SyncBatchNorm()')
+
+    # Trainloader
+    dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt,
+                                            hyp=hyp, augment=True, cache=opt.cache_images, rect=opt.rect, rank=rank,
+                                            world_size=opt.world_size, workers=opt.workers,
+                                            image_weights=opt.image_weights, quad=opt.quad, prefix=colorstr('train: '))
+    mlc = np.concatenate(dataset.labels, 0)[:, 0].max()  # max label class
+    nb = len(dataloader)  # number of batches
+    assert mlc < nc, 'Label class %g exceeds nc=%g in %s. Possible class labels are 0-%g' % (mlc, nc, opt.data, nc - 1)
+
+    # Process 0
+    if rank in [-1, 0]:
+        testloader = create_dataloader(test_path, imgsz_test, batch_size * 2, gs, opt,  # testloader
+                                       hyp=hyp, cache=opt.cache_images and not opt.notest, rect=True, rank=-1,
+                                       world_size=opt.world_size, workers=opt.workers,
+                                       pad=0.5, prefix=colorstr('val: '))[0]
+
+        if not opt.resume:
+            labels = np.concatenate(dataset.labels, 0)
+            c = torch.tensor(labels[:, 0])  # classes
+            # cf = torch.bincount(c.long(), minlength=nc) + 1.  # frequency
+            # model._initialize_biases(cf.to(device))
+            if plots:
+                #plot_labels(labels, names, save_dir, loggers)
+                if tb_writer:
+                    tb_writer.add_histogram('classes', c, 0)
+
+            # Anchors
+            if not opt.noautoanchor:
+                check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
+            model.half().float()  # pre-reduce anchor precision
+
+    # DDP mode
+    if cuda and rank != -1:
+        model = DDP(model, device_ids=[opt.local_rank], output_device=opt.local_rank,
+                    # nn.MultiheadAttention incompatibility with DDP https://github.com/pytorch/pytorch/issues/26698
+                    find_unused_parameters=any(isinstance(layer, nn.MultiheadAttention) for layer in model.modules()))
+
+    # Model parameters
+    hyp['box'] *= 3. / nl  # scale to layers
+    hyp['cls'] *= nc / 80. * 3. / nl  # scale to classes and layers
+    hyp['obj'] *= (imgsz / 640) ** 2 * 3. / nl  # scale to image size and layers
+    hyp['label_smoothing'] = opt.label_smoothing
+    model.nc = nc  # attach number of classes to model
+    model.hyp = hyp  # attach hyperparameters to model
+    model.gr = 1.0  # iou loss ratio (obj_loss = 1.0 or iou)
+    model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc  # attach class weights
+    model.names = names
+
+    # Start training
+    t0 = time.time()
+    nw = max(round(hyp['warmup_epochs'] * nb), 1000)  # number of warmup iterations, max(3 epochs, 1k iterations)
+    # nw = min(nw, (epochs - start_epoch) / 2 * nb)  # limit warmup to < 1/2 of training
+    maps = np.zeros(nc)  # mAP per class
+    results = (0, 0, 0, 0, 0, 0, 0)  # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
+    scheduler.last_epoch = start_epoch - 1  # do not move
+    scaler = amp.GradScaler(enabled=cuda)
+    compute_loss_ota = ComputeLossOTA(model)  # init loss class
+    compute_loss = ComputeLoss(model)  # init loss class
+    logger.info(f'Image sizes {imgsz} train, {imgsz_test} test\n'
+                f'Using {dataloader.num_workers} dataloader workers\n'
+                f'Logging results to {save_dir}\n'
+                f'Starting training for {epochs} epochs...')
+    torch.save(model, wdir / 'init.pt')
+    for epoch in range(start_epoch, epochs):  # epoch ------------------------------------------------------------------
+        model.train()
+
+        # Update image weights (optional)
+        if opt.image_weights:
+            # Generate indices
+            if rank in [-1, 0]:
+                cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc  # class weights
+                iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw)  # image weights
+                dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n)  # rand weighted idx
+            # Broadcast if DDP
+            if rank != -1:
+                indices = (torch.tensor(dataset.indices) if rank == 0 else torch.zeros(dataset.n)).int()
+                dist.broadcast(indices, 0)
+                if rank != 0:
+                    dataset.indices = indices.cpu().numpy()
+
+        # Update mosaic border
+        # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
+        # dataset.mosaic_border = [b - imgsz, -b]  # height, width borders
+
+        mloss = torch.zeros(4, device=device)  # mean losses
+        if rank != -1:
+            dataloader.sampler.set_epoch(epoch)
+        pbar = enumerate(dataloader)
+        logger.info(('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'total', 'labels', 'img_size'))
+        if rank in [-1, 0]:
+            pbar = tqdm(pbar, total=nb)  # progress bar
+        optimizer.zero_grad()
+        for i, (imgs, targets, paths, _) in pbar:  # batch -------------------------------------------------------------
+            ni = i + nb * epoch  # number integrated batches (since train start)
+            imgs = imgs.to(device, non_blocking=True).float() / 255.0  # uint8 to float32, 0-255 to 0.0-1.0
+
+            # Warmup
+            if ni <= nw:
+                xi = [0, nw]  # x interp
+                # model.gr = np.interp(ni, xi, [0.0, 1.0])  # iou loss ratio (obj_loss = 1.0 or iou)
+                accumulate = max(1, np.interp(ni, xi, [1, nbs / total_batch_size]).round())
+                for j, x in enumerate(optimizer.param_groups):
+                    # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
+                    x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
+                    if 'momentum' in x:
+                        x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
+
+            # Multi-scale
+            if opt.multi_scale:
+                sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs  # size
+                sf = sz / max(imgs.shape[2:])  # scale factor
+                if sf != 1:
+                    ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]]  # new shape (stretched to gs-multiple)
+                    imgs = F.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
+
+            # Forward
+            with amp.autocast(enabled=cuda):
+                pred = model(imgs)  # forward
+                if hyp['loss_ota'] == 1:
+                    loss, loss_items = compute_loss_ota(pred, targets.to(device), imgs)  # loss scaled by batch_size
+                else:
+                    loss, loss_items = compute_loss(pred, targets.to(device))  # loss scaled by batch_size
+                if rank != -1:
+                    loss *= opt.world_size  # gradient averaged between devices in DDP mode
+                if opt.quad:
+                    loss *= 4.
+
+            # Backward
+            scaler.scale(loss).backward()
+
+            # Optimize
+            if ni % accumulate == 0:
+                scaler.step(optimizer)  # optimizer.step
+                scaler.update()
+                optimizer.zero_grad()
+                if ema:
+                    ema.update(model)
+
+            # Print
+            if rank in [-1, 0]:
+                mloss = (mloss * i + loss_items) / (i + 1)  # update mean losses
+                mem = '%.3gG' % (torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0)  # (GB)
+                s = ('%10s' * 2 + '%10.4g' * 6) % (
+                    '%g/%g' % (epoch, epochs - 1), mem, *mloss, targets.shape[0], imgs.shape[-1])
+                pbar.set_description(s)
+
+                # Plot
+                if plots and ni < 10:
+                    f = save_dir / f'train_batch{ni}.jpg'  # filename
+                    Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start()
+                    # if tb_writer:
+                    #     tb_writer.add_image(f, result, dataformats='HWC', global_step=epoch)
+                    #     tb_writer.add_graph(torch.jit.trace(model, imgs, strict=False), [])  # add model graph
+                elif plots and ni == 10 and wandb_logger.wandb:
+                    wandb_logger.log({"Mosaics": [wandb_logger.wandb.Image(str(x), caption=x.name) for x in
+                                                  save_dir.glob('train*.jpg') if x.exists()]})
+
+            # end batch ------------------------------------------------------------------------------------------------
+        # end epoch ----------------------------------------------------------------------------------------------------
+
+        # Scheduler
+        lr = [x['lr'] for x in optimizer.param_groups]  # for tensorboard
+        scheduler.step()
+
+        # DDP process 0 or single-GPU
+        if rank in [-1, 0]:
+            # mAP
+            ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'gr', 'names', 'stride', 'class_weights'])
+            final_epoch = epoch + 1 == epochs
+            if not opt.notest or final_epoch:  # Calculate mAP
+                wandb_logger.current_epoch = epoch + 1
+                results, maps, times = test.test(data_dict,
+                                                 batch_size=batch_size * 2,
+                                                 imgsz=imgsz_test,
+                                                 model=ema.ema,
+                                                 single_cls=opt.single_cls,
+                                                 dataloader=testloader,
+                                                 save_dir=save_dir,
+                                                 verbose=nc < 50 and final_epoch,
+                                                 plots=plots and final_epoch,
+                                                 wandb_logger=wandb_logger,
+                                                 compute_loss=compute_loss,
+                                                 is_coco=is_coco)
+
+            # Write
+            with open(results_file, 'a') as f:
+                f.write(s + '%10.4g' * 7 % results + '\n')  # append metrics, val_loss
+            if len(opt.name) and opt.bucket:
+                os.system('gsutil cp %s gs://%s/results/results%s.txt' % (results_file, opt.bucket, opt.name))
+
+            # Log
+            tags = ['train/box_loss', 'train/obj_loss', 'train/cls_loss',  # train loss
+                    'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',
+                    'val/box_loss', 'val/obj_loss', 'val/cls_loss',  # val loss
+                    'x/lr0', 'x/lr1', 'x/lr2']  # params
+            for x, tag in zip(list(mloss[:-1]) + list(results) + lr, tags):
+                if tb_writer:
+                    tb_writer.add_scalar(tag, x, epoch)  # tensorboard
+                if wandb_logger.wandb:
+                    wandb_logger.log({tag: x})  # W&B
+
+            # Update best mAP
+            fi = fitness(np.array(results).reshape(1, -1))  # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
+            if fi > best_fitness:
+                best_fitness = fi
+            wandb_logger.end_epoch(best_result=best_fitness == fi)
+
+            # Save model
+            if (not opt.nosave) or (final_epoch and not opt.evolve):  # if save
+                ckpt = {'epoch': epoch,
+                        'best_fitness': best_fitness,
+                        'training_results': results_file.read_text(),
+                        'model': deepcopy(model.module if is_parallel(model) else model).half(),
+                        'ema': deepcopy(ema.ema).half(),
+                        'updates': ema.updates,
+                        'optimizer': optimizer.state_dict(),
+                        'wandb_id': wandb_logger.wandb_run.id if wandb_logger.wandb else None}
+
+                # Save last, best and delete
+                torch.save(ckpt, last)
+                if best_fitness == fi:
+                    torch.save(ckpt, best)
+                if (best_fitness == fi) and (epoch >= 200):
+                    torch.save(ckpt, wdir / 'best_{:03d}.pt'.format(epoch))
+                if epoch == 0:
+                    torch.save(ckpt, wdir / 'epoch_{:03d}.pt'.format(epoch))
+                elif ((epoch+1) % 25) == 0:
+                    torch.save(ckpt, wdir / 'epoch_{:03d}.pt'.format(epoch))
+                elif epoch >= (epochs-5):
+                    torch.save(ckpt, wdir / 'epoch_{:03d}.pt'.format(epoch))
+                if wandb_logger.wandb:
+                    if ((epoch + 1) % opt.save_period == 0 and not final_epoch) and opt.save_period != -1:
+                        wandb_logger.log_model(
+                            last.parent, opt, epoch, fi, best_model=best_fitness == fi)
+                del ckpt
+
+        # end epoch ----------------------------------------------------------------------------------------------------
+    # end training
+    if rank in [-1, 0]:
+        # Plots
+        if plots:
+            plot_results(save_dir=save_dir)  # save as results.png
+            if wandb_logger.wandb:
+                files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]]
+                wandb_logger.log({"Results": [wandb_logger.wandb.Image(str(save_dir / f), caption=f) for f in files
+                                              if (save_dir / f).exists()]})
+        # Test best.pt
+        logger.info('%g epochs completed in %.3f hours.\n' % (epoch - start_epoch + 1, (time.time() - t0) / 3600))
+        if opt.data.endswith('coco.yaml') and nc == 80:  # if COCO
+            for m in (last, best) if best.exists() else (last):  # speed, mAP tests
+                results, _, _ = test.test(opt.data,
+                                          batch_size=batch_size * 2,
+                                          imgsz=imgsz_test,
+                                          conf_thres=0.001,
+                                          iou_thres=0.7,
+                                          model=attempt_load(m, device).half(),
+                                          single_cls=opt.single_cls,
+                                          dataloader=testloader,
+                                          save_dir=save_dir,
+                                          save_json=True,
+                                          plots=False,
+                                          is_coco=is_coco)
+
+        # Strip optimizers
+        final = best if best.exists() else last  # final model
+        for f in last, best:
+            if f.exists():
+                strip_optimizer(f)  # strip optimizers
+        if opt.bucket:
+            os.system(f'gsutil cp {final} gs://{opt.bucket}/weights')  # upload
+        if wandb_logger.wandb and not opt.evolve:  # Log the stripped model
+            wandb_logger.wandb.log_artifact(str(final), type='model',
+                                            name='run_' + wandb_logger.wandb_run.id + '_model',
+                                            aliases=['last', 'best', 'stripped'])
+        wandb_logger.finish_run()
+    else:
+        dist.destroy_process_group()
+    torch.cuda.empty_cache()
+    return results
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default='yolo7.pt', help='initial weights path')
+    parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
+    parser.add_argument('--data', type=str, default='data/coco.yaml', help='data.yaml path')
+    parser.add_argument('--hyp', type=str, default='data/hyp.scratch.p5.yaml', help='hyperparameters path')
+    parser.add_argument('--epochs', type=int, default=300)
+    parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs')
+    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes')
+    parser.add_argument('--rect', action='store_true', help='rectangular training')
+    parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
+    parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
+    parser.add_argument('--notest', action='store_true', help='only test final epoch')
+    parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
+    parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')
+    parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
+    parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
+    parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
+    parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
+    parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
+    parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
+    parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
+    parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
+    parser.add_argument('--project', default='runs/train', help='save to project/name')
+    parser.add_argument('--entity', default=None, help='W&B entity')
+    parser.add_argument('--name', default='exp', help='save to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--quad', action='store_true', help='quad dataloader')
+    parser.add_argument('--linear-lr', action='store_true', help='linear LR')
+    parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
+    parser.add_argument('--upload_dataset', action='store_true', help='Upload dataset as W&B artifact table')
+    parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval for W&B')
+    parser.add_argument('--save_period', type=int, default=-1, help='Log model after every "save_period" epoch')
+    parser.add_argument('--artifact_alias', type=str, default="latest", help='version of dataset artifact to be used')
+    parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone of yolov7=50, first3=0 1 2')
+    opt = parser.parse_args()
+
+    # Set DDP variables
+    opt.world_size = int(os.environ['WORLD_SIZE']) if 'WORLD_SIZE' in os.environ else 1
+    opt.global_rank = int(os.environ['RANK']) if 'RANK' in os.environ else -1
+    set_logging(opt.global_rank)
+    #if opt.global_rank in [-1, 0]:
+    #    check_git_status()
+    #    check_requirements()
+
+    # Resume
+    wandb_run = check_wandb_resume(opt)
+    if opt.resume and not wandb_run:  # resume an interrupted run
+        ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run()  # specified or most recent path
+        assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
+        apriori = opt.global_rank, opt.local_rank
+        with open(Path(ckpt).parent.parent / 'opt.yaml') as f:
+            opt = argparse.Namespace(**yaml.load(f, Loader=yaml.SafeLoader))  # replace
+        opt.cfg, opt.weights, opt.resume, opt.batch_size, opt.global_rank, opt.local_rank = '', ckpt, True, opt.total_batch_size, *apriori  # reinstate
+        logger.info('Resuming training from %s' % ckpt)
+    else:
+        # opt.hyp = opt.hyp or ('hyp.finetune.yaml' if opt.weights else 'hyp.scratch.yaml')
+        opt.data, opt.cfg, opt.hyp = check_file(opt.data), check_file(opt.cfg), check_file(opt.hyp)  # check files
+        assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
+        opt.img_size.extend([opt.img_size[-1]] * (2 - len(opt.img_size)))  # extend to 2 sizes (train, test)
+        opt.name = 'evolve' if opt.evolve else opt.name
+        opt.save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok | opt.evolve)  # increment run
+
+    # DDP mode
+    opt.total_batch_size = opt.batch_size
+    device = select_device(opt.device, batch_size=opt.batch_size)
+    if opt.local_rank != -1:
+        assert torch.cuda.device_count() > opt.local_rank
+        torch.cuda.set_device(opt.local_rank)
+        device = torch.device('cuda', opt.local_rank)
+        dist.init_process_group(backend='nccl', init_method='env://')  # distributed backend
+        assert opt.batch_size % opt.world_size == 0, '--batch-size must be multiple of CUDA device count'
+        opt.batch_size = opt.total_batch_size // opt.world_size
+
+    # Hyperparameters
+    with open(opt.hyp) as f:
+        hyp = yaml.load(f, Loader=yaml.SafeLoader)  # load hyps
+
+    # Train
+    logger.info(opt)
+    if not opt.evolve:
+        tb_writer = None  # init loggers
+        if opt.global_rank in [-1, 0]:
+            prefix = colorstr('tensorboard: ')
+            logger.info(f"{prefix}Start with 'tensorboard --logdir {opt.project}', view at http://localhost:6006/")
+            tb_writer = SummaryWriter(opt.save_dir)  # Tensorboard
+        train(hyp, opt, device, tb_writer)
+
+    # Evolve hyperparameters (optional)
+    else:
+        # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
+        meta = {'lr0': (1, 1e-5, 1e-1),  # initial learning rate (SGD=1E-2, Adam=1E-3)
+                'lrf': (1, 0.01, 1.0),  # final OneCycleLR learning rate (lr0 * lrf)
+                'momentum': (0.3, 0.6, 0.98),  # SGD momentum/Adam beta1
+                'weight_decay': (1, 0.0, 0.001),  # optimizer weight decay
+                'warmup_epochs': (1, 0.0, 5.0),  # warmup epochs (fractions ok)
+                'warmup_momentum': (1, 0.0, 0.95),  # warmup initial momentum
+                'warmup_bias_lr': (1, 0.0, 0.2),  # warmup initial bias lr
+                'box': (1, 0.02, 0.2),  # box loss gain
+                'cls': (1, 0.2, 4.0),  # cls loss gain
+                'cls_pw': (1, 0.5, 2.0),  # cls BCELoss positive_weight
+                'obj': (1, 0.2, 4.0),  # obj loss gain (scale with pixels)
+                'obj_pw': (1, 0.5, 2.0),  # obj BCELoss positive_weight
+                'iou_t': (0, 0.1, 0.7),  # IoU training threshold
+                'anchor_t': (1, 2.0, 8.0),  # anchor-multiple threshold
+                'anchors': (2, 2.0, 10.0),  # anchors per output grid (0 to ignore)
+                'fl_gamma': (0, 0.0, 2.0),  # focal loss gamma (efficientDet default gamma=1.5)
+                'hsv_h': (1, 0.0, 0.1),  # image HSV-Hue augmentation (fraction)
+                'hsv_s': (1, 0.0, 0.9),  # image HSV-Saturation augmentation (fraction)
+                'hsv_v': (1, 0.0, 0.9),  # image HSV-Value augmentation (fraction)
+                'degrees': (1, 0.0, 45.0),  # image rotation (+/- deg)
+                'translate': (1, 0.0, 0.9),  # image translation (+/- fraction)
+                'scale': (1, 0.0, 0.9),  # image scale (+/- gain)
+                'shear': (1, 0.0, 10.0),  # image shear (+/- deg)
+                'perspective': (0, 0.0, 0.001),  # image perspective (+/- fraction), range 0-0.001
+                'flipud': (1, 0.0, 1.0),  # image flip up-down (probability)
+                'fliplr': (0, 0.0, 1.0),  # image flip left-right (probability)
+                'mosaic': (1, 0.0, 1.0),  # image mixup (probability)
+                'mixup': (1, 0.0, 1.0),   # image mixup (probability)
+                'copy_paste': (1, 0.0, 1.0),  # segment copy-paste (probability)
+                'paste_in': (1, 0.0, 1.0)}    # segment copy-paste (probability)
+        
+        with open(opt.hyp, errors='ignore') as f:
+            hyp = yaml.safe_load(f)  # load hyps dict
+            if 'anchors' not in hyp:  # anchors commented in hyp.yaml
+                hyp['anchors'] = 3
+                
+        assert opt.local_rank == -1, 'DDP mode not implemented for --evolve'
+        opt.notest, opt.nosave = True, True  # only test/save final epoch
+        # ei = [isinstance(x, (int, float)) for x in hyp.values()]  # evolvable indices
+        yaml_file = Path(opt.save_dir) / 'hyp_evolved.yaml'  # save best result here
+        if opt.bucket:
+            os.system('gsutil cp gs://%s/evolve.txt .' % opt.bucket)  # download evolve.txt if exists
+
+        for _ in range(300):  # generations to evolve
+            if Path('evolve.txt').exists():  # if evolve.txt exists: select best hyps and mutate
+                # Select parent(s)
+                parent = 'single'  # parent selection method: 'single' or 'weighted'
+                x = np.loadtxt('evolve.txt', ndmin=2)
+                n = min(5, len(x))  # number of previous results to consider
+                x = x[np.argsort(-fitness(x))][:n]  # top n mutations
+                w = fitness(x) - fitness(x).min()  # weights
+                if parent == 'single' or len(x) == 1:
+                    # x = x[random.randint(0, n - 1)]  # random selection
+                    x = x[random.choices(range(n), weights=w)[0]]  # weighted selection
+                elif parent == 'weighted':
+                    x = (x * w.reshape(n, 1)).sum(0) / w.sum()  # weighted combination
+
+                # Mutate
+                mp, s = 0.8, 0.2  # mutation probability, sigma
+                npr = np.random
+                npr.seed(int(time.time()))
+                g = np.array([x[0] for x in meta.values()])  # gains 0-1
+                ng = len(meta)
+                v = np.ones(ng)
+                while all(v == 1):  # mutate until a change occurs (prevent duplicates)
+                    v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
+                for i, k in enumerate(hyp.keys()):  # plt.hist(v.ravel(), 300)
+                    hyp[k] = float(x[i + 7] * v[i])  # mutate
+
+            # Constrain to limits
+            for k, v in meta.items():
+                hyp[k] = max(hyp[k], v[1])  # lower limit
+                hyp[k] = min(hyp[k], v[2])  # upper limit
+                hyp[k] = round(hyp[k], 5)  # significant digits
+
+            # Train mutation
+            results = train(hyp.copy(), opt, device)
+
+            # Write mutation results
+            print_mutation(hyp.copy(), results, yaml_file, opt.bucket)
+
+        # Plot results
+        plot_evolution(yaml_file)
+        print(f'Hyperparameter evolution complete. Best results saved as: {yaml_file}\n'
+              f'Command to train a new model with these hyperparameters: $ python train.py --hyp {yaml_file}')