YOLOv5 Pruning

[abhinavvsharma]

Hello, Thank you for your contribution!

I am trying to prune a YOLOv5 Nano model by modifying the script of YOLOv7 pruning on this repository. The code is executed without any errors but the MACs before are after pruning is same and model Params is zero in both cases. It seems like the model is not actually pruned. I am sharing the code and output. The only modification needed in YOLOv7 code is the way model is loaded in YOLOv5 is attempt_load and for YOLOv5 there is another wrapper function DetectMultiBackend so, I needed to use model.model instead of model.

Code snippet:

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Run inference on images, videos, directories, streams, etc.

Usage - sources:
    $ python path/to/detect.py --weights yolov5s.pt --source 0              # webcam
                                                             img.jpg        # image
                                                             vid.mp4        # video
                                                             path/          # directory
                                                             path/*.jpg     # glob
                                                             'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                                                             'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream

Usage - formats:
    $ python path/to/detect.py --weights yolov5s.pt                 # PyTorch
                                         yolov5s.torchscript        # TorchScript
                                         yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
                                         yolov5s.xml                # OpenVINO
                                         yolov5s.engine             # TensorRT
                                         yolov5s.mlmodel            # CoreML (macOS-only)
                                         yolov5s_saved_model        # TensorFlow SavedModel
                                         yolov5s.pb                 # TensorFlow GraphDef
                                         yolov5s.tflite             # TensorFlow Lite
                                         yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
"""

import argparse
import os
import sys
from pathlib import Path

import torch
import torch.backends.cudnn as cudnn

FILE = Path(__file__).resolve()
ROOT = FILE.parents[0]  # YOLOv5 root directory
if str(ROOT) not in sys.path:
    sys.path.append(str(ROOT))  # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative

from models.common import DetectMultiBackend
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
                           increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync
import torch_pruning as tp

@torch.no_grad()
def run(
        weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
        source=ROOT / 'data/images',  # file/dir/URL/glob, 0 for webcam
        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
        imgsz=(640, 640),  # inference size (height, width)
        conf_thres=0.25,  # confidence threshold
        iou_thres=0.45,  # NMS IOU threshold
        max_det=1000,  # maximum detections per image
        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
        view_img=False,  # show results
        save_txt=False,  # save results to *.txt
        save_conf=False,  # save confidences in --save-txt labels
        save_crop=False,  # save cropped prediction boxes
        nosave=False,  # do not save images/videos
        classes=None,  # filter by class: --class 0, or --class 0 2 3
        agnostic_nms=False,  # class-agnostic NMS
        augment=False,  # augmented inference
        visualize=False,  # visualize features
        update=False,  # update all models
        project=ROOT / 'runs/detect',  # save results to project/name
        name='exp',  # save results to project/name
        exist_ok=False,  # existing project/name ok, do not increment
        line_thickness=3,  # bounding box thickness (pixels)
        hide_labels=False,  # hide labels
        hide_conf=False,  # hide confidences
        half=False,  # use FP16 half-precision inference
        dnn=False,  # use OpenCV DNN for ONNX inference
):
    source = str(source)
    save_img = not nosave and not source.endswith('.txt')  # save inference images
    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
    if is_url and is_file:
        source = check_file(source)  # download

    # Directories
    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

    # Load model
    device = select_device(device)

    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
    ################################################################################
    # Pruning
    example_inputs = torch.randn(1, 3, 640, 640).to(device)
    imp = tp.importance.MagnitudeImportance(p=2) # L2 norm pruning

    ignored_layers = []
    from models.yolo import Detect
    for m in model.model.modules():
        if isinstance(m, Detect):
            ignored_layers.append(m)
    print("ignored layers:", ignored_layers)

    iterative_steps = 3 # progressive pruning
    pruner = tp.pruner.MagnitudePruner(
        model.model,
        example_inputs,
        importance=imp,
        iterative_steps=iterative_steps,
        ch_sparsity=0.8, # remove 50% channels, ResNet18 = {64, 128, 256, 512} => ResNet18_Half = {32, 64, 128, 256}
        ignored_layers=ignored_layers,
    )
    print("pruner:", pruner)
    base_macs, base_nparams = tp.utils.count_ops_and_params(model.model, example_inputs)
    print("base_macs, base_nparams:", base_macs, base_nparams)

    pruner.step()
    pruned_macs, pruned_nparams = tp.utils.count_ops_and_params(model.model, example_inputs)
    print("pruned_macs, pruned_nparams:", pruned_macs, pruned_nparams)
    print(model.model)
    print("Before Pruning: MACs=%f G, #Params=%f G"%(base_macs/1e9, base_nparams/1e9))
    print("After Pruning: MACs=%f G, #Params=%f G"%(pruned_macs/1e9, pruned_nparams/1e9))
    ####################################################################################
    stride, names, pt = model.stride, model.names, model.pt
    imgsz = check_img_size(imgsz, s=stride)  # check image size

    # Dataloader
    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, auto=pt)
        bs = len(dataset)  # batch_size
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
        bs = 1  # batch_size
    vid_path, vid_writer = [None] * bs, [None] * bs

    # Run inference
    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz))  # warmup
    dt, seen = [0.0, 0.0, 0.0], 0
    for path, im, im0s, vid_cap, s in dataset:
        t1 = time_sync()
        im = torch.from_numpy(im).to(device)
        im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
        im /= 255  # 0 - 255 to 0.0 - 1.0
        if len(im.shape) == 3:
            im = im[None]  # expand for batch dim
        t2 = time_sync()
        dt[0] += t2 - t1

        # Inference
        visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
        pred = model(im, augment=augment, visualize=visualize)
        t3 = time_sync()
        dt[1] += t3 - t2

        # NMS
        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
        dt[2] += time_sync() - t3

        # Second-stage classifier (optional)
        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)

        # Process predictions
        for i, det in enumerate(pred):  # per image
            seen += 1
            if webcam:  # batch_size >= 1
                p, im0, frame = path[i], im0s[i].copy(), dataset.count
                s += f'{i}: '
            else:
                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)

            p = Path(p)  # to Path
            save_path = str(save_dir / p.name)  # im.jpg
            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
            s += '%gx%g ' % im.shape[2:]  # print string
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
            imc = im0.copy() if save_crop else im0  # for save_crop
            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(im.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 save_conf else (cls, *xywh)  # label format
                        with open(f'{txt_path}.txt', 'a') as f:
                            f.write(('%g ' * len(line)).rstrip() % line + '\n')

                    if save_img or save_crop or view_img:  # Add bbox to image
                        c = int(cls)  # integer class
                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
                        annotator.box_label(xyxy, label, color=colors(c, True))
                    if save_crop:
                        save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)

            # Stream results
            im0 = annotator.result()
            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[i] != save_path:  # new video
            #             vid_path[i] = save_path
            #             if isinstance(vid_writer[i], cv2.VideoWriter):
            #                 vid_writer[i].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 = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
            #             vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
            #         vid_writer[i].write(im0)

        # Print time (inference-only)
        LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')

    # Print results
    t = tuple(x / seen * 1E3 for x in dt)  # speeds per image
    temp_var = f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t
    from datetime import datetime
    temp = str(datetime.now()) + ' - ' + weights[0] + ' - ' + temp_var + '\n'
    LOGGER.info(temp)
    file_path = 'inference_log.txt'
    file = open(file_path, 'a')
    file.write(temp)
    file.close()
    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 ''
        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
    if update:
        strip_optimizer(weights)  # update model (to fix SourceChangeWarning)

def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)')
    parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for webcam')
    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
    parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
    parser.add_argument('--max-det', type=int, default=1000, help='maximum 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='show 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: --classes 0, or --classes 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('--visualize', action='store_true', help='visualize features')
    parser.add_argument('--update', action='store_true', help='update all models')
    parser.add_argument('--project', default=ROOT / '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')
    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
    opt = parser.parse_args()
    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
    print_args(vars(opt))
    return opt

def main(opt):
    check_requirements(exclude=('tensorboard', 'thop'))
    run(**vars(opt))

if __name__ == "__main__":
    opt = parse_opt()
    main(opt)

Output:

python3 detect_pruned.py --weights pruned_models/exp657/unpruned/best.pt --conf 0.25 --source /home/small_ml/datasets/coco_datasets_v1_1_cls_0/coco_minitrain_25k/images/val2017/000000000139.jpg
detect_pruned: weights=['pruned_models/exp657/unpruned/best.pt'], source=/home/small_ml/datasets/coco_datasets_v1_1_cls_0/coco_minitrain_25k/images/val2017/000000000139.jpg, data=data/coco128.yaml, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False
Python 3.7.0 required by YOLOv5, but Python 3.6.9 is currently installed
YOLOv5 🚀 v6.1-249-g7c2691f Python-3.6.9 torch-1.10.0 CUDA:0 (NVIDIA Tegra X1, 3964MiB)

Fusing layers... 
YOLOv5n_n_cls_1 summary: 213 layers, 1760518 parameters, 0 gradients, 4.1 GFLOPs
ignored layers: [Detect(
  (m): ModuleList(
    (0): Conv2d(64, 18, kernel_size=(1, 1), stride=(1, 1))
    (1): Conv2d(128, 18, kernel_size=(1, 1), stride=(1, 1))
    (2): Conv2d(256, 18, kernel_size=(1, 1), stride=(1, 1))
  )
)]
pruner: <torch_pruning.pruner.algorithms.magnitude_based_pruner.MagnitudePruner object at 0x7f44241ef0>
base_macs, base_nparams: 2076925600.0 0
pruned_macs, pruned_nparams: 2076925600.0 0
Model(
  (model): Sequential(
    (0): Conv(
      (conv): Conv2d(3, 16, kernel_size=(6, 6), stride=(2, 2), padding=(2, 2))
      (act): SiLU(inplace=True)
    )
    (1): Conv(
      (conv): Conv2d(16, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (2): C3(
      (cv1): Conv(
        (conv): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (3): Conv(
      (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (4): C3(
      (cv1): Conv(
        (conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (5): Conv(
      (conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (6): C3(
      (cv1): Conv(
        (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (7): Conv(
      (conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (8): C3(
      (cv1): Conv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (9): SPPF(
      (cv1): Conv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
    )
    (10): Conv(
      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
      (act): SiLU(inplace=True)
    )
    (11): Upsample(scale_factor=2.0, mode=nearest)
    (12): Concat()
    (13): C3(
      (cv1): Conv(
        (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (14): Conv(
      (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1))
      (act): SiLU(inplace=True)
    )
    (15): Upsample(scale_factor=2.0, mode=nearest)
    (16): Concat()
    (17): C3(
      (cv1): Conv(
        (conv): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (18): Conv(
      (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (19): Concat()
    (20): C3(
      (cv1): Conv(
        (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (21): Conv(
      (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (act): SiLU(inplace=True)
    )
    (22): Concat()
    (23): C3(
      (cv1): Conv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1))
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (24): Detect(
      (m): ModuleList(
        (0): Conv2d(64, 18, kernel_size=(1, 1), stride=(1, 1))
        (1): Conv2d(128, 18, kernel_size=(1, 1), stride=(1, 1))
        (2): Conv2d(256, 18, kernel_size=(1, 1), stride=(1, 1))
      )
    )
  )
)
Before Pruning: MACs=2.076926 G, #Params=0.000000 G
After Pruning: MACs=2.076926 G, #Params=0.000000 G
image 1/1 /home/small_ml/datasets/coco_datasets_v1_1_cls_0/coco_minitrain_25k/images/val2017/000000000139.jpg: 448x640 2 persons, Done. (0.070s)
2023-06-16 10:44:09.202516 - pruned_models/exp657/unpruned/best.pt - Speed: 52.1ms pre-process, 69.9ms inference, 169.5ms NMS per image at shape (1, 3, 640, 640)

Results saved to runs/detect/exp86

When I compared the architecture of pruned model according to this code and unpruned model the only difference I see is that the BatchNorm layers are not present. What modification do I need to prune the YOLOv5 model?

[VainF]

Hi @abhinavvsharma. #nparams=0 means that all parameters have requires_grad=False. Torch-pruning relies on autograd for tracing and thus will not prune any layer if autograd is disabled.

[abhinavvsharma]

Hi @VainF, thank you for your quick response!! I implemented what you said, by changing requires_grad to true after loading the model. I am able to see the value in parameters variable but the results are still the same. I am sharing the code snipper I used to change requires_grad to true. Code snippet:

for p in model.model.parameters():
    p.requires_grad = True

Output of pruning:

Before Pruning: MACs=2.076926 G, #Params=0.001761 G
After Pruning: MACs=2.076926 G, #Params=0.001761 G

[zylovexy]

Have you solved this problem？ @abhinavvsharma

[Dlyrm]

Hi @VainF, thank you for your quick response!! I implemented what you said, by changing requires_grad to true after loading the model. I am able to see the value in parameters variable but the results are still the same. I am sharing the code snipper I used to change requires_grad to true. Code snippet:

for p in model.model.parameters():
    p.requires_grad = True

Output of pruning:

Before Pruning: MACs=2.076926 G, #Params=0.001761 G
After Pruning: MACs=2.076926 G, #Params=0.001761 G

you can try this,fix this line maybe solve your problem: pruned_macs, pruned_nparams = tp.utils.count_ops_and_params(model.model, example_inputs) > pruned_macs, pruned_nparams = tp.utils.count_ops_and_params(pruner.model, example_inputs)