Training NPS Dataset Problem

[zhuang5252]

Hello, thank you very much for your contribution. I have a question for you.

When I use these models (such as yolov5s, yolov5s, yolov5l, yolov5l xs tph) to train NPS, my accuracy, recall, and map do not increase but decrease, as shown in the following figure.

Can you give me some advice on how to solve this problem?

My data distribution is as follows, labels from left to right are category, center point coordinates x, y, box width, and height in order.

[tusharsangam]

Make sure NPS data is preprocessed using the NPS reproduce branch (this is a condensed two-step of the original multi-step preprocessing routine.) (step 1. videos_to_frames_nps.py, step2. nps_to_yolo.py, optional step3. plot videos)
yolo5l.pt is publicly available yolo5l model checkpoint.
Following code also commented in submit-train.slurm file

 python -m torch.distributed.launch --nproc_per_node=2 --master_port 47769 \
 --use_env train.py --img 1280 --adam --batch 4 --epochs 80 --data ./data/NPS.yaml \
 --hy ./data/hyps/hyp.VisDrone.yaml --cfg ./models/yolov5l.yaml \
 --name image_size_1280_temporal_YOLO5l_5_frames_NPS_end_to_end_skip_0 --project ./runs/train/NPS \
 --weights ./pretrained/yolo5l.pt --exist-ok

[throughheavenandearthimtheonlyone]

Hello @zhuang5252,

Could you let me know what type of GPU you are using to train the NPS dataset?

[wenjun90]

Hi @tusharsangam,
I did the step-by-step procedure as per your instructions:

Make sure NPS data is preprocessed using the NPS reproduce branch (this is a condensed two-step of the original multi-step preprocessing routine.) (step 1. videos_to_frames_nps.py, step2. nps_to_yolo.py, optional step3. plot videos) yolo5l.pt is publicly available yolo5l model checkpoint. Following code also commented in submit-train.slurm file

 python -m torch.distributed.launch --nproc_per_node=2 --master_port 47769 \
 --use_env train.py --img 1280 --adam --batch 4 --epochs 80 --data ./data/NPS.yaml \
 --hy ./data/hyps/hyp.VisDrone.yaml --cfg ./models/yolov5l.yaml \
 --name image_size_1280_temporal_YOLO5l_5_frames_NPS_end_to_end_skip_0 --project ./runs/train/NPS \
 --weights ./pretrained/yolo5l.pt --exist-ok

Training:

python train.py   --weights ./pretrained/yolov5l.pt   --cfg ./models/yolov5l.yaml   --data ./data/NPS.yaml   --hyp ./data/hyps/hyp.VisDrone_1.yaml   --epochs 80   --batch-size 4   --imgsz 1280   --adam   --device 1   --workers 8   --project ./runs/train/NPS   --name image_size_1280_temporal_YOLO5l_1_frames_NPS_end_to_end_skip_0   --exist-ok   --label-smoothing 0.0   --patience 100   --save-period -1

The results are quite similar to @zhuang5252 :

train: weights=./pretrained/yolov5l.pt, cfg=./models/yolov5l.yaml, data=./data/NPS.yaml, hyp=./data/hyps/hyp.VisDrone_1.yaml, epochs=80, batch_size=4, imgsz=1280, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=None, image_weights=False, device=1, multi_scale=False, single_cls=False, adam=True, sync_bn=False, workers=8, project=./runs/train/NPS, name=image_size_1280_temporal_YOLO5l_1_frames_NPS_end_to_end_skip_0, exist_ok=True, quad=False, linear_lr=False, label_smoothing=0.0, patience=100, freeze=0, save_period=-1, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest
fatal: ambiguous argument 'nps_pretrained_reproduce..origin/master': unknown revision or path not in the working tree.
Use '--' to separate paths from revisions, like this:
'git <command> [<revision>...] -- [<file>...]'
YOLOv5 🚀 a6eadc9 torch 2.4.1+cu121 CUDA:1 (Tesla V100S-PCIE-32GB, 32494MiB)

hyperparameters: lr0=0.0032, lrf=0.12, num_frames=1, skip_rate=0, momentum=0.843, weight_decay=0.00036, warmup_epochs=2.0, warmup_momentum=0.5, warmup_bias_lr=0.05, box=0.07, cls=0.18, cls_pw=0.631, obj=0.15, obj_pw=0.911, iou_t=0.2, anchor_t=3, fl_gamma=0.0, hsv_h=0.4, hsv_s=0.3, hsv_v=0.5, degrees=0.2, translate=0.0, scale=0.4, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.2, double_mixup=0.0, copy_paste=0.0
TensorBoard: Start with 'tensorboard --logdir runs/train/NPS', view at http://localhost:6006/
train.py:146: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  ckpt = torch.load(weights, map_location=device)  # load checkpoint

                 from  n    paramsmodule                                  arguments                     
  0                -1  1      7040models.common.Conv                      [3, 64, 6, 2, 2]              
  1                -1  1     73984models.common.Conv                      [64, 128, 3, 2]               
  2                -1  1    156928models.common.C3                        [128, 128, 3]                 
  3                -1  1    295424models.common.Conv                      [128, 256, 3, 2]              
  4                -1  1   1118208models.common.C3                        [256, 256, 6]                 
  5                -1  1   1180672models.common.Conv                      [256, 512, 3, 2]              
  6                -1  1   6433792models.common.C3                        [512, 512, 9]                 
  7                -1  1   4720640models.common.Conv                      [512, 1024, 3, 2]             
  8                -1  1   9971712models.common.C3                        [1024, 1024, 3]               
  9                -1  1   2624512models.common.SPPF                      [1024, 1024, 5]               
 10                -1  1    525312models.common.Conv                      [1024, 512, 1, 1]             
 11                -1  1         0torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 12           [-1, 6]  1         0models.common.Concat                    [1]                           
 13                -1  1   2757632models.common.C3                        [1024, 512, 3, False]         
 14                -1  1    131584models.common.Conv                      [512, 256, 1, 1]              
 15                -1  1         0torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 16           [-1, 4]  1         0models.common.Concat                    [1]                           
 17                -1  1    690688models.common.C3                        [512, 256, 3, False]          
 18                -1  1    590336models.common.Conv                      [256, 256, 3, 2]              
 19          [-1, 14]  1         0models.common.Concat                    [1]                           
 20                -1  1   2495488models.common.C3                        [512, 512, 3, False]          
 21                -1  1   2360320models.common.Conv                      [512, 512, 3, 2]              
 22          [-1, 10]  1         0models.common.Concat                    [1]                           
 23                -1  1   9971712models.common.C3                        [1024, 1024, 3, False]        
 24      [17, 20, 23]  1     32310models.yolo.Detect                      [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [256, 512, 1024]]
Model Summary: 468 layers, 46138294 parameters, 46138294 gradients, 108.2 GFLOPs

Transferred 606/613 items from pretrained/yolov5l.pt, excluding ['anchor']
github: Command 'git rev-list nps_pretrained_reproduce..origin/master --count' returned non-zero exit status 128.
Model: Model(
  (model): Sequential(
    (0): Conv(
      (conv): Conv2d(3, 64, kernel_size=(6, 6), stride=(2, 2), padding=(2, 2), bias=False)
      (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (1): Conv(
      (conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (2): C3(
      (cv1): Conv(
        (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (3): Conv(
      (conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (4): C3(
      (cv1): Conv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (4): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (5): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (5): Conv(
      (conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (6): C3(
      (cv1): Conv(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (3): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (4): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (5): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (6): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (7): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (8): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (7): Conv(
      (conv): Conv2d(512, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(1024, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (8): C3(
      (cv1): Conv(
        (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(1024, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (9): SPPF(
      (cv1): Conv(
        (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(1024, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
    )
    (10): Conv(
      (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (11): Upsample(scale_factor=2.0, mode='nearest')
    (12): Concat()
    (13): C3(
      (cv1): Conv(
        (conv): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (14): Conv(
      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (15): Upsample(scale_factor=2.0, mode='nearest')
    (16): Concat()
    (17): C3(
      (cv1): Conv(
        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (18): Conv(
      (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (19): Concat()
    (20): C3(
      (cv1): Conv(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (21): Conv(
      (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (22): Concat()
    (23): C3(
      (cv1): Conv(
        (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv2): Conv(
        (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (cv3): Conv(
        (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(1024, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (1): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): Bottleneck(
          (cv1): Conv(
            (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (cv2): Conv(
            (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (24): Detect(
      (m): ModuleList(
        (0): Conv2d(256, 18, kernel_size=(1, 1), stride=(1, 1))
        (1): Conv2d(512, 18, kernel_size=(1, 1), stride=(1, 1))
        (2): Conv2d(1024, 18, kernel_size=(1, 1), stride=(1, 1))
      )
    )
  )
)Scaled weight_decay = 0.00036
optimizer: Adam with parameter groups 101 weight, 104 weight (no decay), 104 bias
/home/TransVisDrone/transvisdrone-env/lib/python3.8/site-packages/albumentations/__init__.py:13: UserWarning: A new version of Albumentations is available: 1.4.24 (you have 1.4.18). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1.
  check_for_updates()
albumentations: Blur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.3, blur_limit=(3, 7)), ToGray(p=0.01, num_output_channels=3, method='weighted_average'), CLAHE(p=0.3, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8)), RandomBrightnessContrast(p=0.3, brightness_limit=(-0.2, 0.2), contrast_limit=(-0.2, 0.2), brightness_by_max=True)

Frame wise augmentation set to False
data loader shuffle False
train:  printing from the worker id 0
train:  printing from the worker id 1
train:  printing from the worker id 2
train:  printing from the worker id 3
train:  printing from the worker id 4
train:  printing from the worker id 5
train:  printing from the worker id 6
train:  printing from the worker id 7
Image sizes 1280 train, 1280 val
Using 4 dataloader workers
Logging results to runs/train/NPS/image_size_1280_temporal_YOLO5l_1_frames_NPS_end_to_end_skip_0
Starting training for 80 epochs...

     Epoch   gpu_mem       box       obj       cls    labels  img_size
Number of val loader workers 8
Plotting labels... 

autoanchor: Analyzing anchors... anchors/target = 1.79, Best Possible Recall (BPR) = 1.0000
      0/79     9.84G   0.02947  0.001271         0        20      1280: 100%|██████████| 8053/8053 [37:23<00:00,  3.59it/s] 
               Class     Images     Labels          P          R     [email protected] [email protected]:.95  epoch(-1): 100%|██████████| 470/470 [02:00<00:00,  3.91it/s]
                 all       3753       4657      0.116      0.222      0.053    0.00995         -1

     Epoch   gpu_mem       box       obj       cls    labels  img_size
      1/79     11.2G   0.02513 0.0007977         0         8      1280: 100%|██████████| 8053/8053 [37:28<00:00,  3.58it/s] 
               Class     Images     Labels          P          R     [email protected] [email protected]:.95  epoch(-1): 100%|██████████| 470/470 [02:01<00:00,  3.88it/s]
                 all       3753       4657      0.154      0.354      0.108     0.0225         -1

     Epoch   gpu_mem       box       obj       cls    labels  img_size
      2/79     11.2G   0.02387 0.0007523         0         7      1280: 100%|██████████| 8053/8053 [37:12<00:00,  3.61it/s]  
               Class     Images     Labels          P          R     [email protected] [email protected]:.95  epoch(-1): 100%|██████████| 470/470 [01:59<00:00,  3.95it/s]
                 all       3753       4657      0.179      0.443      0.148     0.0302         -1

     Epoch   gpu_mem       box       obj       cls    labels  img_size
      3/79     11.2G    0.0235  0.000729         0        10      1280: 100%|██████████| 8053/8053 [36:40<00:00,  3.66it/s] 
               Class     Images     Labels          P          R     [email protected] [email protected]:.95  epoch(-1): 100%|██████████| 470/470 [01:59<00:00,  3.95it/s]
                 all       3753       4657      0.152      0.343     0.0931     0.0195         -1

     Epoch   gpu_mem       box       obj       cls    labels  img_size
      4/79     11.2G   0.02343 0.0007278         0        10      1280:   9%|▉         | 706/8053 [03:10<27:50,  4.40it/s]

file: data/NPS.yaml

Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]

path: ./DroneDataset/AllFrames # dataset root dir
train: . # train images (relative to 'path') 6471 images
val: . # val images (relative to 'path') 548 images
test: . # test images (optional) 1610 images
inference: val
annotation_path: ./DroneDataset/
annotation_train: train/labels
annotation_val: val/labels
annotation_test: test/labels
video_root_path: ./DroneDataset/Videos/
video_root_path_train: train
video_root_path_val: val
video_root_path_test: test
video_root_path_inference: val

Classes

nc: 1 # number of classes
names: ['drone']

Can you show me the log of the training configuration with 1 frame, please?
Thank you