Question about v4.0 release - 'Transferred 642/650 items from yolov5l.pt'

[Transigent]

❔Question

I am trying to train a custom dataset using a Colab notebook from some months ago. I noticed that recent training produced somewhat poorer results. I noted that Yolov5 v4.0 has been released 9 days ago and I am wondering if the architecture changes are incompatible with the code I have been using.

One thing I did note was the line from the training output shown below:

Transferred 642/650 items from yolov5l.pt

and I wondered whether the difference of 8 items is a result of the removal of one convolution layer from BottleneckCSP (one for each of the eight new C3 layers).

My training line contains the parameter "--weights yolov5l.pt" so I am pulling the .pt file from the repository. Would I be right to assume that the stock .pt file might still contain the additional layers that were part of the v3.1 release. Should this be an issue?

Additional context

                from  n    params  module                                  arguments                     
  0                -1  1      7040  models.common.Focus                     [3, 64, 3]                    
  1                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               
  2                -1  1    156928  models.common.C3                        [128, 128, 3]                 
  3                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              
  4                -1  1   1611264  models.common.C3                        [256, 256, 9]                 
  5                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              
  6                -1  1   6433792  models.common.C3                        [512, 512, 9]                 
  7                -1  1   4720640  models.common.Conv                      [512, 1024, 3, 2]             
  8                -1  1   2624512  models.common.SPP                       [1024, 1024, [5, 9, 13]]      
  9                -1  1   9971712  models.common.C3                        [1024, 1024, 3, False]        
 10                -1  1    525312  models.common.Conv                      [1024, 512, 1, 1]             
 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 12           [-1, 6]  1         0  models.common.Concat                    [1]                           
 13                -1  1   2757632  models.common.C3                        [1024, 512, 3, False]         
 14                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]              
 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 16           [-1, 4]  1         0  models.common.Concat                    [1]                           
 17                -1  1    690688  models.common.C3                        [512, 256, 3, False]          
 18                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]              
 19          [-1, 14]  1         0  models.common.Concat                    [1]                           
 20                -1  1   2495488  models.common.C3                        [512, 512, 3, False]          
 21                -1  1   2360320  models.common.Conv                      [512, 512, 3, 2]              
 22          [-1, 10]  1         0  models.common.Concat                    [1]                           
 23                -1  1   9971712  models.common.C3                        [1024, 1024, 3, False]        
 24      [17, 20, 23]  1    102315  models.yolo.Detect                      [14, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [256, 512, 1024]]
Model Summary: 499 layers, 46701355 parameters, 46701355 gradients, 114.5 GFLOPS

Transferred 642/650 items from yolov5l.pt

[github-actions]

👋 Hello @Transigent, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab Notebook with free GPU:
• Kaggle Notebook with free GPU: https://www.kaggle.com/ultralytics/yolov5
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Docker Image https://hub.docker.com/r/ultralytics/yolov5. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@Transigent you shouldn't mix pretrained weights from earlier releases with the current release. If in doubt simply reclone a fresh copy of the repo and let it autodownload new pretrained weights.

Only layers with identical names and shapes are transferred, so for example if you are training a model on a different dataset from coco pretrained weights the output layers would not normally transfer (being a different shape due to their different class count).

[Transigent]

Thanks for the response @glenn-jocher much appreciated.