# 目錄 # Anaconda env ## Step.1 ### 環境建置介紹 #### 進入Anaconda介面，開啟Powershell Prompt ![1](https://hackmd.io/_uploads/Bkekz7XEJl.png) #### 複製下列程式(參考用) #### - -name 為此環境建置名稱 #### -python 安裝版本 ```javascript= conda create --name yolov7 python=3.9 ``` ![2](https://hackmd.io/_uploads/HyP3b77N1x.png) ## Step.2 ### 查看顯卡版本 ```javascript= nvidia-smi ``` ![3](https://hackmd.io/_uploads/BJcuKPVV1e.png) ### 查詢能夠安裝的 CUDA 版本 CUDA 版本連結 : https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html ![4](https://hackmd.io/_uploads/Hkqd6DVEJx.png) ## Step.3 ### 透過下列pytorch連結去尋找適合的版本 pytorch 版本連結: https://pytorch.org/get-started/previous-versions/ ![5](https://hackmd.io/_uploads/HyI2aPEEkl.png) # LabelImg 標註介紹 ## Step.1 **開啟anaconda 並選擇自己建立的環境開啟 Powershell prompt** **並進入 labelImg-master** ![螢幕擷取畫面 2024-12-29 132132](https://hackmd.io/_uploads/H1GjaLArJl.png) 並輸入以下 ```javascript= python .\labelImg.py ``` ![螢幕擷取畫面 2024-12-29 133635](https://hackmd.io/_uploads/Sy6-eD0Bkl.png) ## Step.2 **首先在 labelImg 左上方點擊** #### ⓵ 開啟目錄 #### ⓶ 改變存放目錄也一樣放入相同資料夾 #### ⓷ 將此改為 YOLO格式 (預設 : txt檔) ![圖片1](https://hackmd.io/_uploads/B1EIBPCB1e.png) ## Step.3 按下 L 快捷鍵 標註照片的特徵 **並於上方檢視中選項按下自動儲存模式** ![螢幕擷取畫面 2024-12-29 142033](https://hackmd.io/_uploads/SyAlsPRHJe.png) **標註完照片後 並結束labelImg 在資料內會看到Class跟txt檔 這樣就完成訓練前所需素材了** ✔️ ![螢幕擷取畫面 2024-12-29 143029](https://hackmd.io/_uploads/HkbGTwRHyx.png) # Yolov7 Install ## Step.1 **pytorch版本** **cuda 版本:12.1** **pytorch 版本: 2.3.1** <font color="#f00">此版本較為穩定</font> ``` conda install pytorch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 pytorch-cuda=12.1 -c pytorch -c nvidia ``` 安裝結束後 進入Powershell Prompt輸入以下指令 ``` >>> python >>> import torch >>> torch.cuda.is_available() >>> torch.cuda.get_device_name(0) ``` ![6](https://hackmd.io/_uploads/rkvxgYE41g.png) **代表安裝成功 !** ## step.2 **執行下列程式** ``` git clone https://github.com/WongKinYiu/yolov7.git ``` ![7](https://hackmd.io/_uploads/rJzIWKNE1x.png) **進入yolov7資料夾尋找 requirements.txt** <font color="#f00">註解掉 11 行及 12 如下方程式碼</font> ```javascript= # Usage: pip install -r requirements.txt # Base ---------------------------------------- matplotlib>=3.2.2 numpy>=1.18.5,<1.24.0 opencv-python>=4.1.1 Pillow>=7.1.2 PyYAML>=5.3.1 requests>=2.23.0 scipy>=1.4.1 #torch>=1.7.0,!=1.12.0 #torchvision>=0.8.1,!=0.13.0 tqdm>=4.41.0 protobuf<4.21.3 # Logging ------------------------------------- tensorboard>=2.4.1 # wandb # Plotting ------------------------------------ pandas>=1.1.4 seaborn>=0.11.0 # Export -------------------------------------- # coremltools>=4.1 # CoreML export # onnx>=1.9.0 # ONNX export # onnx-simplifier>=0.3.6 # ONNX simplifier # scikit-learn==0.19.2 # CoreML quantization # tensorflow>=2.4.1 # TFLite export # tensorflowjs>=3.9.0 # TF.js export # openvino-dev # OpenVINO export # Extras -------------------------------------- ipython # interactive notebook psutil # system utilization thop # FLOPs computation # albumentations>=1.0.3 # pycocotools>=2.0 # COCO mAP # roboflow ``` ## Step.3 #### 執行requirements.txt #### 進入 Powershell Prompt ``` pip install -r requirements.txt ``` ![8](https://hackmd.io/_uploads/ByNIIt4Nye.png) #### 完成後進行yolov7初始化驗證 ``` python detect.py ``` #### 如果有出現下列流程代表訓練完成 ![9](https://hackmd.io/_uploads/ByZHvt4Eyg.png) ## Step.4 #### 自定義模型訓練 #### 在yolov7資料夾中新增mydataset資料夾 #### 於資料夾內新增all的資料夾(可看下圖) #### mydataset資料夾內部架構 ``` mydataset- ┕ all ┕ splitFile.py ``` #### splitFile.py程式碼如下 ``` javascript= import os import sys import shutil from random import sample from collections import OrderedDict if len(sys.argv) < 2: print('input val num') exit() valNum = int(sys.argv[1]) lst = os.listdir('all') lst.remove('classes.txt') for f in lst: if 'txt' not in f: extension = f.split('.')[-1] break names = [i.split('.')[0] for i in lst] names = list(OrderedDict.fromkeys(names)) valNames = sorted(sample(names, valNum)) names = sorted(list(set(names).difference(set(valNames)))) paths = [os.path.join('images', 'train'), os.path.join('images', 'val'), os.path.join('labels', 'train'), os.path.join('labels', 'val')] for p in paths: os.makedirs(p) trainPath = [] for fname in names: orgImgPath = os.path.join('all', f'{fname}.{extension}') newImgPath = os.path.join(paths[0], f'{fname}.{extension}') trainPath.append(os.path.abspath(newImgPath) + '\n') orgTxtPath = os.path.join('all', f'{fname}.txt') newTxtPath = os.path.join(paths[2], f'{fname}.txt') shutil.copy(orgImgPath, newImgPath) shutil.copy(orgTxtPath, newTxtPath) valPath = [] for fname in valNames: orgImgPath = os.path.join('all', f'{fname}.{extension}') newImgPath = os.path.join(paths[1], f'{fname}.{extension}') valPath.append(os.path.abspath(newImgPath) + '\n') orgTxtPath = os.path.join('all', f'{fname}.txt') newTxtPath = os.path.join(paths[3], f'{fname}.txt') shutil.copy(orgImgPath, newImgPath) shutil.copy(orgTxtPath, newTxtPath) with open('train.txt', 'w') as f: f.writelines(trainPath) with open('val.txt', 'w') as f: f.writelines(valPath) shutil.copy(os.path.join('all', 'classes.txt'), 'classes.names') ``` 進入mydataset資料夾位址輸入以下指令 <font color="#f00">後面____為多少為驗證數量</font> ``` python splitFile.py ___ ``` #### 並在建立yolov7_custom 在yolov7/cfg/training ```javascript= # parameters nc: 1 # number of classes depth_multiple: 1.0 # model depth multiple width_multiple: 1.0 # layer channel multiple # anchors anchors: - [12,16, 19,36, 40,28] # P3/8 - [36,75, 76,55, 72,146] # P4/16 - [142,110, 192,243, 459,401] # P5/32 # yolov7 backbone backbone: # [from, number, module, args] [[-1, 1, Conv, [32, 3, 1]], # 0 [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 [-1, 1, Conv, [64, 1, 1]], [-2, 1, Conv, [64, 1, 1]], [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [64, 3, 1]], [[-1, -3, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [256, 1, 1]], # 11 [-1, 1, MP, []], [-1, 1, Conv, [128, 1, 1]], [-3, 1, Conv, [128, 1, 1]], [-1, 1, Conv, [128, 3, 2]], [[-1, -3], 1, Concat, [1]], # 16-P3/8 [-1, 1, Conv, [128, 1, 1]], [-2, 1, Conv, [128, 1, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [[-1, -3, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [512, 1, 1]], # 24 [-1, 1, MP, []], [-1, 1, Conv, [256, 1, 1]], [-3, 1, Conv, [256, 1, 1]], [-1, 1, Conv, [256, 3, 2]], [[-1, -3], 1, Concat, [1]], # 29-P4/16 [-1, 1, Conv, [256, 1, 1]], [-2, 1, Conv, [256, 1, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [[-1, -3, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [1024, 1, 1]], # 37 [-1, 1, MP, []], [-1, 1, Conv, [512, 1, 1]], [-3, 1, Conv, [512, 1, 1]], [-1, 1, Conv, [512, 3, 2]], [[-1, -3], 1, Concat, [1]], # 42-P5/32 [-1, 1, Conv, [256, 1, 1]], [-2, 1, Conv, [256, 1, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [[-1, -3, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [1024, 1, 1]], # 50 ] # yolov7 head head: [[-1, 1, SPPCSPC, [512]], # 51 [-1, 1, Conv, [256, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [37, 1, Conv, [256, 1, 1]], # route backbone P4 [[-1, -2], 1, Concat, [1]], [-1, 1, Conv, [256, 1, 1]], [-2, 1, Conv, [256, 1, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [256, 1, 1]], # 63 [-1, 1, Conv, [128, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [24, 1, Conv, [128, 1, 1]], # route backbone P3 [[-1, -2], 1, Concat, [1]], [-1, 1, Conv, [128, 1, 1]], [-2, 1, Conv, [128, 1, 1]], [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [64, 3, 1]], [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [128, 1, 1]], # 75 [-1, 1, MP, []], [-1, 1, Conv, [128, 1, 1]], [-3, 1, Conv, [128, 1, 1]], [-1, 1, Conv, [128, 3, 2]], [[-1, -3, 63], 1, Concat, [1]], [-1, 1, Conv, [256, 1, 1]], [-2, 1, Conv, [256, 1, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [256, 1, 1]], # 88 [-1, 1, MP, []], [-1, 1, Conv, [256, 1, 1]], [-3, 1, Conv, [256, 1, 1]], [-1, 1, Conv, [256, 3, 2]], [[-1, -3, 51], 1, Concat, [1]], [-1, 1, Conv, [512, 1, 1]], [-2, 1, Conv, [512, 1, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [512, 1, 1]], # 101 [75, 1, RepConv, [256, 3, 1]], [88, 1, RepConv, [512, 3, 1]], [101, 1, RepConv, [1024, 3, 1]], [[102,103,104], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) ] ``` #### 建立mydata 在yolov7/data/mydata (範例) ```javascript= # train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/] train: ./mydataset/train.txt val: ./mydataset/val.txt test: ./mydataset\test.txt # number of classes nc: 1 # class names names: [ 'bud eye'] ``` 之後在yolov7 位址中輸入 ```javascript= ============================================================================================================================================================================================== yolov7 and yolov7x python train.py --workers 8 --device 0 --batch-size 8 --data .\data\mydata.yaml --img 640 640 --cfg .\cfg\training\yolov7_custom.yaml --hyp .\data\hyp.scratch.p5.yaml --weights .\yolov7.pt --epochs 100 ============================================================================================================================================================================================== yolov7-w6 (及其他變體) python train_aux.py --workers 8 --device 0 --batch-size 8 --data .\data\mydata.yaml --img 640 640 --cfg .\cfg\training\yolov7-w6.yaml --hyp .\data\hyp.scratch.p5.yaml --weights .\yolov7-w6.pt --epochs 100 ============================================================================================================================================================================================== ``` <font color="#f00">使用yolov7變體須修正loss函數</font> https://drive.google.com/file/d/1tM-6DtT8qtdfKCnM4c11jXqHyeeWwRGq/view?usp=sharing # Yolov8 Install ## Step 1. #### 首先建立 YOLOv8 環境 #### 並開啟 YOLOv8 環境中的Powershell Prompt ```javascript= conda create --name YOLOv8 python=3.8.20 ``` ![1](https://hackmd.io/_uploads/SkxSXDqB3kg.png) ## Step 2. #### 下載 ultralytics ```javascript= pip install ultralytics ``` ![3](https://hackmd.io/_uploads/HJ0Ct5H21e.png) ## Step 3. #### 1. Pytorch Install #### 這邊建議換成Conda指令去安裝pytorch比較會成功 ##### *Conda使用指令 ```javascript= # CUDA 12.1 conda install pytorch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 pytorch-cuda=12.1 -c pytorch -c nvidia ``` ##### *pip使用指令 ```javascript= # CUDA 12.1 pip install torch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 --index-url https://download.pytorch.org/whl/cu121 ``` ![9](https://hackmd.io/_uploads/rkSfujr3ke.png) #### 2. 安裝過程 ![8](https://hackmd.io/_uploads/HJBRLir3Jl.png) #### 3. 驗證 torch 是否安裝 ![7](https://hackmd.io/_uploads/SksFUiS3yx.png) ``` >>> python >>> import torch >>> torch.cuda.is_available() >>> torch.cuda.get_device_name(0) ``` ## Step 4. #### 測試模型 nc: 為訓練模型類別 ```javascript= yolo predict model=yolo11n.pt source='https://ultralytics.com/images/bus.jpg' ``` ![11](https://hackmd.io/_uploads/rkVpuiB2kx.png) #### 恭喜安裝完成 !!! ## Step 5. #### 如何訓練自己模型 先進入 ultralytics\cfg\models\yolov8資料夾 ![13](https://hackmd.io/_uploads/rk06ojrhJl.png) ```javascript= # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license # Ultralytics YOLOv8 object detection model with P3/8 - P5/32 outputs # Model docs: https://docs.ultralytics.com/models/yolov8 # Task docs: https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' # [depth, width, max_channels] n: [0.33, 0.25, 1024] # YOLOv8n summary: 129 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPS s: [0.33, 0.50, 1024] # YOLOv8s summary: 129 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPS m: [0.67, 0.75, 768] # YOLOv8m summary: 169 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPS l: [1.00, 1.00, 512] # YOLOv8l summary: 209 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPS x: [1.00, 1.25, 512] # YOLOv8x summary: 209 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPS # YOLOv8.0n backbone backbone: # [from, repeats, module, args] - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - [-1, 3, C2f, [128, True]] - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - [-1, 6, C2f, [256, True]] - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - [-1, 6, C2f, [512, True]] - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - [-1, 3, C2f, [1024, True]] - [-1, 1, SPPF, [1024, 5]] # 9 # YOLOv8.0n head head: - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 3, C2f, [512]] # 12 - [-1, 1, nn.Upsample, [None, 2, "nearest"]] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 3, C2f, [256]] # 15 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] - [[-1, 12], 1, Concat, [1]] # cat head P4 - [-1, 3, C2f, [512]] # 18 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] - [[-1, 9], 1, Concat, [1]] # cat head P5 - [-1, 3, C2f, [1024]] # 21 (P5/32-large) - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5) ``` ### 如何訓練模型 ```javascript= ### 訓練模型 yolo task=detect mode=train model="D:\ultralytics\cfg\models\v8\yolov8.yaml" data="D:\ultralytics\mydata\mydata.yaml" epochs=100 batch=16 ### 驗證模型 yolo task=detect mode=val model="D:\ultralytics\runs\detect\train10\weights\best.pt" data= "D:\ultralytics\mydata\mydata.yaml" epochs=100 batch=16 ``` # Yolov9 Install **Coming soon~**