笔记本SSD目标检测
done # # To activate this environment, use # # $ conda activate wind_ssd # # To deactivate an active environment, use # # $ conda deactivate (base) C:\Users\BIM>
(wind_ssd) F:\PytorchProject\SSD-master>nvidia-smi Sat Apr 2 08:22:56 2022 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 466.60 Driver Version: 466.60 CUDA Version: 11.3 | |-------------------------------+----------------------+----------------------+ | GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 NVIDIA GeForce ... WDDM | 00000000:01:00.0 On | N/A | | N/A 70C P0 102W / N/A | 13682MiB / 16384MiB | 34% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ +-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | 0 N/A N/A 580 C ...vs\wind_paddle\python.exe N/A | | 0 N/A N/A 1440 C+G Insufficient Permissions N/A | | 0 N/A N/A 7784 C+G C:\Windows\explorer.exe N/A | | 0 N/A N/A 9860 C+G ...artMenuExperienceHost.exe N/A | | 0 N/A N/A 10228 C+G ...5n1h2txyewy\SearchApp.exe N/A | | 0 N/A N/A 10668 C+G ...cw5n1h2txyewy\LockApp.exe N/A | | 0 N/A N/A 11376 C+G ...bbwe\Microsoft.Photos.exe N/A | | 0 N/A N/A 11572 C+G ...2txyewy\TextInputHost.exe N/A | | 0 N/A N/A 13208 C+G ...y\ShellExperienceHost.exe N/A | | 0 N/A N/A 114580 C+G ...me\Application\chrome.exe N/A | +-----------------------------------------------------------------------------+ (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master>
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
(wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master>pip list Package Version ------------------ --------- brotlipy 0.7.0 certifi 2021.10.8 cffi 1.15.0 charset-normalizer 2.0.4 cryptography 36.0.0 idna 3.3 mkl-fft 1.3.1 mkl-random 1.2.2 mkl-service 2.4.0 numpy 1.21.5 Pillow 9.0.1 pip 21.2.4 pycparser 2.21 pyOpenSSL 22.0.0 PySocks 1.7.1 requests 2.27.1 setuptools 58.0.4 six 1.16.0 torch 1.11.0 torchaudio 0.11.0 torchvision 0.12.0 typing_extensions 4.1.1 urllib3 1.26.8 wheel 0.37.1 win-inet-pton 1.1.0 wincertstore 0.2 (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master>
git clone https://github.com/lufficc/SSD.git
(wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master>pip install -r requirements.txt Requirement already satisfied: torch>=1.8 in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from -r requirements.txt (line 1)) (1.11.0) Requirement already satisfied: torchvision in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from -r requirements.txt (line 2)) (0.12.0) Collecting yacs Downloading yacs-0.1.8-py3-none-any.whl (14 kB) Collecting tqdm Using cached tqdm-4.63.1-py2.py3-none-any.whl (76 kB) Collecting opencv-python Using cached opencv_python-4.5.5.64-cp36-abi3-win_amd64.whl (35.4 MB) Collecting vizer Downloading Vizer-0.1.5.tar.gz (2.5 kB) Requirement already satisfied: typing_extensions in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from torch>=1.8->-r requirements.txt (line 1)) (4.1.1) Requirement already satisfied: numpy in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from torchvision->-r requirements.txt (line 2)) (1.21.5) Requirement already satisfied: requests in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from torchvision->-r requirements.txt (line 2)) (2.27.1) Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from torchvision->-r requirements.txt (line 2)) (9.0.1) Collecting PyYAML Using cached PyYAML-6.0-cp37-cp37m-win_amd64.whl (153 kB) Collecting colorama Using cached colorama-0.4.4-py2.py3-none-any.whl (16 kB) Requirement already satisfied: certifi>=2017.4.17 in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from requests->torchvision->-r requirements.txt (line 2)) (2021.10.8) Requirement already satisfied: charset-normalizer~=2.0.0 in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from requests->torchvision->-r requirements.txt (line 2)) (2.0.4) Requirement already satisfied: urllib3<1.27,>=1.21.1 in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from requests->torchvision->-r requirements.txt (line 2)) (1.26.8) Requirement already satisfied: idna<4,>=2.5 in e:\anaconda3\install\envs\wind_ssd\lib\site-packages (from requests->torchvision->-r requirements.txt (line 2)) (3.3) Building wheels for collected packages: vizer Building wheel for vizer (setup.py) ... done Created wheel for vizer: filename=Vizer-0.1.5-py3-none-any.whl size=3507 sha256=a486299c00fe0a123e6ffdb57630b89edf942885c3d3a11f79ee976eb785fea0 Stored in directory: c:\users\bim\appdata\local\pip\cache\wheels\67\a2\c6\7aaa279c50f12c49cc49233acbfd38e23ae3908c373ea4ec85 Successfully built vizer Installing collected packages: PyYAML, opencv-python, colorama, yacs, vizer, tqdm Successfully installed PyYAML-6.0 colorama-0.4.4 opencv-python-4.5.5.64 tqdm-4.63.1 vizer-0.1.5 yacs-0.1.8 (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master>
python demo.py --config-file configs/vgg_ssd300_voc0712.yaml --images_dir demo --ckpt vgg_ssd300_voc0712.pth
警告：
(wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master>python demo.py --config-file configs/vgg_ssd300_voc0712.yaml --images_dir demo --ckpt vgg_ssd300_voc0712.pth F:\PytorchProject\SSD-master\ssd\utils\nms.py:10: UserWarning: No NMS is available. Please upgrade torchvision to 0.3.0+ warnings.warn('No NMS is available. Please upgrade torchvision to 0.3.0+') (wind_ssd) F:\PytorchProject\SSD-master>
处理：
打开 nms.py，注释掉几行，然后 加上：
_nms = torchvision.ops.nms
print(torchvision.__version__) print(torchvision.ops.nms) _nms = torchvision.ops.nms ''' if torchvision.__version__ >= '0.3.0': _nms = torchvision.ops.nms else: warnings.warn('No NMS is available. Please upgrade torchvision to 0.3.0+') sys.exit(-1) '''
再次运行
(wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master>python demo.py --config-file configs/vgg_ssd300_voc0712.yaml --images_dir demo --ckpt vgg_ssd300_voc0712.pth 0.12.0 <function nms at 0x0000027C42E4B048> Namespace(ckpt='vgg_ssd300_voc0712.pth', config_file='configs/vgg_ssd300_voc0712.yaml', dataset_type='voc', images_dir='demo', opts=[], output_dir='demo/result', score_threshold=0.7) Loaded configuration file configs/vgg_ssd300_voc0712.yaml MODEL: NUM_CLASSES: 21 INPUT: IMAGE_SIZE: 300 DATASETS: TRAIN: ("voc_2007_trainval", "voc_2012_trainval") TEST: ("voc_2007_test", ) SOLVER: MAX_ITER: 120000 LR_STEPS: [80000, 100000] GAMMA: 0.1 BATCH_SIZE: 32 LR: 1e-3 OUTPUT_DIR: 'outputs/vgg_ssd300_voc0712' Running with config: DATASETS: TEST: ('voc_2007_test',) TRAIN: ('voc_2007_trainval', 'voc_2012_trainval') DATA_LOADER: NUM_WORKERS: 8 PIN_MEMORY: True INPUT: IMAGE_SIZE: 300 PIXEL_MEAN: [123, 117, 104] MODEL: BACKBONE: NAME: vgg OUT_CHANNELS: (512, 1024, 512, 256, 256, 256) PRETRAINED: True BOX_HEAD: NAME: SSDBoxHead PREDICTOR: SSDBoxPredictor CENTER_VARIANCE: 0.1 DEVICE: cuda META_ARCHITECTURE: SSDDetector NEG_POS_RATIO: 3 NUM_CLASSES: 21 PRIORS: ASPECT_RATIOS: [[2], [2, 3], [2, 3], [2, 3], [2], [2]] BOXES_PER_LOCATION: [4, 6, 6, 6, 4, 4] CLIP: True FEATURE_MAPS: [38, 19, 10, 5, 3, 1] MAX_SIZES: [60, 111, 162, 213, 264, 315] MIN_SIZES: [30, 60, 111, 162, 213, 264] STRIDES: [8, 16, 32, 64, 100, 300] SIZE_VARIANCE: 0.2 THRESHOLD: 0.5 OUTPUT_DIR: outputs/vgg_ssd300_voc0712 SOLVER: BATCH_SIZE: 32 GAMMA: 0.1 LR: 0.001 LR_STEPS: [80000, 100000] MAX_ITER: 120000 MOMENTUM: 0.9 WARMUP_FACTOR: 0.3333333333333333 WARMUP_ITERS: 500 WEIGHT_DECAY: 0.0005 TEST: BATCH_SIZE: 10 CONFIDENCE_THRESHOLD: 0.01 MAX_PER_CLASS: -1 MAX_PER_IMAGE: 100 NMS_THRESHOLD: 0.45 Loaded weights from vgg_ssd300_voc0712.pth E:\Anaconda3\install\envs\wind_ssd\lib\site-packages\torch\nn\functional.py:780: UserWarning: Note that order of the arguments: ceil_mode and return_indices will changeto match the args list in nn.MaxPool2d in a future release. warnings.warn("Note that order of the arguments: ceil_mode and return_indices will change" (0001/0015) 2021-06-29_111824.jpg: objects 01 | load 013ms | inference 3301ms | FPS 0 (0002/0015) 20210107164948.jpg: objects 03 | load 026ms | inference 046ms | FPS 22 (0003/0015) 20210107165009.jpg: objects 02 | load 015ms | inference 047ms | FPS 21 (0004/0015) 20210107165329.jpg: objects 03 | load 005ms | inference 050ms | FPS 20 (0005/0015) 20210107165607.jpg: objects 04 | load 008ms | inference 063ms | FPS 16 (0006/0015) 20210107165645.jpg: objects 04 | load 029ms | inference 042ms | FPS 24 (0007/0015) 20210107165946.jpg: objects 04 | load 006ms | inference 026ms | FPS 39 (0008/0015) 20210107170115.jpg: objects 04 | load 006ms | inference 024ms | FPS 42 (0009/0015) 20210107170234.jpg: objects 02 | load 015ms | inference 024ms | FPS 41 (0010/0015) 20210107170250.jpg: objects 04 | load 024ms | inference 035ms | FPS 29 (0011/0015) 20210107170519.jpg: objects 01 | load 017ms | inference 043ms | FPS 23 (0012/0015) 20210107170601.jpg: objects 00 | load 006ms | inference 026ms | FPS 39 (0013/0015) bus.jpg: objects 03 | load 018ms | inference 012ms | FPS 84 (0014/0015) QQ图片20211201092825.jpg: objects 00 | load 240ms | inference 031ms | FPS 32 (0015/0015) zidane.jpg: objects 02 | load 025ms | inference 012ms | FPS 84 (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master> (wind_ssd) F:\PytorchProject\SSD-master>
查看检测结果：
###########################