--- # System prepended metadata title: '**2021/07/22&23**' tags: [藍柏婷, 2021/07/22, 2021/07/23] --- # **2021/07/22&23** [[15 Re-training SSD-Mobilenet]](https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-ssd.md) ###### tags: `藍柏婷` ###### tags: `2021/07/22` ### **==== 重新訓練SSD-Mobilenet (Re-training SSD-Mobilenet) ====** >*Next, we'll train our own SSD-Mobilenet object detection model using PyTorch and the Open Images dataset. SSD-Mobilenet is a popular network architecture for realtime object detection on mobile and embedded devices that combines the SSD-300 Single-Shot MultiBox Detector with a Mobilenet backbone. 接下來，我們將使用 PyTorch 和 Open Images 數據集訓練我們自己的 SSD-Mobilenet 對象檢測模型。 SSD-Mobilenet 是一種流行的網絡架構，用於移動和嵌入式設備上的實時對象檢測，它將 SSD-300 單次多盒檢測器與 Mobilenet 骨幹網相結合。 --- by dusty-nv on jetson-inference* ![](https://i.imgur.com/VrR0UvL.png) #### **== 設置 Setup ==** :::info **首先確保您的Jetson和PyTorch上安裝了JetPack 4.4或更高版本，用於Python 3.6** ::: :::info **我們沒有使用 docker container** ::: # you only need to run these if you aren't using the container $ cd jetson-inference/python/training/detection/ssd $ wget https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth -O models/mobilenet-v1-ssd-mp-0_675.pth $ pip3 install -v -r requirements.txt #### **== 途中遇到問題 ==** :::warning ``` $ cd jetson-inference/python/training/detection/ssd $ wget https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth -O models/mobilenet-v1-ssd-mp-0_675.pth ``` >-> 可以運行 ``` $ pip3 install -v -r requirements.txt ``` >-> 一開始回顯示找不到`requirements.txt` > >-> 我將`requirements.txt`貼至`jetson-inference/python/training/detection/ssd`下 > >-> 它顯示`Command “python setup.py egg_info” failed with error code 1 in /tmp/pip-build-Fv1UbD/torch/` >> >>*I actually managed to resolve this issue myself, I traced the problem to a glitch with the Jetpack image after experiencing various other issues. I reformatted the SD card, flashed the Jetpack image and then rebuilt the jetson-inference project again and all the issues were resolved.* >>*實際上，我自己設法解決了這個問題，在遇到各種其他問題後，我將問題追溯到 Jetpack 映像的故障。我重新格式化了 SD 卡，刷新了 Jetpack 映像，然後再次重建了 jetson-inference 項目，所有問題都解決了。* >>--- by https://forums.developer.nvidia.com/t/issues-installing-pytorch-on-jetson-nano-running-jetpack-4-2/119972 ::: :::info 因為`jetson-inference/python/training/detection/ssd`中沒有任何檔案，所以要到 https://github.com/dusty-nv/pytorch-ssd (點`jetson-inference/Re-training SSD-Mobilenet`那頁，`設置 Setup`下的`jetson-inference/python/training/detection/ssd`連結)中，點`Code`、`Download ZIP`，下載完壓縮檔(ZIP)後，右鍵`解壓縮(Open With Archive Manager)`、`Extract`，選`jetson-inference/python/training/detection/ssd`，將所有檔案存到`ssd`中。 ::: #### **== 重新設置 Re-setup ==** $ cd jetson-inference/python/training/detection/ssd $ wget https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth -O models/mobilenet-v1-ssd-mp-0_675.pth $ pip3 install -v -r requirements.txt >``` >$ cd jetson-inference/python/training/detection/ssd >``` >進入`jetson-inference/python/training/detection/ssd`。 > >``` >$ mkdir models >``` >在`ssd`中創建資料夾`models`。 > >``` >$ wget https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth -O models/mobilenet-v1-ssd-mp-0_675.pth` >``` >在 https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth 中，下載`mobilenet-v1-ssd-mp-0_675.pth`，存進`models`資料夾中。 > >``` >$ pip3 install -v -r requirements.txt >``` >註：`$ pip3 install -v -r requirements.txt`要跑個20多分鐘，請耐心等候! --- #### **== 下載數據 Downloading the Data ==** $ python3 open_images_downloader.py --class-names " Apple,Orange,Banana,Strawberry,Grape,Pear,Pineapple,Watermelon " --data=data/fruit >註：`$ python3 open_images_downloader.py --class-names " Apple,Orange,Banana,Strawberry,Grape,Pear,Pineapple,Watermelon " --data=data/fruit`要跑很久，請耐心等候! #### **== 途中遇到問題 ==** :::warning 很不幸的，我又遇到問題了! ```javascript iamai2021@iamai2021:~/Desktop/scifair/image_classification_demo/jetson-inference/python/training/detection/ssd$ python3 open_images_downloader.py --class-names "Apple,Orange,Banana,Strawberry,Grape,Pear,Pineapple,Watermelon" --data=data/fruit 2021-07-22 20:02:48 - Requested 8 classes, found 8 classes 2021-07-22 20:02:48 - Read annotation file data/fruit/train-annotations-bbox.csv 2021-07-22 20:15:52 - Available train images: 5145 2021-07-22 20:15:52 - Available train boxes: 23539 Traceback (most recent call last): File "open_images_downloader.py", line 138, in os.makedirs(image_dir, exist_ok=True) File "/usr/lib/python3.6/os.py", line 220, in makedirs mkdir(name, mode) PermissionError: [Errno 13] Permission denied: 'data/fruit/validation' ``` 大致上就是我沒有`data`的權限。 ::: :::info （我查看了`data`的內容，發現它的擁有者是 "root"，也就是說我最初是有用過`docker container`的。所以接下來我如果要使用到`ssd/data`的話，就要進入`docker container`。） ::: #### **== 進入docker container ==** ###### tags: `2021/07/23` $ docker/run.sh 輸入密碼後，出現`#`代表進入`docker container`了。 ```javascript iamai2021@iamai2021:~/Desktop/scifair/image_classification_demo/jetson-inference$ docker/run.sh reading L4T version from /etc/nv_tegra_release L4T BSP Version: L4T R32.5.1 [sudo] password for iamai2021: size of data/networks: 696577370 bytes CONTAINER: dustynv/jetson-inference:r32.5.0 DATA_VOLUME: --volume /home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data:/jetson-inference/data --volume /home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/python/training/classification/data:/jetson-inference/python/training/classification/data --volume /home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/python/training/classification/models:/jetson-inference/python/training/classification/models --volume /home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/python/training/detection/ssd/data:/jetson-inference/python/training/detection/ssd/data --volume /home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/python/training/detection/ssd/models:/jetson-inference/python/training/detection/ssd/models USER_VOLUME: USER_COMMAND: V4L2_DEVICES: --device /dev/video0 localuser:root being added to access control list ``` #### **== 重新下載數據 Downloading the Data Again ==** # python3 open_images_downloader.py --class-names " Apple,Orange,Banana,Strawberry,Grape,Pear,Pineapple,Watermelon " --data=data/fruit >註：`# python3 open_images_downloader.py --class-names " Apple,Orange,Banana,Strawberry,Grape,Pear,Pineapple,Watermelon " --data=data/fruit`要跑很久，請耐心等候! >>註：下載完後可以直接關閉 stell，再另開一個新的 stell。 >**`--data=`：改變下載目錄** >(預設：jetson->inference/python/training/detection/ssd/data) >**`--stats-only`：顯示該類別圖像數量** > >ex. >```javascript >... >2020-07-09 16:18:06 - Total available images: 6360 >2020-07-09 16:18:06 - Total available boxes: 27188 > >------------------------------------- > 'train' set statistics >------------------------------------- > Image count: 5145 > Bounding box count: 23539 > Bounding box distribution: > Strawberry: 7553/23539 = 0.32 > Orange: 6186/23539 = 0.26 > Apple: 3622/23539 = 0.15 > Grape: 2560/23539 = 0.11 > Banana: 1574/23539 = 0.07 > Pear: 757/23539 = 0.03 > Watermelon: 753/23539 = 0.03 > Pineapple: 534/23539 = 0.02 > >... > >------------------------------------- > Overall statistics >------------------------------------- > Image count: 6360 > Bounding box count: 27188 >``` >**`--max-images=`：將總數據量限制為指定數量的圖像，同時保持每個類別的圖像分佈與原始數據量大致相同。如果一個類別的圖像比另一個類別多，則比例將大致保持不變。** >ex. >```javascript >$ python3 open_images_downloader.py --max-images=2500 --class-names "Apple,Orange,Banana,Strawberry,Grape,Pear,Pineapple,Watermelon" --data=data/fruit >``` >**`--max-annotations-per-class=`：將每個類別限制指定數量上限，如果一個類別的可用數量少於該數量，則將使用它的所有數據 --- 如果原數據在各類別之間分佈不平衡，這將非常有用。** 跑出之結果 -> ```javascript root@iamai2021:/jetson-inference# cd python/training/detection/ssd root@iamai2021:/jetson-inference/python/training/detection/ssd# python3 open_images_downloader.py --max-images=1000 --class-names "Apple,Orange,Banana,Strawberry,Grape,Pear,Pineapple,Watermelon" --data=data/fruit 2021-07-23 07:10:42 - Requested 8 classes, found 8 classes 2021-07-23 07:10:42 - Read annotation file data/fruit/train-annotations-bbox.csv 2021-07-23 07:23:27 - Available train images: 5145 2021-07-23 07:23:27 - Available train boxes: 23539 2021-07-23 07:23:27 - Download https://storage.googleapis.com/openimages/2018_04/validation/validation-annotations-bbox.csv. 2021-07-23 07:23:31 - Read annotation file data/fruit/validation-annotations-bbox.csv 2021-07-23 07:23:33 - Available validation images: 285 2021-07-23 07:23:33 - Available validation boxes: 825 2021-07-23 07:23:33 - Download https://storage.googleapis.com/openimages/2018_04/test/test-annotations-bbox.csv. 2021-07-23 07:23:38 - Read annotation file data/fruit/test-annotations-bbox.csv 2021-07-23 07:23:41 - Available test images: 930 2021-07-23 07:23:41 - Available test boxes: 2824 2021-07-23 07:23:41 - Total available images: 6360 2021-07-23 07:23:41 - Total available boxes: 27188 2021-07-23 07:23:41 - Limiting train dataset to: 808 images (3763 boxes) 2021-07-23 07:23:41 - Limiting validation dataset to: 44 images (163 boxes) 2021-07-23 07:23:41 - Limiting test dataset to: 146 images (340 boxes) ------------------------------------- 'train' set statistics ------------------------------------- Image count: 808 Bounding box count: 3763 Bounding box distribution: Strawberry: 1338/3763 = 0.36 Orange: 987/3763 = 0.26 Apple: 510/3763 = 0.14 Grape: 427/3763 = 0.11 Banana: 248/3763 = 0.07 Watermelon: 111/3763 = 0.03 Pear: 75/3763 = 0.02 Pineapple: 67/3763 = 0.02 ------------------------------------- 'validation' set statistics ------------------------------------- Image count: 44 Bounding box count: 163 Bounding box distribution: Strawberry: 42/163 = 0.26 Grape: 36/163 = 0.22 Orange: 33/163 = 0.20 Apple: 32/163 = 0.20 Watermelon: 7/163 = 0.04 Banana: 6/163 = 0.04 Pineapple: 4/163 = 0.02 Pear: 3/163 = 0.02 ------------------------------------- 'test' set statistics ------------------------------------- Image count: 146 Bounding box count: 340 Bounding box distribution: Orange: 103/340 = 0.30 Grape: 92/340 = 0.27 Strawberry: 56/340 = 0.16 Apple: 26/340 = 0.08 Watermelon: 25/340 = 0.07 Banana: 17/340 = 0.05 Pineapple: 17/340 = 0.05 Pear: 4/340 = 0.01 ------------------------------------- Overall statistics ------------------------------------- Image count: 998 Bounding box count: 4266 2021-07-23 07:23:42 - Saving 'train' data to data/fruit/sub-train-annotations-bbox.csv. 2021-07-23 07:23:42 - Saving 'validation' data to data/fruit/sub-validation-annotations-bbox.csv. 2021-07-23 07:23:42 - Saving 'test' data to data/fruit/sub-test-annotations-bbox.csv. 2021-07-23 07:23:42 - Starting to download 998 images. 2021-07-23 07:23:56 - Downloaded 100 images. 2021-07-23 07:24:07 - Downloaded 200 images. 2021-07-23 07:24:21 - Downloaded 300 images. 2021-07-23 07:24:39 - Downloaded 400 images. 2021-07-23 07:24:54 - Downloaded 500 images. 2021-07-23 07:25:07 - Downloaded 600 images. 2021-07-23 07:25:22 - Downloaded 700 images. 2021-07-23 07:25:37 - Downloaded 800 images. 2021-07-23 07:25:50 - Downloaded 900 images. 2021-07-23 07:26:22 - Task Done. root@iamai2021:/jetson-inference/python/training/detection/ssd# ``` --- #### **== 訓練 SSD-Mobilenet 模型 Training the SSD-Mobilenet Model ==** $ python3 train_ssd.py --data=data/fruit --model-dir=models/fruit --batch-size=4 --epochs=５ | Argument 引數 | Default 預設 | Description 描述 | | -------- | -------- | -------- | | `--data` | data/ | 數據存的位置 | | `--model-dir` | models/ | 輸出訓練模型"檢查點"的目錄 | | `--resume` | None | 從現有"檢查點"恢復訓練的路徑 | | `--batch-size` | 4 | 嘗試根據可用內存增加 | | `--epochs` | 30 | 最多 100 個，會增加訓練時間 | | `--workers` | 2 | 數據加載器線程數（0 = 禁用多線程）| :::info 注意：如果在訓練期間內存不足或進程“終止”，請嘗試`Mounting SWAP`和`Disabling the Desktop GUI`（https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-transfer-learning.md#mounting-swap）。 為了節省內存，您還可以減少`--batch-size`（默認4）和`--workers`（默認2） ::: :::danger 千萬不要使用 `禁用桌面 GUI (Disabling the Desktop GUI)` ::: >**訓練表現 Training Performance** >下面是 SSD-Mobilenet 訓練性能，以幫助估計訓練所需的時間： >| | Images/sec |Time per epoch*| >| ------- | -------- | ------- | >| Nano | 4.77 | 17 min 55 sec | > >註：fruits dataset (5145 training images, batch size=4) >註：18 min x 5 epochs = 90 min（不可考，我家電腦慢的可憐） >註：網站有 100 epochs 下載包 （存進`/ssd/models/fruit`裡面）https://nvidia.box.com/shared/static/gq0zlf0g2r258g3ldabl9o7vch18cxmi.gz 跑出之結果 -> ```javascript iamai2021@iamai2021:~/Desktop/scifair/image_classification_demo/jetson-inference/python/training/detection/ssd$ python3 train_ssd.py --data=data/fruit --model-dir=models/fruit --batch-size=4 --epochs=5 2021-07-23 17:51:18 - Using CUDA... 2021-07-23 17:51:18 - Namespace(balance_data=False, base_net=None, base_net_lr=0.001, batch_size=4, checkpoint_folder='models/fruit', dataset_type='open_images', datasets=['data/fruit'], debug_steps=10, extra_layers_lr=None, freeze_base_net=False, freeze_net=False, gamma=0.1, lr=0.01, mb2_width_mult=1.0, milestones='80,100', momentum=0.9, net='mb1-ssd', num_epochs=5, num_workers=2, pretrained_ssd='models/mobilenet-v1-ssd-mp-0_675.pth', resume=None, scheduler='cosine', t_max=100, use_cuda=True, validation_epochs=1, weight_decay=0.0005) 2021-07-23 17:51:18 - Prepare training datasets. 2021-07-23 17:51:18 - loading annotations from: data/fruit/sub-train-annotations-bbox.csv 2021-07-23 17:51:18 - annotations loaded from: data/fruit/sub-train-annotations-bbox.csv num images: 808 2021-07-23 17:51:21 - Dataset Summary:Number of Images: 808 Minimum Number of Images for a Class: -1 Label Distribution: Apple: 510 Banana: 248 Grape: 427 Orange: 987 Pear: 75 Pineapple: 67 Strawberry: 1338 Watermelon: 111 2021-07-23 17:51:21 - Stored labels into file models/fruit/labels.txt. 2021-07-23 17:51:21 - Train dataset size: 808 2021-07-23 17:51:21 - Prepare Validation datasets. 2021-07-23 17:51:21 - loading annotations from: data/fruit/sub-test-annotations-bbox.csv 2021-07-23 17:51:21 - annotations loaded from: data/fruit/sub-test-annotations-bbox.csv num images: 146 2021-07-23 17:51:21 - Dataset Summary:Number of Images: 146 Minimum Number of Images for a Class: -1 Label Distribution: Apple: 26 Banana: 17 Grape: 92 Orange: 103 Pear: 4 Pineapple: 17 Strawberry: 56 Watermelon: 25 2021-07-23 17:51:21 - Validation dataset size: 146 2021-07-23 17:51:21 - Build network. 2021-07-23 17:51:21 - Init from pretrained ssd models/mobilenet-v1-ssd-mp-0_675.pth 2021-07-23 17:51:22 - Took 0.51 seconds to load the model. 2021-07-23 17:52:42 - Learning rate: 0.01, Base net learning rate: 0.001, Extra Layers learning rate: 0.01. 2021-07-23 17:52:42 - Uses CosineAnnealingLR scheduler. 2021-07-23 17:52:42 - Start training from epoch 0. /home/iamai2021/.local/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:123: UserWarning: Detected call of lr_scheduler.step() before optimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step() before lr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate "https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning) /home/iamai2021/.local/lib/python3.6/site-packages/torch/nn/_reduction.py:44: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead. warnings.warn(warning.format(ret)) 2021-07-23 18:07:52 - Epoch: 0, Step: 10/202, Avg Loss: 13.9509, Avg Regression Loss 4.1929, Avg Classification Loss: 9.7580 2021-07-23 18:29:33 - Epoch: 0, Step: 20/202, Avg Loss: 9.2671, Avg Regression Loss 3.7125, Avg Classification Loss: 5.5546 2021-07-23 19:02:31 - Epoch: 0, Step: 30/202, Avg Loss: 8.6253, Avg Regression Loss 3.2659, Avg Classification Loss: 5.3594 ``` --- #### **== 將模型轉換為 ONNX (Converting the Model to ONNX) ==** $ python3 onnx_export.py --model-dir=models/fruit >保存一個`ssd-mobilenet.onnx`的模型在`jetson-inference/python/training/detection/ssd/models/fruit/`下 --- #### **== 使用 TensorRT 處理圖像 Processing Images with TensorRT ==** :::info 在jetson-inference/python/training/detection/ssd/中操作 ::: $ IMAGES=/home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images $ detectnet --model=models/fruit/ssd-mobilenet.onnx --labels=models/fruit/labels.txt \ --input-blob=input_0 --output-cvg=scores --output-bbox=boxes \ "$IMAGES/fruit_.jpg" $IMAGES/test/fruit_.jpg >``` >$ IMAGES=/data/images # substitute your jetson-inference path here >``` >從以下圖片可以看出`jetson-inference`的位置位於`/home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference` > >![](https://i.imgur.com/gvFwMtO.png) >``` >$ detectnet --model=models/fruit/ssd-mobilenet.onnx --labels=models/fruit/labels.txt \ > --input-blob=input_0 --output-cvg=scores --output-bbox=boxes \ > "$IMAGES/fruit_.jpg" $IMAGES/test/fruit_.jpg >``` >要改為0,1,2,3......等數字 跑出之結果 -> ```javascript iamai2021@iamai2021:~/Desktop/scifair/image_classification_demo/jetson-inference/python/training/detection/ssd$ detectnet --model=models/fruit/ssd-mobilenet.onnx --labels=models/fruit/labels.txt \ --input-blob=input_0 --output-cvg=scores --output-bbox=boxes \ "$IMAGES/fruit_1.jpg" $IMAGES/test/fruit_1.jpg [video] created imageLoader from file:///home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images/fruit_1.jpg ------------------------------------------------ imageLoader video options: ------------------------------------------------ -- URI: file:///home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images/fruit_1.jpg - protocol: file - location: /home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images/fruit_1.jpg - extension: jpg -- deviceType: file -- ioType: input -- codec: unknown -- width: 0 -- height: 0 -- frameRate: 0.000000 -- bitRate: 0 -- numBuffers: 4 -- zeroCopy: true -- flipMethod: none -- loop: 0 -- rtspLatency 2000 ------------------------------------------------ [video] created imageWriter from file:///home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images/test/fruit_1.jpg ------------------------------------------------ imageWriter video options: ------------------------------------------------ -- URI: file:///home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images/test/fruit_1.jpg - protocol: file - location: /home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images/test/fruit_1.jpg - extension: jpg -- deviceType: file -- ioType: output -- codec: unknown -- width: 0 -- height: 0 -- frameRate: 0.000000 -- bitRate: 0 -- numBuffers: 4 -- zeroCopy: true -- flipMethod: none -- loop: 0 -- rtspLatency 2000 ------------------------------------------------ [OpenGL] glDisplay -- X screen 0 resolution: 1920x1080 [OpenGL] glDisplay -- X window resolution: 1920x1080 [OpenGL] glDisplay -- display device initialized (1920x1080) [video] created glDisplay from display://0 ------------------------------------------------ glDisplay video options: ------------------------------------------------ -- URI: display://0 - protocol: display - location: 0 -- deviceType: display -- ioType: output -- codec: raw -- width: 1920 -- height: 1080 -- frameRate: 0.000000 -- bitRate: 0 -- numBuffers: 4 -- zeroCopy: true -- flipMethod: none -- loop: 0 -- rtspLatency 2000 ------------------------------------------------ detectNet -- loading detection network model from: -- prototxt NULL -- model models/fruit/ssd-mobilenet.onnx -- input_blob 'input_0' -- output_cvg 'scores' -- output_bbox 'boxes' -- mean_pixel 0.000000 -- mean_binary NULL -- class_labels models/fruit/labels.txt -- threshold 0.500000 -- batch_size 1 [TRT] TensorRT version 7.1.3 [TRT] loading NVIDIA plugins... [TRT] Registered plugin creator - ::GridAnchor_TRT version 1 [TRT] Registered plugin creator - ::NMS_TRT version 1 [TRT] Registered plugin creator - ::Reorg_TRT version 1 [TRT] Registered plugin creator - ::Region_TRT version 1 [TRT] Registered plugin creator - ::Clip_TRT version 1 [TRT] Registered plugin creator - ::LReLU_TRT version 1 [TRT] Registered plugin creator - ::PriorBox_TRT version 1 [TRT] Registered plugin creator - ::Normalize_TRT version 1 [TRT] Registered plugin creator - ::RPROI_TRT version 1 [TRT] Registered plugin creator - ::BatchedNMS_TRT version 1 [TRT] Could not register plugin creator - ::FlattenConcat_TRT version 1 [TRT] Registered plugin creator - ::CropAndResize version 1 [TRT] Registered plugin creator - ::DetectionLayer_TRT version 1 [TRT] Registered plugin creator - ::Proposal version 1 [TRT] Registered plugin creator - ::ProposalLayer_TRT version 1 [TRT] Registered plugin creator - ::PyramidROIAlign_TRT version 1 [TRT] Registered plugin creator - ::ResizeNearest_TRT version 1 [TRT] Registered plugin creator - ::Split version 1 [TRT] Registered plugin creator - ::SpecialSlice_TRT version 1 [TRT] Registered plugin creator - ::InstanceNormalization_TRT version 1 [TRT] detected model format - ONNX (extension '.onnx') [TRT] desired precision specified for GPU: FASTEST [TRT] requested fasted precision for device GPU without providing valid calibrator, disabling INT8 [TRT] native precisions detected for GPU: FP32, FP16 [TRT] selecting fastest native precision for GPU: FP16 [TRT] attempting to open engine cache file models/fruit/ssd-mobilenet.onnx.1.1.7103.GPU.FP16.engine [TRT] loading network plan from engine cache... models/fruit/ssd-mobilenet.onnx.1.1.7103.GPU.FP16.engine [TRT] device GPU, loaded models/fruit/ssd-mobilenet.onnx [TRT] Deserialize required 16159728 microseconds. [TRT] [TRT] CUDA engine context initialized on device GPU: [TRT] -- layers 107 [TRT] -- maxBatchSize 1 [TRT] -- workspace 0 [TRT] -- deviceMemory 23420416 [TRT] -- bindings 3 [TRT] binding 0 -- index 0 -- name 'input_0' -- type FP32 -- in/out INPUT -- # dims 4 -- dim #0 1 (SPATIAL) -- dim #1 3 (SPATIAL) -- dim #2 300 (SPATIAL) -- dim #3 300 (SPATIAL) [TRT] binding 1 -- index 1 -- name 'scores' -- type FP32 -- in/out OUTPUT -- # dims 3 -- dim #0 1 (SPATIAL) -- dim #1 3000 (SPATIAL) -- dim #2 9 (SPATIAL) [TRT] binding 2 -- index 2 -- name 'boxes' -- type FP32 -- in/out OUTPUT -- # dims 3 -- dim #0 1 (SPATIAL) -- dim #1 3000 (SPATIAL) -- dim #2 4 (SPATIAL) [TRT] [TRT] binding to input 0 input_0 binding index: 0 [TRT] binding to input 0 input_0 dims (b=1 c=3 h=300 w=300) size=1080000 [TRT] binding to output 0 scores binding index: 1 [TRT] binding to output 0 scores dims (b=1 c=3000 h=9 w=1) size=108000 [TRT] binding to output 1 boxes binding index: 2 [TRT] binding to output 1 boxes dims (b=1 c=3000 h=4 w=1) size=48000 [TRT] [TRT] device GPU, models/fruit/ssd-mobilenet.onnx initialized. [TRT] detectNet -- number object classes: 9 [TRT] detectNet -- maximum bounding boxes: 3000 [TRT] detectNet -- loaded 9 class info entries [TRT] detectNet -- number of object classes: 9 [image] loaded '/home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images/fruit_1.jpg' (1024x683, 3 channels) 2 objects detected detected obj 0 class #1 (Apple) confidence=0.966337 bounding box 0 (392.750000, 306.816406) (745.179688, 659.201538) w=352.429688 h=352.385132 detected obj 1 class #1 (Apple) confidence=0.875261 bounding box 1 (244.625000, 42.770874) (558.347961, 393.125183) w=313.722961 h=350.354309 [OpenGL] glDisplay -- set the window size to 1024x683 [OpenGL] creating 1024x683 texture (GL_RGB8 format, 2098176 bytes) [cuda] registered openGL texture for interop access (1024x683, GL_RGB8, 2098176 bytes) [image] saved '/home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images/test/fruit_1.jpg' (1024x683, 3 channels) [TRT] ------------------------------------------------ [TRT] Timing Report models/fruit/ssd-mobilenet.onnx [TRT] ------------------------------------------------ [TRT] Pre-Process CPU 0.14365ms CUDA 3.27328ms [TRT] Network CPU 351.21375ms CUDA 347.62515ms [TRT] Post-Process CPU 130.86665ms CUDA 131.09120ms [TRT] Visualize CPU 316.61752ms CUDA 316.79739ms [TRT] Total CPU 798.84155ms CUDA 798.78699ms [TRT] ------------------------------------------------ [TRT] note -- when processing a single image, run 'sudo jetson_clocks' before to disable DVFS for more accurate profiling/timing measurements [image] imageLoader -- End of Stream (EOS) has been reached, stream has been closed detectnet: shutting down... detectnet: shutdown complete. ``` #### **== 靜態測試圖像結果圖示 ==** （位於`/home/iamai2021/Desktop/scifair/image_classification_demo/jetson-inference/data/images/test`中） ![](https://i.imgur.com/xAR5t0J.jpg) #### **== 運行實時攝像頭程序 Running the Live Camera Program ==** detectnet --model=models/fruit/ssd-mobilenet.onnx --labels=models/fruit/labels.txt \ --input-blob=input_0 --output-cvg=scores --output-bbox=boxes \ /dev/video0 跑出之結果 -> ```javascript iamai2021@iamai2021:~/Desktop/scifair/image_classification_demo/jetson-inference/python/training/detection/ssd$ detectnet --model=models/fruit/ssd-mobilenet.onnx --labels=models/fruit/labels.txt --input-blob=input_0 --output-cvg=scores --output-bbox=boxes /dev/video0 [gstreamer] initialized gstreamer, version 1.14.5.0 [gstreamer] gstCamera -- attempting to create device v4l2:///dev/video0 [gstreamer] gstCamera -- found v4l2 device: UVC Camera (046d:0825) [gstreamer] v4l2-proplist, device.path=(string)/dev/video0, udev-probed=(boolean)false, device.api=(string)v4l2, v4l2.device.driver=(string)uvcvideo, v4l2.device.card=(string)"UVC\ Camera\ \(046d:0825\)", v4l2.device.bus_info=(string)usb-70090000.xusb-2, v4l2.device.version=(uint)264649, v4l2.device.capabilities=(uint)2216689665, v4l2.device.device_caps=(uint)69206017; [gstreamer] gstCamera -- found 38 caps for v4l2 device /dev/video0 [gstreamer] [0] video/x-raw, format=(string)YUY2, width=(int)1280, height=(int)960, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 15/2, 5/1 }; [gstreamer] [1] video/x-raw, format=(string)YUY2, width=(int)1280, height=(int)720, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 15/2, 5/1 }; [gstreamer] [2] video/x-raw, format=(string)YUY2, width=(int)1184, height=(int)656, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 10/1, 5/1 }; [gstreamer] [3] video/x-raw, format=(string)YUY2, width=(int)960, height=(int)720, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 10/1, 5/1 }; [gstreamer] [4] video/x-raw, format=(string)YUY2, width=(int)1024, height=(int)576, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 10/1, 5/1 }; [gstreamer] [5] video/x-raw, format=(string)YUY2, width=(int)960, height=(int)544, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 15/1, 10/1, 5/1 }; [gstreamer] [6] video/x-raw, format=(string)YUY2, width=(int)800, height=(int)600, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [7] video/x-raw, format=(string)YUY2, width=(int)864, height=(int)480, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [8] video/x-raw, format=(string)YUY2, width=(int)800, height=(int)448, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [9] video/x-raw, format=(string)YUY2, width=(int)752, height=(int)416, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [10] video/x-raw, format=(string)YUY2, width=(int)640, height=(int)480, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [11] video/x-raw, format=(string)YUY2, width=(int)640, height=(int)360, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [12] video/x-raw, format=(string)YUY2, width=(int)544, height=(int)288, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [13] video/x-raw, format=(string)YUY2, width=(int)432, height=(int)240, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [14] video/x-raw, format=(string)YUY2, width=(int)352, height=(int)288, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [15] video/x-raw, format=(string)YUY2, width=(int)320, height=(int)240, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [16] video/x-raw, format=(string)YUY2, width=(int)320, height=(int)176, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [17] video/x-raw, format=(string)YUY2, width=(int)176, height=(int)144, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [18] video/x-raw, format=(string)YUY2, width=(int)160, height=(int)120, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [19] image/jpeg, width=(int)1280, height=(int)960, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [20] image/jpeg, width=(int)1280, height=(int)720, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [21] image/jpeg, width=(int)1184, height=(int)656, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [22] image/jpeg, width=(int)960, height=(int)720, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [23] image/jpeg, width=(int)1024, height=(int)576, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [24] image/jpeg, width=(int)960, height=(int)544, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [25] image/jpeg, width=(int)800, height=(int)600, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [26] image/jpeg, width=(int)864, height=(int)480, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [27] image/jpeg, width=(int)800, height=(int)448, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [28] image/jpeg, width=(int)752, height=(int)416, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [29] image/jpeg, width=(int)640, height=(int)480, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [30] image/jpeg, width=(int)640, height=(int)360, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [31] image/jpeg, width=(int)544, height=(int)288, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [32] image/jpeg, width=(int)432, height=(int)240, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [33] image/jpeg, width=(int)352, height=(int)288, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [34] image/jpeg, width=(int)320, height=(int)240, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [35] image/jpeg, width=(int)320, height=(int)176, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [36] image/jpeg, width=(int)176, height=(int)144, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] [37] image/jpeg, width=(int)160, height=(int)120, pixel-aspect-ratio=(fraction)1/1, framerate=(fraction){ 30/1, 25/1, 20/1, 15/1, 10/1, 5/1 }; [gstreamer] gstCamera -- selected device profile: codec=mjpeg format=unknown width=1280 height=720 [gstreamer] gstCamera pipeline string: [gstreamer] v4l2src device=/dev/video0 ! image/jpeg, width=(int)1280, height=(int)720 ! jpegdec ! video/x-raw ! appsink name=mysink [gstreamer] gstCamera successfully created device v4l2:///dev/video0 [video] created gstCamera from v4l2:///dev/video0 ------------------------------------------------ gstCamera video options: ------------------------------------------------ -- URI: v4l2:///dev/video0 - protocol: v4l2 - location: /dev/video0 -- deviceType: v4l2 -- ioType: input -- codec: mjpeg -- width: 1280 -- height: 720 -- frameRate: 30.000000 -- bitRate: 0 -- numBuffers: 4 -- zeroCopy: true -- flipMethod: none -- loop: 0 -- rtspLatency 2000 ------------------------------------------------ [OpenGL] glDisplay -- X screen 0 resolution: 1920x1080 [OpenGL] glDisplay -- X window resolution: 1920x1080 [OpenGL] glDisplay -- display device initialized (1920x1080) [video] created glDisplay from display://0 ------------------------------------------------ glDisplay video options: ------------------------------------------------ -- URI: display://0 - protocol: display - location: 0 -- deviceType: display -- ioType: output -- codec: raw -- width: 1920 -- height: 1080 -- frameRate: 0.000000 -- bitRate: 0 -- numBuffers: 4 -- zeroCopy: true -- flipMethod: none -- loop: 0 -- rtspLatency 2000 ------------------------------------------------ detectNet -- loading detection network model from: -- prototxt NULL -- model models/fruit/ssd-mobilenet.onnx -- input_blob 'input_0' -- output_cvg 'scores' -- output_bbox 'boxes' -- mean_pixel 0.000000 -- mean_binary NULL -- class_labels models/fruit/labels.txt -- threshold 0.500000 -- batch_size 1 [TRT] TensorRT version 7.1.3 [TRT] loading NVIDIA plugins... [TRT] Registered plugin creator - ::GridAnchor_TRT version 1 [TRT] Registered plugin creator - ::NMS_TRT version 1 [TRT] Registered plugin creator - ::Reorg_TRT version 1 [TRT] Registered plugin creator - ::Region_TRT version 1 [TRT] Registered plugin creator - ::Clip_TRT version 1 [TRT] Registered plugin creator - ::LReLU_TRT version 1 [TRT] Registered plugin creator - ::PriorBox_TRT version 1 [TRT] Registered plugin creator - ::Normalize_TRT version 1 [TRT] Registered plugin creator - ::RPROI_TRT version 1 [TRT] Registered plugin creator - ::BatchedNMS_TRT version 1 [TRT] Could not register plugin creator - ::FlattenConcat_TRT version 1 [TRT] Registered plugin creator - ::CropAndResize version 1 [TRT] Registered plugin creator - ::DetectionLayer_TRT version 1 [TRT] Registered plugin creator - ::Proposal version 1 [TRT] Registered plugin creator - ::ProposalLayer_TRT version 1 [TRT] Registered plugin creator - ::PyramidROIAlign_TRT version 1 [TRT] Registered plugin creator - ::ResizeNearest_TRT version 1 [TRT] Registered plugin creator - ::Split version 1 [TRT] Registered plugin creator - ::SpecialSlice_TRT version 1 [TRT] Registered plugin creator - ::InstanceNormalization_TRT version 1 [TRT] detected model format - ONNX (extension '.onnx') [TRT] desired precision specified for GPU: FASTEST [TRT] requested fasted precision for device GPU without providing valid calibrator, disabling INT8 [TRT] native precisions detected for GPU: FP32, FP16 [TRT] selecting fastest native precision for GPU: FP16 [TRT] attempting to open engine cache file models/fruit/ssd-mobilenet.onnx.1.1.7103.GPU.FP16.engine [TRT] loading network plan from engine cache... models/fruit/ssd-mobilenet.onnx.1.1.7103.GPU.FP16.engine [TRT] device GPU, loaded models/fruit/ssd-mobilenet.onnx [TRT] Deserialize required 34499541 microseconds. [TRT] [TRT] CUDA engine context initialized on device GPU: [TRT] -- layers 107 [TRT] -- maxBatchSize 1 [TRT] -- workspace 0 [TRT] -- deviceMemory 23420416 [TRT] -- bindings 3 [TRT] binding 0 -- index 0 -- name 'input_0' -- type FP32 -- in/out INPUT -- # dims 4 -- dim #0 1 (SPATIAL) -- dim #1 3 (SPATIAL) -- dim #2 300 (SPATIAL) -- dim #3 300 (SPATIAL) [TRT] binding 1 -- index 1 -- name 'scores' -- type FP32 -- in/out OUTPUT -- # dims 3 -- dim #0 1 (SPATIAL) -- dim #1 3000 (SPATIAL) -- dim #2 9 (SPATIAL) [TRT] binding 2 -- index 2 -- name 'boxes' -- type FP32 -- in/out OUTPUT -- # dims 3 -- dim #0 1 (SPATIAL) -- dim #1 3000 (SPATIAL) -- dim #2 4 (SPATIAL) [TRT] [TRT] binding to input 0 input_0 binding index: 0 [TRT] binding to input 0 input_0 dims (b=1 c=3 h=300 w=300) size=1080000 [TRT] binding to output 0 scores binding index: 1 [TRT] binding to output 0 scores dims (b=1 c=3000 h=9 w=1) size=108000 [TRT] binding to output 1 boxes binding index: 2 [TRT] binding to output 1 boxes dims (b=1 c=3000 h=4 w=1) size=48000 [TRT] [TRT] device GPU, models/fruit/ssd-mobilenet.onnx initialized. [TRT] detectNet -- number object classes: 9 [TRT] detectNet -- maximum bounding boxes: 3000 [TRT] detectNet -- loaded 9 class info entries [TRT] detectNet -- number of object classes: 9 [gstreamer] opening gstCamera for streaming, transitioning pipeline to GST_STATE_PLAYING [gstreamer] gstreamer changed state from NULL to READY ==> mysink [gstreamer] gstreamer changed state from NULL to READY ==> capsfilter1 [gstreamer] gstreamer changed state from NULL to READY ==> jpegdec0 [gstreamer] gstreamer changed state from NULL to READY ==> capsfilter0 [gstreamer] gstreamer changed state from NULL to READY ==> v4l2src0 [gstreamer] gstreamer changed state from NULL to READY ==> pipeline0 [gstreamer] gstreamer changed state from READY to PAUSED ==> capsfilter1 [gstreamer] gstreamer changed state from READY to PAUSED ==> jpegdec0 [gstreamer] gstreamer changed state from READY to PAUSED ==> capsfilter0 [gstreamer] gstreamer stream status CREATE ==> src [gstreamer] gstreamer changed state from READY to PAUSED ==> v4l2src0 [gstreamer] gstreamer changed state from READY to PAUSED ==> pipeline0 [gstreamer] gstreamer message new-clock ==> pipeline0 [gstreamer] gstreamer stream status ENTER ==> src [gstreamer] gstreamer changed state from PAUSED to PLAYING ==> capsfilter1 [gstreamer] gstreamer changed state from PAUSED to PLAYING ==> jpegdec0 [gstreamer] gstreamer changed state from PAUSED to PLAYING ==> capsfilter0 [gstreamer] gstreamer changed state from PAUSED to PLAYING ==> v4l2src0 [gstreamer] gstreamer message stream-start ==> pipeline0 detectnet: failed to capture video frame detectnet: failed to capture video frame detectnet: failed to capture video frame [gstreamer] gstCamera -- onPreroll [gstreamer] gstCamera -- map buffer size was less than max size (1382400 vs 1382407) [gstreamer] gstCamera recieve caps: video/x-raw, format=(string)I420, width=(int)1280, height=(int)720, interlace-mode=(string)progressive, multiview-mode=(string)mono, multiview-flags=(GstVideoMultiviewFlagsSet)0:ffffffff:/right-view-first/left-flipped/left-flopped/right-flipped/right-flopped/half-aspect/mixed-mono, pixel-aspect-ratio=(fraction)1/1, chroma-site=(string)mpeg2, colorimetry=(string)1:4:0:0, framerate=(fraction)30/1 [gstreamer] gstCamera -- recieved first frame, codec=mjpeg format=i420 width=1280 height=720 size=1382407 RingBuffer -- allocated 4 buffers (1382407 bytes each, 5529628 bytes total) [gstreamer] gstreamer changed state from READY to PAUSED ==> mysink [gstreamer] gstreamer message async-done ==> pipeline0 [gstreamer] gstreamer changed state from PAUSED to PLAYING ==> mysink [gstreamer] gstreamer changed state from PAUSED to PLAYING ==> pipeline0 RingBuffer -- allocated 4 buffers (2764800 bytes each, 11059200 bytes total) [gstreamer] gstreamer message qos ==> v4l2src0 [OpenGL] glDisplay -- set the window size to 1280x720 [OpenGL] creating 1280x720 texture (GL_RGB8 format, 2764800 bytes) [cuda] registered openGL texture for interop access (1280x720, GL_RGB8, 2764800 bytes) [TRT] ------------------------------------------------ [TRT] Timing Report models/fruit/ssd-mobilenet.onnx [TRT] ------------------------------------------------ [TRT] Pre-Process CPU 139.35304ms CUDA 141.23817ms [TRT] Network CPU 388.54294ms CUDA 386.25436ms [TRT] Post-Process CPU 3.97593ms CUDA 4.20906ms [TRT] Total CPU 531.87195ms CUDA 531.70160ms [TRT] ------------------------------------------------ [TRT] note -- when processing a single image, run 'sudo jetson_clocks' before to disable DVFS for more accurate profiling/timing measurements [TRT] ------------------------------------------------ [TRT] Timing Report models/fruit/ssd-mobilenet.onnx [TRT] ------------------------------------------------ [TRT] Pre-Process CPU 0.05547ms CUDA 1.56542ms [TRT] Network CPU 67.45556ms CUDA 54.54016ms [TRT] Post-Process CPU 3.96697ms CUDA 4.17838ms [TRT] Total CPU 71.47800ms CUDA 60.28396ms [TRT] ------------------------------------------------ ... ... [TRT] ------------------------------------------------ [TRT] Timing Report models/fruit/ssd-mobilenet.onnx [TRT] ------------------------------------------------ [TRT] Pre-Process CPU 0.05912ms CUDA 2.62240ms [TRT] Network CPU 40.36085ms CUDA 27.54724ms [TRT] Post-Process CPU 4.40839ms CUDA 4.45115ms [TRT] Total CPU 44.82835ms CUDA 34.62078ms [TRT] ------------------------------------------------ [OpenGL] glDisplay -- the window has been closed [TRT] ------------------------------------------------ [TRT] Timing Report models/fruit/ssd-mobilenet.onnx [TRT] ------------------------------------------------ [TRT] Pre-Process CPU 0.09860ms CUDA 1.17719ms [TRT] Network CPU 39.76318ms CUDA 28.97302ms [TRT] Post-Process CPU 4.35792ms CUDA 4.40286ms [TRT] Total CPU 44.21970ms CUDA 34.55307ms [TRT] ------------------------------------------------ detectnet: shutting down... [gstreamer] gstCamera -- stopping pipeline, transitioning to GST_STATE_NULL [gstreamer] gstCamera -- pipeline stopped detectnet: shutdown complete. iamai2021@iamai2021:~/Desktop/scifair/image_classification_demo/jetson-inference/python/training/detection/ssd$ ``` #### **== 實時攝像頭結果圖示 ==** ![](https://i.imgur.com/EG0PPL1.png) （看來畫的很逼真呀!!!看來Jetson Nano也認同呢!） ![](https://i.imgur.com/aD0H0To.png) （哈哈!這也行!） ![](https://i.imgur.com/ObiadOW.png) （看來好吃的波羅蜜 美洲沒有...）