王者血条图像识别fasterrcnn-mobilenetv3-large-fpn模型权重文件和相关工程文件

# A Simple Pipeline to Train PyTorch FasterRCNN Model Train PyTorch FasterRCNN models easily on any custom dataset. Choose between official PyTorch models trained on COCO dataset, or choose any backbone from Torchvision classification models, or even write your own custom backbones. ***You can run a Faster RCNN model with Mini Darknet backbone and Mini Detection Head at more than 150 FPS on an RTX 3080***.  ## Get Started ​ [](https://colab.research.google.com/drive/1oFxPpBeE8SzSQq7BTUv28IIqQeiHHLdj?usp=sharing) [](https://www.kaggle.com/code/sovitrath/custom-faster-rcnn-training-kaggle/notebook) * [Find blog posts/tutorials on DebuggerCafe](#Tutorials) ## [Check All Updates Here](https://github.com/sovit-123/fasterrcnn-pytorch-training-pipeline/blob/main/docs/updates.md) **Latest Update** * Filter classes to visualize during inference using the `--classes` command line argument with space separated class indices from the dataset YAML file. For example, to visualize only persons in COCO dataset, use, `python inference.py --classes 1 <rest of the command>` To visualize person and car, use, `python inference.py --classes 1 3 <rest of the command>` * Added Deep SORT Real-Time tracking to `inference_video.py` and `onnx_video_inference.py`. Using `--track` command with the usual inference command. Support for **MobileNet** Re-ID for now. ## Custom Model Naming Conventions ***For this repository:*** * **Small head refers to 512 representation size in the Faster RCNN head and predictor.** * **Tiny head refers to 256 representation size in the Faster RCNN head and predictor.** * **Nano head refers to 128 representation size in the Faster RCNN head and predictor.** ## [Check All Available Model Flags](#A-List-of-All-Model-Flags-to-Use-With-the-Training-Script) ## Go To * [Setup on Ubuntu](#Setup-for-Ubuntu) * [Setup on Windows](#Setup-on-Windows) * [Train on Custom Dataset](#Train-on-Custom-Dataset) * [Inference](#Inference) * [Evaluation](#Evaluation) * [Available Models](#A-List-of-All-Model-Flags-to-Use-With-the-Training-Script) * [Tutorials](#Tutorials) ## Setup on Ubuntu 1. Clone the repository. ```bash git clone https://github.com/sovit-123/fastercnn-pytorch-training-pipeline.git ``` 2. Install requirements. 1. **Method 1**: If you have CUDA and cuDNN set up already, do this in your environment of choice. ```bash pip install -r requirements.txt ``` 2. **Method 2**: If you want to install PyTorch with CUDA Toolkit in your environment of choice. ```bash conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch ``` OR ```bash conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch ``` OR install the version with CUDA support as per your choice from **[here](https://pytorch.org/get-started/locally/)**. Then install the remaining **[requirements](https://github.com/sovit-123/fasterrcnn-pytorch-training-pipeline/blob/main/requirements.txt)**. ## Setup on Windows 1. **First you need to install Microsoft Visual Studio from [here](https://my.visualstudio.com/Downloads?q=Visual%20Studio%202017)**. Sing In/Sing Up by clicking on **[this link](https://my.visualstudio.com/Downloads?q=Visual%20Studio%202017)** and download the **Visual Studio Community 2017** edition.  Install with all the default chosen settings. It should be around 6 GB. Mainly, we need the C++ Build Tools. 2. Then install the proper **`pycocotools`** for Windows. ```bash pip install git+https://github.com/gautamchitnis/cocoapi.git@cocodataset-master#subdirectory=PythonAPI ``` 3. Clone the repository. ```bash git clone https://github.com/sovit-123/fastercnn-pytorch-training-pipeline.git ``` 4. Install PyTorch with CUDA support. ```bash conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch ``` OR ```bash conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch ``` OR install the version with CUDA support as per your choice from **[here](https://pytorch.org/get-started/locally/)**. Then install the remaining **[requirements](https://github.com/sovit-123/pytorch-efficientdet-api/blob/main/requirements.txt)** except for `pycocotools`. ## Train on Custom Dataset Taking an exmaple of the [smoke dataset](https://www.kaggle.com/didiruh/smoke-pascal-voc) from Kaggle. Let's say that the dataset is in the `data/smoke_pascal_voc` directory in the following format. And the `smoke.yaml` is in the `data_configs` directory. Assuming, we store the smoke data in the `data` directory ```bash ├── data │ ├── smoke_pascal_voc │ │ ├── archive │ │ │ ├── train │ │ │ └── valid │ └── README.md ├── data_configs │ └── smoke.yaml ├── models │   ├── create_fasterrcnn_model.py │   ... │   └── __init__.py ├── outputs │   ├── inference │   └── training │   ... ├── readme_images │   ... ├── torch_utils │   ├── coco_eval.py │   ... ├── utils │   ├── annotations.py │   ... ├── datasets.py ├── inference.py ├── inference_video.py ├── __init__.py ├── README.md ├── requirements.txt └── train.py ``` The content of the `smoke.yaml` should be the following: ```yaml # Images and labels direcotry should be relative to train.py TRAIN_DIR_IMAGES: ../../xml_od_data/smoke_pascal_voc/archive/train/images TRAIN_DIR_LABELS: ../../xml_od_data/smoke_pascal_voc/archive/train/annotations # VALID_DIR should be relative to train.py VALID_DIR_IMAGES: ../../xml_od_data/smoke_pascal_voc/archive/valid/images VALID_DIR_LABELS: ../../xml_od_data/smoke_pascal_voc/archive/valid/annotations # Class names. CLASSES: [ '__background__', 'smoke' ] # Number of classes (object classes + 1 for background class in Faster RCNN). NC: 2 # Whether to save the predictions of the validation set while training. SAVE_VALID_PREDICTION_IMAGES: True ``` ***Note that*** *the data and annotations can be in the same directory as well. In that case, the TRAIN_DIR_IMAGES and TRAIN_DIR_LABELS will save the same path. Similarly for VALID images and labels. The `datasets.py` will take care of that*. Next, to start the training, you can use the following command. **Command format:** ```bash python train.py --data <path to the data config YAML file> --epochs 100 --model <model name (defaults to fasterrcnn_resnet50)> --name <folder name inside output/training/> --batch 16 ``` **In this case, the exact command would be:** ```bash python train.py --data data_configs/smoke.yaml --epochs 100 --model fasterrcnn_resnet50_fpn --name smoke_training --batch 16 ``` **The terimal output should be similar to the following:** ``` Number of training samples: 665 Number of validation samples: 72 3,191,405 total parameters. 3,191,405 training parameters. Epoch 0: adjusting learning rate of group 0 to 1.0000e-03. Epoch: [0] [ 0/84] eta: 0:02:17 lr: 0.000013 loss: 1.6518 (1.6518) time: 1.6422 data: 0.2176 max mem: 1525 Epoch: [0] [83/84] eta: 0:00:00 lr: 0.001000 loss: 1.6540 (1.8020) time: 0.0769 data: 0.0077 max mem: 1548 Epoch: [0] Total time: 0:00:08 (0.0984 s / it) creating index... index created! Test: [0/9] eta: 0:00:02 model_time: 0.0928 (0.0928) evaluator_time: 0.0245 (0.0245) time: 0.2972 data: 0.1534 max mem: 1548 Test: [8/9]