numpy, pytorch, vscode自測題

1.對於指定數組，取特定值，其它設置爲0， 比如pytorch segmentation結果包含多個類，只取特定類，如何做？

#classp = [0,1,2,2,3,0,5,2]這樣，後面box,score,mask與之對應
ids = torch.where(classp==0)#選擇人類別
classp = classp[ids]
box = box[ids]
score = score[ids]
mask = mask[ids[0], :]

  類似的也可以更簡單

#classp = [0,1,2,2,3,0,5,2]這樣，後面box,score,mask與之對應
ids = (classp==0)#選擇人類別
classp = classp[ids]
box = box[ids]
score = score[ids]
mask = mask[ids, :]

  

2. pytorch在inference階段，如何保證模型沒有梯度信息？

  使用with torch.no_grad(), 修飾

with torch.no_grad():
            cudnn.fastest = True
            torch.set_default_tensor_type('torch.cuda.FloatTensor')
            print('yolact loading model...', end='')
            net = Yolact()
            net.load_weights(config.yolact['model_path'])
            net.eval()
            print(' Done.')
            self.net = net.cuda()
            self.net.detect.use_fast_nms = True
            self.net.detect.use_cross_class_nms = False

3.如何把numpy數組，轉化爲pytorch tensor, 在轉換到cuda上

  torch.from_numpy(np_array).cuda().float()

4.vs code裏面如何調試一個文件？如何加入調試參數，很多args?如何使用conda環境的python?如何指定調試的工作目錄？

  1)通過圖形界面操作，生成launch.json

  2)編輯，加入args:["--thresh=0.5", "--cuda"

  3)加入pythonPath:"/home/silva/anaconda3/envs/py372/bin/python"

 4）加入cwd:"/home/silva/work"

{
    // Use IntelliSense to learn about possible attributes.
    // Hover to view descriptions of existing attributes.
    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
    "version": "0.2.0",
    "configurations": [
        
        {
            "name": "Python: Current File",
            "type": "python",
            "request": "launch",
            "program": "${file}",
            "pythonPath": "/home/silva/anaconda3/envs/py372/bin/python",
            "cwd": "${fileDirname}",
            "args": [
                "--trained_model=weights/yolact_resnet50_54_800000.pth",
                "--score_threshold=0.15",
                "--top_k=15",
                "--video_multiframe=4",
                "--video=0"
            ]
        }
    ]
}

5. numpy array 作爲函數參數傳遞，是作爲引用傳遞，還是拷貝傳遞？

  以前經常搞錯，原來是引用傳遞。在函數內部，修改了array, 那麼調用函數的那個array也會修改。

  def abc(arr): arr = np.zeros((3,3))

  調用a=np.ones((3,3)), 那麼abc(a), 執行後，print(a)是多少？不變

  如果def abc(arr): arr+=3， abc(a)執行後？增加了3

如果def abc(arr): arr[1][1]=34， abc(a)執行後？a對應元素變爲了34

參考 https://stackoverflow.com/questions/11585793/are-numpy-arrays-passed-by-reference

6.pytorch, detectron2 如何從pth的checkpoint中，更改類別數，重新訓練？

detection_checkpoint.py做如下更改

    def _load_file(self, filename):
        if filename.endswith(".pkl"):
            with PathManager.open(filename, "rb") as f:
                data = pickle.load(f, encoding="latin1")
            if "model" in data and "__author__" in data:
                # file is in Detectron2 model zoo format
                self.logger.info("Reading a file from '{}'".format(data["__author__"]))
                return data
            else:
                # assume file is from Caffe2 / Detectron1 model zoo
                if "blobs" in data:
                    # Detection models have "blobs", but ImageNet models don't
                    data = data["blobs"]
                data = {k: v for k, v in data.items() if not k.endswith("_momentum")}
                return {"model": data, "__author__": "Caffe2", "matching_heuristics": True}

        loaded = super()._load_file(filename)  # load native pth checkpoint
        model_dict = loaded['model']
        #model_dict = pretrained_model.state_dict()
        pretrained_dict = {k: v for k, v in model_dict.items() if k in model_dict and "roi_heads" not in k}#去掉roi_heads
        #model_dict.update(pretrained_dict)
        loaded['model'] = pretrained_dict
        loaded['optimizer']['state']={} #去掉optimizer
        print("loaded new model")
        if "model" not in loaded:
            loaded = {"model": loaded}
        return loaded

參考https://github.com/facebookresearch/maskrcnn-benchmark/pull/324/files