一、源码

{
       "mode": "sr",    "use_cl": true,    "gpu_ids": [0, 1],    "scale": ,    "is_train": true,    "use_chop": true,    "rgb_range": 255,    "self_ensemble": false,    "save_image": false,    "datasets": {
         "train": {
           "mode": "LRHR",        "dataroot_HR": "./datasets/Augment/Infra_train_HR_aug/x4",        "dataroot_LR": "./datasets/Augment/Infra_train_LR_aug/x4",        "data_type": "npy",        "n_workers": 4,        "batch_size": 16,        "LR_size": 40,        "use_flip": true,        "use_rot": true,        "noise": "."      },      "val": {
           "mode": "LRHR",        "dataroot_HR": "./datasets/Augment/Infra_val_HR_aug/x4",        "dataroot_LR": "./datasets/Augment/Infra_val_LR_aug/LRBI/x4",        "data_type": "img"      }    }}

二、报错

Traceback (most recent call last):  File "train.py", line 161, in 
   
        main()  File "train.py", line 24, in main    opt = option.parse(opt)  File "/SRFBN_Boom/options/options.py", line 23, in parse    opt = json.loads(json_str, object_pairs_hook=OrderedDict) # 字典  File "/home/anaconda3/envs/IamComing/lib/python3.7/json/__init__.py", line 361, in loads    return cls(**kw).decode(s)  File "/home/anaconda3/envs/uIamComing/lib/python3.7/json/decoder.py", line 337, in decode    obj, end = self.raw_decode(s, idx=_w(s, 0).end())  File "/home/anaconda3/envs/IamComing/lib/python3.7/json/decoder.py", line 355, in raw_decode    raise JSONDecodeError("Expecting value", s, err.value) from Nonejson.decoder.JSONDecodeError: Expecting value: line 11 column 14 (char 79)

三、解决方案

错误解读：json.decoder.JSONDecodeError: Expecting value: line 11 column 14 (char 79)是说在第11行第14列（字符79）处有误，一般情况就是是不是出现了其他符号，或者漏打了逗号，导致json无法识别。

因为json文件只能识别字典类型的数据，也就是花括号{}，同时要成对，字典也可以嵌套。

经过仔细的检查，我发现自己的是在scale参数那里漏掉了数字，然后导致后面的出错，读取不到scale的参数。

同时，有时候报错的位置不一定对，但是我们认真找还是可以找出来的，毕竟自己的程序自己肯定熟悉。

```python{
       "mode": "sr",    "use_cl": true,    "gpu_ids": [0, 1],    "scale": 4, # 出错的位置，这是修改正确的，补上了超分辨率放大的倍数这个参数。    "is_train": true,    "use_chop": true,    "rgb_range": 255,    "self_ensemble": false,    "save_image": false,}

四、后续

解决完这个错误之后，又出现了一个新的问题，

RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 10.76 GiB total capacity; 193.96 MiB already allocated; 6.44 MiB free; 16.04 MiB cached)