Created by: iceriver97

我在设置 Lovasz loss 后报错：

#Device count: 1
batch_size_per_dev: 8
Traceback (most recent call last):
  File "PaddleSeg/pdseg/train.py", line 466, in <module>
    main(args)
  File "PaddleSeg/pdseg/train.py", line 453, in main
    train(cfg)
  File "PaddleSeg/pdseg/train.py", line 237, in train
    train_prog, startup_prog, phase=ModelPhase.TRAIN)
  File "/home/aistudio/PaddleSeg/pdseg/models/model_builder.py", line 196, in build_model
    probas = fluid.layers.softmax(logits, axis=1)
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/nn.py", line 2663, in softmax
    'softmax')
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/data_feeder.py", line 80, in check_variable_and_dtype
    extra_message)
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/data_feeder.py", line 97, in check_type
    (input_name, op_name, expected_type, type(input), extra_message))
TypeError: The type of 'input' in softmax must be (<class 'paddle.fluid.framework.Variable'>, <class 'paddle.fluid.core_avx.VarBase'>), but received <class 'tuple'>. 

下面是配置文件内容：

# 数据集配置
DATASET:
    DATA_DIR: "./work/dataset/land_train/"
    NUM_CLASSES: 7
    TEST_FILE_LIST: "./work/dataset/land_train/test.txt"
    TRAIN_FILE_LIST: "./work/dataset/land_train/train.txt"
    VAL_FILE_LIST: "./work/dataset/land_train/val.txt"
    VIS_FILE_LIST: "./work/dataset/land_train/test.txt"

# 预训练模型配置
MODEL:
    MODEL_NAME: "ocrnet"
    DEFAULT_NORM_TYPE: "bn"
    # 此处设置backbone的配置
    HRNET:
        STAGE2:
            NUM_CHANNELS: [18, 36]
        STAGE3:
            NUM_CHANNELS: [18, 36, 72]
        STAGE4:
            NUM_CHANNELS: [18, 36, 72, 144]
    # 此处设置OCR HEAD
    OCR:
        OCR_MID_CHANNELS: 512
        OCR_KEY_CHANNELS: 256
    MULTI_LOSS_WEIGHT: [1.0, 1.0]

# 其他配置
TRAIN_CROP_SIZE: (512, 512)
EVAL_CROP_SIZE: (512, 512)
AUG:
    AUG_METHOD: "unpadding"
    FIX_RESIZE_SIZE: (512, 512)
    RICH_CROP:
        ENABLE: True
        BLUR: True
        BLUR_RATIO: 0.2
        MAX_ROTATION: 45
        MIN_AREA_RATIO: 0.5
    MIRROR: True
    FLIP: True
BATCH_SIZE: 8
TRAIN:
    PRETRAINED_MODEL_DIR: "./PaddleSeg/pretrained_model/ocrnet_w18_bn_cityscapes/"
    MODEL_SAVE_DIR: "./PaddleSeg/saved_model/ocrnet_optic/"
    SNAPSHOT_EPOCH: 40
TEST:
    TEST_MODEL: "./PaddleSeg/saved_model/ocrnet_optic/final"
SOLVER:
    NUM_EPOCHS: 200
    LR: 0.001
    LR_POLICY: "poly"
    OPTIMIZER: "sgd"
    LOSS: ["lovasz_softmax_loss","softmax_loss"]
    LOSS_WEIGHT:
        LOVASZ_SOFTMAX_LOSS: 0.2
        SOFTMAX_LOSS: 0.8