[Bug]ValueError: Target 160 is out of upper bound?

[lvsh2012]

/home/aistudio/work/PaddleSeg 2022-09-29 10:52:04 [INFO]
------------Environment Information------------- platform: Linux-4.15.0-140-generic-x86_64-with-debian-stretch-sid Python: 3.7.4 (default, Aug 13 2019, 20:35:49) [GCC 7.3.0] Paddle compiled with cuda: True NVCC: Build cuda_11.2.r11.2/compiler.29618528_0 cudnn: 8.2 GPUs used: 1 CUDA_VISIBLE_DEVICES: None GPU: ['GPU 0: Tesla V100-SXM2-16GB'] GCC: gcc (Ubuntu 7.5.0-3ubuntu1~16.04) 7.5.0 PaddleSeg: 2.6.0 PaddlePaddle: 2.3.2 OpenCV: 4.1.1

2022-09-29 10:52:04 [INFO]
---------------Config Information--------------- batch_size: 4 iters: 1000 loss: coef:

• 1
• 1
• 1 types:
• ignore_index: 255 type: CrossEntropyLoss lr_scheduler: end_lr: 0 learning_rate: 0.01 power: 0.9 type: PolynomialDecay model: backbone: pretrained: https://bj.bcebos.com/paddleseg/dygraph/PP_STDCNet2.tar.gz type: STDC2 type: PPLiteSeg optimizer: momentum: 0.9 type: sgd weight_decay: 4.0e-05 train_dataset: dataset_root: data/mine mode: train num_classes: 4 train_path: data/mine/train.txt transforms:
• max_scale_factor: 2.0 min_scale_factor: 0.5 scale_step_size: 0.25 type: ResizeStepScaling
• crop_size:
  • 512
  • 512 type: RandomPaddingCrop
• type: RandomHorizontalFlip
• brightness_range: 0.5 contrast_range: 0.5 saturation_range: 0.5 type: RandomDistort
• type: Normalize type: Dataset val_dataset: dataset_root: data/mine mode: val num_classes: 4 transforms:

• type: Normalize type: Dataset val_path: data/mine/valid.txt

  W0929 10:52:04.378280 4902 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 11.2, Runtime API Version: 11.2 W0929 10:52:04.378324 4902 gpu_resources.cc:91] device: 0, cuDNN Version: 8.2. 2022-09-29 10:52:05 [INFO] Loading pretrained model from https://bj.bcebos.com/paddleseg/dygraph/PP_STDCNet2.tar.gz 2022-09-29 10:52:05 [INFO] There are 265/265 variables loaded into STDCNet. /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/nn/layer/norm.py:654: UserWarning: When training, we now always track global mean and variance. "When training, we now always track global mean and variance.") Traceback (most recent call last): File "train.py", line 230, in main(args) File "train.py", line 225, in main to_static_training=cfg.to_static_training) File "/home/aistudio/work/PaddleSeg/paddleseg/core/train.py", line 211, in train losses=losses) File "/home/aistudio/work/PaddleSeg/paddleseg/core/train.py", line 55, in loss_computation loss_list.append(coef_i loss_i(logits, labels)) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 930, in call return self._dygraph_call_func(inputs, *kwargs) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 915, in _dygraph_call_func outputs = self.forward(inputs, kwargs) File "/home/aistudio/work/PaddleSeg/paddleseg/models/losses/cross_entropy_loss.py", line 86, in forward weight=self.weight) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/nn/functional/loss.py", line 1723, in cross_entropy label_max.item())) ValueError: Target 160 is out of upper bound.**

[Bobholamovic]

Please check if there are illegal values in the labels, say, 160 (given that the number of classes is 4).