PaddleClas
PaddleClas copied to clipboard
PaddlePaddle
PaddleClas2.3 损失函数脚本配置报错，度量学习。亟待回复。谢谢。
欢迎您使用PaddleClas并反馈相关问题，非常感谢您对PaddleClas的贡献！ 提出issue时，辛苦您提供以下信息，方便我们快速定位问题并及时有效地解决您的问题：
- PaddleClas版本以及PaddlePaddle版本：请您提供您使用的版本号或分支信息，如PaddleClas release/2.3和PaddlePaddle 2.2.2
- 涉及的其他产品使用的版本号：如您在使用PaddleClas的同时还在使用其他产品，如PaddleServing、PaddleInference等，请您提供其版本号
- 训练环境信息： a. 具体操作系统，如Linux/Windows/MacOS b. Python版本号，如Python3.6/7/8 c. CUDA/cuDNN版本， 如CUDA10.2/cuDNN 7.6.5等
- 完整的代码(相比于repo中代码，有改动的地方)、详细的错误信息及相关log 参考 PaddleClas 代码解析-2.3 损失函数
Loss: Train: - CELoss: weight: 1.0 - TripletLossV2: weight: 1.0 margin: 0.5
但是报错：
Traceback (most recent call last):
File "tools/train.py", line 32, in <module>
engine.train()
File "/home/aistudio/PaddleClas/ppcls/engine/engine.py", line 265, in train
self.train_epoch_func(self, epoch_id, print_batch_step)
File "/home/aistudio/PaddleClas/ppcls/engine/train/train.py", line 51, in train_epoch
loss_dict = engine.train_loss_func(out, batch[1])
File "/home/aistudio/PaddleClas/ppcls/loss/__init__.py", line 46, in __call__
loss = loss_func(input, batch)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 917, 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 907, in _dygraph_call_func
outputs = self.forward(*inputs, **kwargs)
File "/home/aistudio/PaddleClas/ppcls/loss/triplet.py", line 27, in forward
inputs = input["features"]
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/varbase_patch_methods.py", line 598, in __getitem__
return self._getitem_index_not_tensor(item)
ValueError: (InvalidArgument) Currently, Tensor.__indices__() only allows indexing by Integers, Slices, Ellipsis, None, tuples of these types and list of Bool and Integers, but received str in 1th slice item (at /paddle/paddle/fluid/pybind/imperative.cc:645)
你好，请问你具体修改了什么代码呢？或者是运行了哪个脚本出现这个报错呢
就是普通的ResNet50.yaml 修改 Loss: Train: - CELoss: weight: 1.0 - TripletLossV2: weight: 1.0 margin: 0.5，其他没变