FTTransform多分类练习时遇到的问题

[Wyw-Kevin]

1、现在4.04版本torchkeras没有找到KerasModel来导入，但是有kerasmodel可以导入
2、在keras_model.fit(
train_data = dl_train,
val_data= dl_val,
ckpt_path='checkpoint',
epochs=20,
patience=10,
monitor="val_acc",
mode="max",
plot = True,
wandb = False
)部分出现错误
ValueError Traceback (most recent call last)
Cell In[47], line 1
----> 1 keras_model.fit(
2 train_data = dl_train,
3 val_data= dl_val,
4 ckpt_path='checkpoint',
5 epochs=20,
6 patience=10,
7 monitor="val_acc",
8 mode="max",
9 plot = True,
10 wandb = False
11 )

File d:\miniconda\envs\Classifier\Lib\site-packages\torchkeras\kerasmodel.py:321, in KerasModel.fit(self, train_data, val_data, epochs, ckpt_path, patience, monitor, mode, callbacks, plot, wandb, mixed_precision, cpu, gradient_accumulation_steps)
319 train_epoch_runner = self.EpochRunner(train_step_runner, quiet)
320 train_metrics = {'epoch': epoch}
--> 321 train_metrics.update(train_epoch_runner(train_dataloader))
323 for name, metric in train_metrics.items():
324 self.history[name] = self.history.get(name, []) + [metric]

File d:\miniconda\envs\Classifier\Lib\site-packages\torchkeras\kerasmodel.py:133, in EpochRunner.call(self, dataloader)
130 for step, batch in loop:
131 # Perform a step with the provided StepRunner
...
---> 49 features, labels = batch
51 # Compute loss
52 with self.accelerator.autocast():

ValueError: too many values to unpack (expected 2)
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...