如何解决“InvalidArgumentError: jpeg::Uncompress failed”。

Question

我正在研究图像分类模型，使用 RandomForestClassifier 创建模型，使用 TensorFlow 创建训练模型层。我的数据集仅包含 jpg 图像，一切都很好，直到我运行此代码

train_rfc=feature_extractor.predict(train_ds)
rf_model=rfc(n_estimators=100,random_state=42)
rf_model.fit(train_rfc,train_en_label)

执行此操作后我得到了

---------------------------------------------------------------------------

InvalidArgumentError                      Traceback (most recent call last)

<ipython-input-17-6b7f83954d85> in <module>()
----> 1 train_rfc=feature_extractor.predict(train_ds)
      2 rf_model=rfc(n_estimators=100,random_state=42)
      3 rf_model.fit(train_rfc,train_en_label)

6 frames

/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     58     ctx.ensure_initialized()
     59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60                                         inputs, attrs, num_outputs)
     61   except core._NotOkStatusException as e:
     62     if name is not None:

InvalidArgumentError:  jpeg::Uncompress failed. Invalid JPEG data or crop window.
     [[{{node decode_image/DecodeImage}}]]
     [[IteratorGetNext]] [Op:__inference_predict_function_247]

Function call stack:
predict_function

谁能建议我必须在输入管道中进行哪些更改。