For me the solution was downgrading the h5py
package (in my case to 2.10.0), apparently putting back only Keras and Tensorflow to the correct versions was not enough.
More Related Contents:
- How to apply gradient clipping in TensorFlow?
- Keras Sequential model input layer
- Keras custom loss function: Accessing current input pattern
- How can I use a pre-trained neural network with grayscale images?
- Removing then Inserting a New Middle Layer in a Keras Model
- What is the role of TimeDistributed layer in Keras?
- keras: how to save the training history attribute of the history object
- How to fix “ResourceExhaustedError: OOM when allocating tensor”
- Understanding Keras LSTMs
- How to get the location of all text present in an image using OpenCV?
- How to concatenate two layers in keras?
- Keras replacing input layer
- ValueError at /image/ Tensor Tensor(“activation_5/Softmax:0”, shape=(?, 4), dtype=float32) is not an element of this graph
- ValueError: Error when checking target: expected model_2 to have shape (None, 252, 252, 1) but got array with shape (300, 128, 128, 3)
- How to get other metrics in Tensorflow 2.0 (not only accuracy)?
- How to understand the term `tensor` in TensorFlow?
- Unbalanced data and weighted cross entropy
- Custom loss function in Keras
- Save and load model optimizer state
- confusion matrix error “Classification metrics can’t handle a mix of multilabel-indicator and multiclass targets”
- Keras accuracy does not change
- How does mask_zero in Keras Embedding layer work?
- Keras LSTM input dimension setting
- How to add and remove new layers in keras after loading weights?
- How to log Keras loss output to a file
- ‘Tensor’ object has no attribute ‘lower’
- ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
- Can I send callbacks to a KerasClassifier?
- Keras give input to intermediate layer and get final output
- how to implement custom metric in keras?