| You are attempting to create a variable while in a… | exception | error | |
| A KerasTensor cannot be used as input to a TensorFlow… | exception | error | |
| A KerasTensor cannot be used as input to a JAX function. A… | exception | error | |
| `backend_variable` must be a `backend.Variable`. Recevied… | exception | error | keras, export, savedmodel, type-error, backend |
| Layer ' ' was never built and thus it doesn't have any… | exception | critical | keras, model-loading, custom-layers, serialization |
| Variable is already initialized. | exception | error | |
| ldexp exponent must be an integer type. Received: x2 dtype= | exception | error | |
| Unable to revive model from config. When overriding the… | exception | error | |
| Argument `constant_values` can only be provided when `mode… | exception | error | |
| Invalid value for argument `interpolation`. Expected of one | validation | error | |
| Unknown resize method | exception | error | |
| Expected `padding` to be a tuple of 3 tuples of 2 integers… | exception | error | keras, padding, argument-validation, legacy, conv3d |
| Shapes are incompatible for associative_scan interleaving… | exception | error | |
| The endpoint ' ' is neither an attribute of the reloaded… | exception | error | keras, tfsmlayer, training-endpoint, savedmodel, validation |
| Input `x` should be a tuple of two tensors - real and… | exception | error | |
| Arguments `target` and `output` must have the same shape up… | exception | error | |
| Unsupported quantization mode | exception | error | keras, lora, quantization, model-saving, einsum-dense |
| Invalid transform rank: expected rank 1 (single transform)… | exception | error | |
| Both input arrays must be (arrays of) 2 or 3-dimensional… | exception | error | |
| Received: input_number= | validation | error | keras, preprocessing, range-validation, augmentation |
| Cannot save layer ' ' because it is quantized with mode ' '… | exception | critical | keras, quantization, gptq, awq, model-saving, calibration |
| Invalid value for argument `fill_mode`. Expected of one | exception | error | |
| Invalid value for argument `fill_mode`. Expected one of | exception | error | |
| At least one tensor in input `x` is not of type… | exception | error | |
| Cannot add call-context args after the layer has been… | exception | error | keras, layer, lifecycle, api-misuse |
| Invalid axis values. Received: axis= | exception | error | |
| The last dimension of `query_shape` and `value_shape` must… | exception | error | keras, attention, shape-mismatch, validation, grouped-query-attention |
| For NASNet-A models, the `penultimate_filters` must be a… | exception | error | |
| Requested the deserialization of a `TFSMLayer`, which loads… | exception | error | keras, tfsmlayer, deserialization, security, unsafe-deserialization |
| The endpoint ' ' is neither an attribute of the reloaded… | exception | error | keras, tfsmlayer, savedmodel, endpoint, validation |
| The `mask` passed to the `TimeDistributed` layer must be at… | exception | error | keras, time-distributed, masking, shape-validation |
| Could not determine row/column split. | exception | error | keras, gptq, quantization, einsum-dense, kernel-shape |
| `input_tensors` must have the same structure as… | validation | error | |
| Requested the deserialization of a `Lambda` layer whose… | exception | error | |
| Invalid images dtype: expected float dtype. Received… | exception | error | |
| Invalid value for argument `method`. Expected of one | exception | error | |
| Array inputs to associative_scan must have the same first… | exception | error | |
| start_points and end_points must have the same shape… | exception | error | |
| Input size must be at least | exception | error | |
| When setting `include_top=True` and loading `imagenet`… | exception | error | |
| `dot_product_attention` only supports 4D inputs. Received… | exception | error | |
| Invalid end_points shape: expected (4,2) for a single image… | exception | error | |
| Invalid Reduction Key | validation | error | keras, losses, reduction, invalid-argument |
| Invalid value for argument `fill_mode`. Only `'constant'`… | exception | error | |
| Invalid start_points shape: expected (4,2) for a single… | exception | error | |
| Unknown fill_mode | exception | error | |
| `TimeDistributed` Layer should be passed an `input_shape`… | exception | error | keras, time-distributed, shape-validation, input-dimensions |
| Values in `cropping` argument should be smaller than the… | validation | error | keras, cropping3d, shape-validation, reshaping-layer |
| Invalid input shape for input | validation | error | |
| The TFSMLayer is only currently supported with the… | exception | error | keras, tfsmlayer, backend, tensorflow, not-implemented |
| Invalid feature type | validation | error | |
| Theta of a Thresholded ReLU layer cannot be None, expecting… | validation | error | keras, activation, argument-validation, legacy, relu |
| You forgot to call `super().__init__()` in the `__init__()`… | exception | error | keras, metrics, custom-metric, init, subclassing |
| In a nested call() argument, you cannot mix tensors and… | validation | error | keras, tensor, argument-validation, nested-argument |
| Argument synchronized=True is not supported with NumPy. | exception | error | |
| Expected input to have rank >= 2. Received input with shape | validation | error | keras, linalg, shape-validation, rank-error, matrix-ops |
| Flash attention is not supported in numpy backend. | exception | error | |
| `mode` argument value not supported. Expected one of | exception | error | |
| object has no attribute 'kernel' nor 'embeddings | exception | error | |
| `f` should be a callable. Received: f= | exception | error | |
| Returning attention scores is not supported when flash… | exception | error | keras, attention, flash-attention, grouped-query-attention, incompatibility |
| `initializer` was passed both positionally and as a keyword… | validation | error | keras, layers, add-weight, arguments |
| Length of `start_indices` must match length of `shape`… | exception | error | |
| Rank of `condition` should be less than or equal to rank of… | exception | error | keras, broadcasting, rank-mismatch, legacy, switch |
| Received an invalid value for argument `num_heads`… | exception | error | keras, multi-head-attention, argument-validation, value-error |
| Unknown data_format | exception | error | keras, tensorflow, data-format, argument-validation |
| Invalid coordinates rank: expected at least rank 2… | exception | error | |
| Sequential model ' ' has no defined outputs yet. | exception | error | keras, sequential, outputs, lazy-build |
| For `padding='same'`, `output_size` width | exception | error | keras, image, patches, shape-mismatch, input-validation |
| The argument `kernel_size` cannot contain 0. Received… | exception | error | keras, separable-conv, kernel-size, invalid-arguments |
| input_tensor.shape[2] must equal input_shape[1]; Received… | exception | error | |
| Unknown loss function | validation | error | |
| Could not interpret serialized | exception | error | |
| Unknown `interpolation | exception | error | keras, preprocessing, argument-validation, enum |
| Cannot do batch_dot on inputs with tf.shapes | exception | error | keras, tensorflow, batch-dot, dimension-mismatch |
| Expected the 2 dimensions of the `dilation_rate` argument… | exception | error | keras, tensorflow, conv2d-transpose, dilation, argument-validation |
| ImageNet weights can only be loaded with NASNetLarge or… | exception | error | |
| Input shapes and must match for PSNR calculation. | exception | error | |
| Unsupported `.npy` file version | validation | error | |
| Cannot interpret `dtype` argument. Expected a string or an… | exception | error | |
| Unsupported reduction | exception | error | |
| Improper config format for | exception | error | |
| Invalid channel size: expected 3 (RGB) or 1 (Grayscale)… | exception | error | |
| If providing `bounding_boxes['labels']` as a list, it… | validation | error | keras, bounding-boxes, labels, densify, type-error |
| Subclasses must implement compute_loss | exception | error | |
| Unexpected object from deserialization, expected a layer or… | validation | error | |
| adaptive_average_pool supports only 1D/2D/3D inputs | validation | error | |
| The number of input channels must be evenly divisible by… | validation | error | |
| If `include_top` is True, you should specify a static… | exception | error | |
| Unrecognized value for `merge_mode`. Received | validation | error | |
| All cells must have a `call` method. Received cell without… | exception | error | keras, rnn, stacked-cells, duck-typing |
| Leading dimensions of input arrays must match | exception | error | |
| Unsupported sparse format | validation | error | |
| Variable is not properly initialized (raw_value missing)… | exception | error | |
| `cdist` inputs must have rank >= 2 | exception | error | |
| For layer ' ', Received ` ()` argument ` `, which does not… | validation | error | keras, shape-inference, api-contract, naming-convention |
| Expect `mesh` to be an instance of `DeviceMesh`. Received… | exception | error | |
| Failed to convert PyTorch model to LiteRT. Common causes… | exception | error | |
| Graph disconnected: cannot find parent for tensor | exception | error | keras, graph, disconnected-graph, functional-api |
| 'row_axis', 'col_axis', and 'channel_axis' must be distinct | exception | error | keras, preprocessing, image, validation |