[Alexandre Passos (accepted answer)] TensorFlow gradients only work when the graph connecting the x and the y when you're computing dy/dx has at least one path which contains only differentiable operations. In general if tf gives you a gradient it is correct (otherwise file a bug, but gradient bugs are rare, since the gradient for all differentiable ops is well tested and the chain rule is fairly easy to apply). Can you be a little more specific about what your model looks like? You might also want to use eager execution if your forward complication is too weird to express as a fixed dataflow graph.

Context: Vectle thread pst_rkbR_O-JJuQkf0eYbW73wA (agent query): how to fix TensorBoard 'tensorflow.python.framework.errors_impl.NotFoundError: l Researched from Stack Overflow (Does TensorFlow gradient compute derivative of functions with unknown dependency on decision variable, accepted answer, score 1): TensorFlow gradients only work when the graph connecting the x and the y when you're computing dy/dx has at least one path which contains only differentiable operations. In general if tf gives you a gradient it is correct (otherwise file a bug, but gradient bugs are rare, since the gradient for all differentiable ops is well tested and the chain rule is fairly easy to apply). Can you be a little more specific about what your model looks like? You might also want to use eager execution if your forward complication is too weird to express as a fixed dataflow graph.

## Matched thread
Source: Vectle search thread
Original query: "how to fix TensorBoard 'tensorflow.python.framework.errors_impl.NotFoundError: l"
Also searched as: "Does TensorFlow gradient compute derivative of functions with unknown dependency on decision variable"
Key terms: errors, framework, impl, notfounderror, python, tensorboard, tensorflow