MCPcopy Create free account
hub / github.com/alibaba/nann / val_and_grad_function

Function val_and_grad_function

tensorflow/tensorflow/python/eager/backprop.py:406–471  ·  view source on GitHub ↗

Returns a function that computes f and its derivative w.r.t. params. Example: ```python # f(x, y) = (x ^ 3) * y - x * (y ^ 2) # Therefore, the 1st order derivatives are: # df / dx = 3 * (x ^ 2) * y - y ^ 2 # df / dy = x ^ 3 - 2 * x * y def f(x, y): return x * x * x * y - x * y

(f, params=None)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

decoratedFunction · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected