def test_squeeze(x, data):
axes = data.draw(valid_axes(x.ndim), label="axes")
x_arr = Tensor(np.copy(x))
x_arr2 = Tensor(np.copy(x))
def f(x):
return np.squeeze(x, axes)
try:
numpy_out = np.squeeze(x, axes)
except ValueError:
with raises(ValueError):
squeeze(x_arr, axes, constant=False)
return
o = squeeze(x_arr, axes, constant=False)
o_method = x_arr2.squeeze(axes)
assert_allclose(o.data, numpy_out)
assert_allclose(o_method.data, numpy_out)
grad = data.draw(
hnp.arrays(shape=o.shape,
dtype=float,
elements=st.floats(1, 10),
unique=True),
label="grad",
)
o.backward(grad)
o_method.backward(grad)
dx, = numerical_gradient_full(f, x, back_grad=grad)
assert_allclose(x_arr.grad, dx)
assert_allclose(x_arr2.grad, dx)
dbad = []
wcaption = []
for x in batch:
dgoodtemp = iv.get_resnet_vector(x[0], resnet=resnet)
dbadtemp = iv.get_resnet_vector(x[2], resnet=resnet)
wcaptiontemp = text_embeds[x[1]]
dgood.append(dgoodtemp)
dbad.append(dbadtemp)
wcaption.append(wcaptiontemp)
wcaption = np.array(wcaption)
wgood = model(np.array(dgood))
wbad = model(np.array(dbad))
sgood = (wcaption[:, np.newaxis] @ wgood[:, :, np.newaxis])
sbad = (wcaption[:, np.newaxis] @ wbad[:, :, np.newaxis])
sgood = mg.squeeze(sgood)
sbad = mg.squeeze(sbad)
loss = la.loss(sgood, sbad)
accuracy = la.acc(sgood, sbad)
loss.backward()
optim.step()
loss.null_gradients()
if batch_rate % 100 == 0:
plotter.set_train_batch({
"loss": loss.item(),
"accuracy": accuracy
},
batch_size=batch_size)
if epoch_rate % plot_rate == 0 and epoch_rate > 0: