def __forward(self, train, a_batch, q_batch, y_batch = None): n_units = self.__n_units mod = self.__mod gpu = self.__gpu batch_size = len(a_batch) x_len = len(a_batch[0]) if gpu >=0: a_batch = [[mod.array(e) for e in row] for row in a_batch] self.reset_state() x_data = mod.concatenate([mod.transpose(mod.concatenate(a_batch[b], axis=0)).reshape((1,n_units,1,x_len)) for b in range(batch_size)], axis=0) x = Variable(x_data, volatile=not train) x = F.reshape(x, (batch_size,n_units,x_len)) M_t = F.swapaxes(x, 1, 2) full_shape = (batch_size, x_len, n_units) for l in range(x_len): x_t = [] for b in range(batch_size): x = a_batch[b][l] x_t.append(x) x_t = Variable(mod.concatenate(x_t, axis=0), volatile=not train) o_t, m_t, z_t = self.read(M_t, x_t, batch_size, train) c_t = self.compose(o_t, m_t, train) M_t, h_t = self.write(M_t, c_t, z_t, full_shape, train) if gpu >=0: q_batch = [[mod.array(e) for e in row] for row in q_batch] x_data = mod.concatenate([mod.transpose(mod.concatenate(q_batch[b], axis=0)).reshape((1,n_units,1,x_len)) for b in range(batch_size)], axis=0) x = Variable(x_data, volatile=not train) x = F.reshape(x, (batch_size,n_units,x_len)) M2_t = F.swapaxes(x, 1, 2) for l in range(x_len): x_t = [] for b in range(batch_size): x = q_batch[b][l] x_t.append(x) x_t = Variable(mod.concatenate(x_t, axis=0), volatile=not train) o_t, m_t, z_t, m2_t, z2_t = self.read2(M_t, M2_t, x_t, batch_size, train) c_t = self.compose2(o_t, m_t, m2_t, train) M_t, M2_t, h2_t = self.write2(M_t, M2_t, c_t, z_t, z2_t, full_shape, train) hs = F.concat([F.concat([h_t, h2_t], axis=1), h_t-h2_t, h_t*h2_t], axis=1) hs = F.relu(self.h_l1(hs)) y = self.l_y(F.dropout(hs, ratio=0.3, train=train)) preds = mod.argmax(y.data, 1).tolist() accum_loss = 0 if train else None if train: if gpu >= 0: y_batch = cuda.to_gpu(y_batch) lbl = Variable(y_batch, volatile=not train) accum_loss = F.softmax_cross_entropy(y, lbl) return preds, accum_loss
for i in range(0, len(index_test), BATCH_SIZE):
Text = []
Label = []
Feature = []
for n in range(BATCH_SIZE):
if i + n >= (len(index_test)):
text = index_test[i + n - len(index_test)][0]
label = index_test[i + n - len(index_test)][1]
feature = index_test[i + n - len(index_test)][2]
else:
text = index_test[i + n][0]
label = index_test[i + n][1]
feature = index_test[i + n][2]
Text.append(text)
Label.append(label)
Feature.append(feature)
Text = np.array(Text, dtype="int32")
Label = np.array(Label, dtype="int32")
Feature = np.array(Feature, dtype="float32")
Feature = np.mat(Feature)
Feature = Feature.reshape(-1, 1)
Feature = np.array(Feature)
# print("feature vector = ", Feature)
Feature = Variable(Feature)
model.cleargrads()
loss = model(Text, Label, Feature)
#loss.backward()
#optimizer.update()
def __call__(self, x, t=None):
on_gpu = isinstance(x.data, cupy.ndarray)
self.cae_ones1.train = self.train
self.vgg2.train = self.train
roi_scale = self.cae_ones1.encode(x)
if t is None:
assert self.train is False
if on_gpu:
roi_scale_data = cuda.to_cpu(roi_scale.data)
rois_data = self.initial_roi * roi_scale_data
if on_gpu:
rois_data = cuda.to_cpu(rois_data)
x_data = cuda.to_cpu(x.data)
rois_data = rois_data.astype(int)
cropped = []
for i in xrange(len(x_data)):
roi = rois_data[i]
im = blob_to_im(x_data[i])
im = im[roi[0]:roi[2], roi[1]:roi[3]]
im = resize(im, (128, 128), preserve_range=True)
cropped.append(im_to_blob(im))
cropped = np.array(cropped, dtype=np.float32)
if on_gpu:
cropped = cuda.to_gpu(cropped)
cropped = Variable(cropped, volatile=not self.train)
self.vgg2(cropped)
self.y = self.vgg2.y
return self.y
# randomly change the param and estimate good parameter for the task
min_y = None
rands_shape = [self.learning_n_sample] + list(roi_scale.data.shape)
rands = self.learning_rate * (2 * np.random.random(rands_shape) - 1) + 1
rands[0] = np.ones(roi_scale.data.shape)
for i, rand in enumerate(rands):
if on_gpu:
roi_scale_data = cuda.to_cpu(roi_scale.data)
rois_data = rand * (self.initial_roi * roi_scale_data)
x_data = cuda.to_cpu(x.data)
skip = False
rois_data = rois_data.astype(int)
cropped = []
for j in xrange(len(x_data)):
roi = rois_data[j]
im = blob_to_im(x_data[j])
im = im[roi[0]:roi[2], roi[1]:roi[3]]
if im.size == 0:
skip = True
break
im = resize(im, (128, 128), preserve_range=True)
cropped.append(im_to_blob(im))
if skip:
continue
cropped = np.array(cropped)
if on_gpu:
cropped = cuda.to_gpu(cropped)
cropped = Variable(cropped, volatile=not self.train)
self.vgg2(cropped, t)
h = self.vgg2.y
loss = F.softmax_cross_entropy(h, t)
if min_y is None:
min_loss_data = float(loss.data)
min_y = h
min_loss = loss
min_rand = rand
min_rois = rois_data
elif min_loss_data > float(loss.data):
min_loss_data = float(loss.data)
min_y = h
min_loss = loss
min_rand = rand
min_rois = rois_data
if on_gpu:
min_rand = cuda.to_gpu(min_rand)
rois_data = min_rand * roi_scale.data
xp = cuda.get_array_module(rois_data)
rois_data = rois_data.astype(xp.float32)
rois = Variable(rois_data, volatile=not self.train)
loss1 = F.mean_squared_error(roi_scale, rois)
loss2 = min_loss
self.loss = loss1 + loss2
self.accuracy = F.accuracy(min_y, t)
return self.loss
x = []
for i in range(5):
x.append(atrain[r:r + train_size])
r = random.choice([0, alen - train_size])
x = Variable(np.array(x).astype(np.float32))
y = Variable(
np.array([[1, 0], [1, 0], [1, 0], [1, 0],
[1, 0]]).astype(np.float32)) #aはゼロ
model.cleargrads() #勾配初期化
loss = model(x, y) #誤差計算
loss.backward() #勾配計算
optimizer.update() #パラメータ更新
r = random.choice([0, blen - train_size])
x = []
for i in range(5):
x.append(atrain[r:r + train_size])
r = random.choice([0, alen - train_size])
x = Variable(np.array(x).float32)
y = Variable(
np.array([[0, 1], [0, 1], [0, 1], [0, 1],
[0, 1]]).astype(np.float32)) #bは１
model.cleargrads() #勾配初期化
loss = model(x, y) #誤差計算
loss.backward() #勾配計算
optimizer.update() #パラメータ更新
if j % 10 == 0:
print(j, "/", epoch_count, "回終了")
#####結果の出力##########################
xt = Variable(make_wakati(恥の多い生涯を送って来ました))
yt = model.fwd(xt)
cv2.waitKey(50)
#print('shape', img2.shape[:2])
img1 = img1[:, :, :3]
img1 = np.asarray(img1, dtype=np.float32) / 255.0
img1 = img1.transpose(2, 0, 1)
img2 = img2[:, :, :3]
img2 = np.asarray(img2, dtype=np.float32) / 255.0
img2 = img2.transpose(2, 0, 1)
# load model
#model.predictor.train = False
# forward
x = []
x.append(np.array(img1))
x.append(np.array((img2)))
x = np.asarray(x, dtype=np.float32)
x = Variable(x)
if hasattr(cuda, "cupy"):
print('hasatt inside')
cuda.get_device(0).use()
model.to_gpu()
x.to_gpu()
one_hot_t = []
first = [0, 0, 0, 1]
secund = [0, 0, 1, 0]
one_hot_t.append(np.array(first))
one_hot_t.append(np.array(secund))
