def forward(net, input_data, deploy=False):
"""Defines and creates the ReInspect network given the net, input data
and configurations."""
net.clear_forward()
if deploy:
image = np.array(input_data["image"])
else:
image = np.array(input_data["image"])
label = np.array(input_data["label"])
net.f(NumpyData("label", data=label))
net.f(NumpyData("image", data=image))
generate_decapitated_alexnet(net)
net.f(
InnerProduct(name="fc8_dish",
bottoms=["fc7"],
param_lr_mults=[1.0 * 10, 2.0 * 10],
param_decay_mults=[1.0, 0.0],
weight_filler=Filler("gaussian", 0.01),
bias_filler=Filler("constant", 0.0),
num_output=128))
net.f(Softmax("dish_probs", bottoms=["fc8_dish"]))
if not deploy:
net.f(SoftmaxWithLoss(name="loss", bottoms=["fc8_dish", "label"]))
# net.f(Accuracy(name="dish_accuracy",bottoms=["fc8_dish_23", "label"]))
if deploy:
probs = np.array(net.blobs["dish_probs"].data)
return probs
else:
return None
def forward(net, sentence_batches):
net.clear_forward()
batch = next(sentence_batches)
sentence_batch = pad_batch(batch)
length = min(sentence_batch.shape[1], 100)
assert length > 0
net.f(NumpyData('lstm_seed', np.zeros((batch_size, dimension))))
for step in range(length):
if step == 0:
prev_hidden = 'lstm_seed'
prev_mem = 'lstm_seed'
word = np.zeros(sentence_batch[:, 0].shape)
else:
prev_hidden = 'lstm%d_hidden' % (step - 1)
prev_mem = 'lstm%d_mem' % (step - 1)
word = sentence_batch[:, step - 1]
net.f(NumpyData('word%d' % step, word))
net.f(
Wordvec('wordvec%d' % step,
dimension,
vocab_size,
bottoms=['word%d' % step],
param_names=['wordvec_param']))
net.f(
Concat('lstm_concat%d' % step,
bottoms=[prev_hidden, 'wordvec%d' % step]))
net.f(
LstmUnit('lstm%d' % step,
bottoms=['lstm_concat%d' % step, prev_mem],
param_names=[
'lstm_input_value', 'lstm_input_gate',
'lstm_forget_gate', 'lstm_output_gate'
],
tops=['lstm%d_hidden' % step,
'lstm%d_mem' % step],
num_cells=dimension))
net.f(
Dropout('dropout%d' % step, 0.16,
bottoms=['lstm%d_hidden' % step]))
net.f(NumpyData('label%d' % step, sentence_batch[:, step]))
net.f(
InnerProduct('ip%d' % step,
vocab_size,
bottoms=['dropout%d' % step],
param_names=['softmax_ip_weights',
'softmax_ip_bias']))
net.f(
SoftmaxWithLoss('softmax_loss%d' % step,
ignore_label=zero_symbol,
bottoms=['ip%d' % step,
'label%d' % step]))
def generate_losses(net, net_config):
"""Generates the two losses used for ReInspect. The hungarian loss and
the final box_loss, that represents the final softmax confidence loss"""
net.f("""
name: "hungarian"
type: "HungarianLoss"
bottom: "bbox_concat"
bottom: "boxes"
bottom: "box_flags"
top: "hungarian"
top: "box_confidences"
top: "box_assignments"
loss_weight: %s
hungarian_loss_param {
match_ratio: 0.5
permute_matches: true
}""" % net_config["hungarian_loss_weight"])
net.f(SoftmaxWithLoss("box_loss",
bottoms=["score_concat", "box_confidences"]))
def forward(net, input_data, net_config, deploy=False):
"""Defines and creates the ReInspect network given the net, input data
and configurations."""
net.clear_forward()
net.f(
NumpyData("wordvec_layer",
data=np.array(input_data["wordvec_layer"]))) # 128*38*100*1
net.f(NumpyData("target_words",
data=np.array(input_data["target_words"]))) # 128*100*1*1
tops = []
slice_point = []
for i in range(net_config['max_len']):
tops.append('label%d' % i)
if i != 0:
slice_point.append(i)
net.f(
Slice("label_slice_layer",
slice_dim=1,
bottoms=["target_words"],
tops=tops,
slice_point=slice_point))
tops = []
slice_point = []
for i in range(net_config['max_len']):
tops.append('target_wordvec%d_4d' % i)
if i != 0:
slice_point.append(i)
net.f(
Slice("wordvec_slice_layer",
slice_dim=2,
bottoms=['wordvec_layer'],
tops=tops,
slice_point=slice_point))
for i in range(net_config["max_len"]): # 128*38*1*1 -> 128*38
net.f("""
name: "target_wordvec%d"
type: "Reshape"
bottom: "target_wordvec%d_4d"
top: "target_wordvec%d"
reshape_param {
shape {
dim: 0 # copy the dimension from below
dim: -1
}
}
""" % (i, i, i))
#net.f(Reshape('target_wordvec%d'%i, bottoms = ['target_wordvec%d_4d'%i], shape = [0,-1]))
filler = Filler("uniform", net_config["init_range"])
for i in range(net_config['max_len']):
if i == 0:
net.f(
NumpyData(
"dummy_layer",
np.zeros((net_config["batch_size"],
net_config["lstm_num_cells"]))))
net.f(
NumpyData(
"dummy_mem_cell",
np.zeros((net_config["batch_size"],
net_config["lstm_num_cells"]))))
for j in range(net_config['lstm_num_stacks']):
bottoms = []
if j == 0:
bottoms.append('target_wordvec%d' % i)
if j >= 1:
bottoms.append('dropout%d_%d' % (j - 1, i))
if i == 0:
bottoms.append("dummy_layer")
else:
bottoms.append('lstm%d_hidden%d' % (j, i - 1))
net.f(Concat('concat%d_layer%d' % (j, i), bottoms=bottoms))
param_names = []
for k in range(4):
param_names.append('lstm%d_param_%d' % (j, k))
bottoms = ['concat%d_layer%d' % (j, i)]
if i == 0:
bottoms.append('dummy_mem_cell')
else:
bottoms.append('lstm%d_mem_cell%d' % (j, i - 1))
net.f(
LstmUnit('lstm%d_layer%d' % (j, i),
net_config["lstm_num_cells"],
weight_filler=filler,
param_names=param_names,
bottoms=bottoms,
tops=[
'lstm%d_hidden%d' % (j, i),
'lstm%d_mem_cell%d' % (j, i)
]))
net.f(
Dropout('dropout%d_%d' % (j, i),
net_config["dropout_ratio"],
bottoms=['lstm%d_hidden%d' % (j, i)]))
bottoms = []
for i in range(net_config['max_len']):
bottoms.append('dropout%d_%d' % (net_config['lstm_num_stacks'] - 1, i))
net.f(Concat('hidden_concat', bottoms=bottoms, concat_dim=0))
net.f(
InnerProduct("inner_product",
net_config['vocab_size'],
bottoms=["hidden_concat"],
weight_filler=filler))
bottoms = []
for i in range(net_config['max_len']):
bottoms.append('label%d' % i)
net.f(Concat('label_concat', bottoms=bottoms, concat_dim=0))
if deploy:
net.f(Softmax("word_probs", bottoms=["inner_product"]))
else:
net.f(
SoftmaxWithLoss("word_loss",
bottoms=["inner_product", "label_concat"],
ignore_label=net_config['zero_symbol']))
def forward(net, input_data, net_config, phase='train', deploy=False):
"""Defines and creates the ReInspect network given the net, input data
and configurations."""
net.clear_forward()
batch_ws_i = input_data["ws_i"]
batch_stop_i = [net_config['max_len']] * net_config['batch_size']
wordvec_layer = input_data["wordvec_layer"] # 128*38*100*1
net.f(NumpyData("target_words",
data=np.array(input_data["target_words"]))) # 128*100*1*1
tops = []
slice_point = []
for i in range(net_config['max_len']):
tops.append('label%d' % i)
if i != 0:
slice_point.append(i)
net.f(
Slice("label_slice_layer",
slice_dim=1,
bottoms=["target_words"],
tops=tops,
slice_point=slice_point))
net.f(NumpyData("target_wordvec%d" % 0,
data=wordvec_layer[:, :, 0, 0])) # start symbol, 128*38
filler = Filler("uniform", net_config["init_range"])
for i in range(net_config['max_len']):
if i == 0:
net.f(
NumpyData(
"dummy_layer",
np.zeros((net_config["batch_size"],
net_config["lstm_num_cells"]))))
net.f(
NumpyData(
"dummy_mem_cell",
np.zeros((net_config["batch_size"],
net_config["lstm_num_cells"]))))
for j in range(net_config['lstm_num_stacks']):
bottoms = []
if j == 0:
bottoms.append('target_wordvec%d' % i)
if j >= 1:
bottoms.append('dropout%d_%d' % (j - 1, i))
if i == 0:
bottoms.append("dummy_layer")
else:
bottoms.append('lstm%d_hidden%d' % (j, i - 1))
net.f(Concat('concat%d_layer%d' % (j, i), bottoms=bottoms))
param_names = []
for k in range(4):
param_names.append('lstm%d_param_%d' % (j, k))
bottoms = ['concat%d_layer%d' % (j, i)]
if i == 0:
bottoms.append('dummy_mem_cell')
else:
bottoms.append('lstm%d_mem_cell%d' % (j, i - 1))
net.f(
LstmUnit('lstm%d_layer%d' % (j, i),
net_config["lstm_num_cells"],
weight_filler=filler,
param_names=param_names,
bottoms=bottoms,
tops=[
'lstm%d_hidden%d' % (j, i),
'lstm%d_mem_cell%d' % (j, i)
]))
net.f(
Dropout('dropout%d_%d' % (j, i),
net_config["dropout_ratio"],
bottoms=['lstm%d_hidden%d' % (j, i)]))
net.f(
InnerProduct("ip%d" % i,
net_config['vocab_size'],
bottoms=[
'dropout%d_%d' %
(net_config['lstm_num_stacks'] - 1, i)
],
weight_filler=filler))
if i < net_config['max_len'] - 1:
tar_wordvec = np.array(wordvec_layer[:, :, i + 1, 0]) # 128*38
if phase == 'test':
net.f(Softmax("word_probs%d" % i, bottoms=["ip%d" % i]))
probs = net.blobs["word_probs%d" % i].data
for bi in range(net_config['batch_size']):
if i >= batch_ws_i[bi] and i < batch_stop_i[bi]:
vec = [0] * net_config["vocab_size"]
peakIndex = np.argmax(probs[bi, :])
if peakIndex == net_config['whitespace_symbol']:
batch_stop_i[bi] = i + 1
vec[peakIndex] = 1
tar_wordvec[bi, :] = vec
net.f(NumpyData("target_wordvec%d" % (i + 1), data=tar_wordvec))
bottoms = []
for i in range(net_config['max_len']):
bottoms.append("ip%d" % i)
net.f(Concat('ip_concat', bottoms=bottoms, concat_dim=0))
bottoms = []
for i in range(net_config['max_len']):
bottoms.append('label%d' % i)
net.f(Concat('label_concat', bottoms=bottoms, concat_dim=0))
if deploy:
net.f(Softmax("word_probs", bottoms=["ip_concat"]))
net.f(
SoftmaxWithLoss("word_loss",
bottoms=["ip_concat", "label_concat"],
ignore_label=net_config['zero_symbol']))