def val_fn(imgs, target, caps):
# We only keep the first caps for now
caps = [cap[0] for cap in caps]
caps = text_utils.pad_to_the_max(caps)
res = self.val_fn(caps, target)
return res
def train(self, imgs, target, caps):
#We only keep the first caps for now
caps = [cap[np.random.choice(len(cap))] for cap in caps]
caps = text_utils.pad_to_the_max(caps)
res = self.train_fn(caps, target)
return res
def val_fn(imgs, target, caps):
caps = [cap[np.random.choice(len(cap))] for cap in caps]
caps = text_utils.pad_to_the_max(caps)
noise_size = self.options['noise_size']
noise = np.random.normal(size=(len(imgs), noise_size))
imgs = utils.put_in_middle(np.array(imgs), 0.5)
res = self.generate_sample_fn(caps, imgs, noise)
return 0, res[0]
def train(self, imgs, target, caps):
caps = [cap[np.random.choice(len(cap))] for cap in caps]
caps = text_utils.pad_to_the_max(caps)
[disc_loss] = self.train_discriminator_fn(caps, target)
gen_loss = self.train_generator_fn(caps, target)
return disc_loss, gen_loss
def train(self, imgs, target, caps):
noise_size = self.options['noise_size']
noise = np.random.normal(size=(len(imgs), noise_size))
caps = [cap[np.random.choice(len(cap))] for cap in caps]
caps = text_utils.pad_to_the_max(caps)
imgs = utils.put_in_middle(np.array(imgs), 0.5)
[disc_loss] = self.train_discriminator_fn(caps, imgs, noise, target)
gen_loss = self.train_generator_fn(caps, imgs, noise, target)
return disc_loss, gen_loss
def train(self, imgs, target, caps): # imgs = bagel, target = tim-bit, caps = captions
caps = [cap[np.random.choice(len(cap))] for cap in caps]
caps = text_utils.pad_to_the_max(caps)
[disc_loss] = self.train_discriminator_fn(caps, target) # inherited from class->GAN i.e captions ,
gen_loss = self.train_generator_fn(caps, target) # inherited from class->GAN
use_wgan = self.options['use_wgan']
if use_wgan:
discriminator_params_values = lasagne.layers.get_all_param_values(self.discriminator, trainable=True)
clamped_weights = [np.clip(w, -0.05, 0.05) for w in discriminator_params_values]
lasagne.layers.set_all_param_values(self.discriminator, clamped_weights, trainable=True)
return disc_loss, gen_loss
def val_fn(imgs, target, caps):
caps = [cap[np.random.choice(len(cap))] for cap in caps]
caps = text_utils.pad_to_the_max(caps)
res = self.generate_sample_fn(caps)
return 0, res[0]