def __init__(self, num_layers=12, model_dim=512, num_heads=8, ffn_dim=2048, transformer_layer=12, dropout=0.0):
super(transformer, self).__init__()
self.CLS = nn.Parameter(torch.FloatTensor(6, model_dim))
self.SEP = nn.Parameter(torch.FloatTensor(1, model_dim))
self.enc = encoder(num_layers, model_dim, num_heads, ffn_dim, dropout)
self.linear = nn.Linear(model_dim, 5, bias=False)
# self.sigmoid = nn.Sigmoid()
## fit for Multimodal-Transformer
self.output_linear = nn.Linear(5, 1, bias=False)
def main():
# load dataset
df = pd.read_csv('movies_metadata.csv')
df = df.loc[:, ['title', 'genres', 'overview']]
df = df[pd.notnull(df.overview)]
df = df[pd.notnull(df.title)]
df = df[pd.notnull(df.genres)]
# Training parameters
max_len_desc = 300
max_len_title = 50
max_input_len = max_len_title + max_len_desc
genres_to_be_predicted = [
'Drama', 'Comedy', 'Documentary', 'Science Fiction', 'Romance'
]
num_classes = len(genres_to_be_predicted)
params = {
'GENRES': genres_to_be_predicted,
'VOCABULARY_SIZE': 20000,
'EMBEDDING_DIM': 100,
'MAX_LEN_DESC': max_len_desc,
'MAX_LEN_TITLE': max_len_title,
'INPUT_LEN': max_input_len,
'NUM_DENSE_1': 512,
'NUM_CLASSES': num_classes,
'NUM_EPOCHS': 4,
'BATCH_DIM': 64
}
# init custom classes
p = preprocessor(genres=params['GENRES'])
e = encoder(max_words=params['VOCABULARY_SIZE'],
maxlen_desc=params['MAX_LEN_DESC'],
maxlen_title=params['MAX_LEN_TITLE'])
m = model_classifier()
# prepare data for training
df = p.preprocess(df)
X, y = e.encode(df)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.30,
random_state=1000)
e.save()
# create and train model
model = m.define_model(params)
history = m.train_model(X_train, X_test, y_train, y_test)
# save
m.save_model()
m.save_params()
def lancer():
if var_demo.get() == 0:
if var_mode.get() == "encode":
if var_choix.get() == "fichier":
valeur = entre_file.get()
elif var_choix.get() == "texte":
valeur = var_texte.get()
encoder(var_choix.get(), valeur, var_save.get())
else:
valeur = entre_file.get()
if var_correc.get() == 0:
decoder(valeur, var_save.get(), True)
else:
print("sans correection")
decoder(valeur, var_save.get(), False)
else:
valeur = entre_texte_demo.get()
temps, s_bytes, s_trit1, len_Trit, nb0, s_trit3, s_trit4, s_dna, dicoDebut, dicoReverse, dicoI3, ID, dicoP, dicoIX, dicoIX_dna, dicoFinal, s_dna_final = encoder(
"texte", valeur, var_save.get())
var_afficher = afficherEncodage(valeur, temps, s_bytes, s_trit1,
len_Trit, nb0, s_trit3, s_trit4, s_dna,
dicoDebut, dicoReverse, dicoI3, ID,
dicoP, dicoIX, dicoIX_dna, dicoFinal,
s_dna_final)
fenetre_demo = Tk()
fenetre_demo.title(
"Démonstration de l'encodage d'un texte vers de l'ADN")
barre = Scrollbar(fenetre_demo)
label_demo = Text(fenetre_demo, yscrollcommand=barre.set)
barre.config(command=label_demo.yview)
barre.pack(side="right", fill='y')
label_demo.pack(expand=1, fill="both")
label_demo.insert(0.0, var_afficher)
joindre_salon_ok["seq"]=1
joindre_salon_ok["Type"]=11
joindre_salon_nok={}
joindre_salon_nok["taille"]=125
joindre_salon_nok["seq"]=1
joindre_salon_nok["Type"]=12
ack={}
ack["taille"]=125
ack["seq"]=1
ack["Type"]=63
print("---------- TEST TYPE 1 ----------\n")
print(inscription)
test1=encode.encoder(inscription)
print("\n{0}\n".format(test1))
test1bis=decode.decoder(test1)
print(test1bis)
print("\n---------- TEST TYPE 2 ----------\n")
print(film)
test2=encode.encoder(film)
print("\n{0}\n".format(test2))
test2bis=decode.decoder(test2)
print(test2bis)
print("\n---------- TEST TYPE 3 ----------\n")
print(user)
test3=encode.encoder(user)
print("\n{0}\n".format(test3))
test3bis=decode.decoder(test3)
print(test3bis)
from decode import decoder
from encode import encoder
f1 = open("file1.txt", 'wb')
f2 = open("file2.txt", 'wb')
str1 = encoder('godofwarpauplatinapaunotoba')
str2 = encoder('godofwarpalplatinapaunotoba')
f1.write(str1.encode('utf8'))
f2.write(str2.encode('utf8'))
f1.close()
f2.close()
mem_size = 99
#code = open("/Users/paul/xenotations_first.txt", "r")
def load_from_fime(path):
code = open(path, "r")
c = code.readlines()
clean_code = list(map(lambda x: x.rstrip(), c))
return clean_code
logging.info("INIT STACK")
new_stack = stack()
logging.info("INIT PARSER")
new_decoder = parser()
new_encoder = encoder()
if args.path:
logging.info("LOAD CODE")
clean_code = load_from_fime(args.path)
else:
logging.error("No Input Specification")
exit()
logging.info("INIT MEMORY")
new_mem = pointer(clean_code, mem_size)
new_interp = interpreter(new_decoder, new_stack, new_encoder, new_mem)
logging.info("START EXECUTION")
while True:
from decode import decoder
from encode import encoder
assert decoder(encoder("alodicksiano")) == "alodicksiano"
assert decoder(encoder("alodicksiano")) == "alodicksiano"
assert decoder(encoder("alodicksiano")) == "alodicksiano"
assert decoder(encoder("123456789 123456789 123456789 123456789")
) == "123456789 123456789 123456789 123456789"
Entry(self, textvariable=self.keyheight, width=40).grid(row=5, column=1, sticky='W')
self.keywidth = StringVar()
Label(self, text="照片的宽(pixel)：").grid(row=6, sticky='W', pady=5)
Entry(self, textvariable=self.keywidth, width=40).grid(row=6, column=1, sticky='W')
def xz():
filename = tkinter.filedialog.askopenfilename()
if filename != '':
Label(self, text=filename).grid(row=7, column=1, sticky='w')
self.filename_in=filename
def xz2():
filename = tkinter.filedialog.asksaveasfilename()
if filename != '':
Label(self, text=filename).grid(row=8, column=1, sticky='w')
self.filename_out=filename
Label(self, text="输入文件夹：").grid(row=7, column=0, sticky='W', pady=5)
Button(self, text=" ... ", command=xz).grid(row=7, column=2, sticky='W', padx=2)
Label(self, text="输出文件夹：").grid(row=8, column=0, sticky='W', pady=5)
Button(self, text=" ... ", command=xz2).grid(row=8, column=2, sticky='W', padx=2)
Button(self,text='确定',width=5,height=2, command=self.quit).grid(row=14,column=1,sticky='W',padx=100)
app = Application()
app.mainloop()
en.encoder(app.filename_in,"output.mp4",int(app.interval.get()),int(app.keywidth.get()),int(app.keyheight.get()))