Esempio n. 1
0
def save_dataset(X,y,file_path):
    print "saving extended dataset..."
    print "saving %d images..." % X.shape[0]

    f = open(file_path,"w")
    z = zip(X,y)
    np.random.shuffle(z)
    t = Timer(X.shape[0])
    t.start()
    for X, y in z:
        f.write("%d,\"%s\"\n" % (np.int(np.argmax(y)), " ".join([str(i) for i in X.flatten().astype(int)])))
        t.print_update(1)
    f.close()
    print "it took",seconds_to_string(t.over())
Esempio n. 2
0
def apply_transformations(X,y,transformations):
    
    nb = X.shape[0]
    for name, settings in transformations.items():
        nb = nb + nb * settings.get('ratio',2)

    print "A dataset of approximately %d images will we produced.." % nb
       
    if nb*257*2**20/(0.+2**30*33423)*4 > 4.0:
        a = ""
        while a not in ["y","n"]:
            a = raw_input("This may use more than %dG of RAM. Do you want to continue? (y/n) " % (nb*257*2**20/(0.+2**30*33423)*4))
            if a=='n':
                sys.exit(0)

    t = Timer(nb)
    t.start()

    tX = X[:]
    ty = y[:]
    noise_transformations = []
    for noise_t in ['noise','sharpen','denoise']:
        if noise_t in transformations:
            settings = transformations.pop(noise_t)
            nX, ny = generate(transformations_dict[noise_t],settings,X,y,t=t)
            tX = np.vstack((tX,nX))
            ty = np.vstack((ty,ny))

    X = tX
    y = ty
    for name, settings in transformations.items():
        nX, ny = generate(transformations_dict[name],settings,X,y,t=t)
        X = np.vstack((X,nX))
        y = np.vstack((y,ny))

    print "it took",seconds_to_string(t.over())

    return X, y
Esempio n. 3
0
    start = time.time()
    print "ceci est un  : ",lmi.p((u'ceci',u'est',u'un'))
    print "It tooks ",time.time()-start,"s"
    start = time.time()
    print "Voici une phrase plutôt simple",lmi.p((u'Voici',u'une',u'phrase',u'plutôt',u'simple'))
    print "It tooks ",time.time()-start,"s"
    start = time.time()
    print "Phrase formé mal avec qwetrqq inconnu mot",lmi.p((u'Phrase',u'formé',u'mal',u'avec',u'qwetrqq',u'inconnu',u'mot'))
    print "It tooks ",time.time()-start,"s"

#    sys.exit(0)

    tmps = 0
    tmpss = 0
    t = Timer(ngram.len(2))
    t.start()
    # need 3-grams for this
    for i, ng in enumerate(ngram.getgrams(2)):
        tmps = 0
        for j, nng in enumerate(ngram.contains(tuple(list(ng)+[""]),(0,-1))):
            tmps += lmi.p(nng)

        tmpss += tmps
        update = t.update(1)
        if update:
            sys.stderr.write("time remaining : "+seconds_to_string(update)+"\n")
        print i,tmpss
        print "tmp %i : %f" % (i,tmpss/(0.+i+1))

    print "final : ",tmpss/(0.+ngram.len(2))