fast.ai 深度学习笔记（三）（1）

@property
def model(self): 
    return self.models.model

m=learn.model; m
'''
EmbeddingDotBias (
  (u): Embedding(671, 50)
  (i): Embedding(9066, 50)
  (ub): Embedding(671, 1)
  (ib): Embedding(9066, 1)
)
'''

movie_bias = to_np(m.ib(V(topMovieIdx)))

def load_model(m, p): 
    m.load_state_dict(torch.load(p, map_location=lambda storage, loc: storage))

movie_ratings = [(b[0], movie_names[i]) for i,b in zip(topMovies,movie_bias)]

sorted(movie_ratings, key=lambda o: o[0])[:15]
'''
[(-0.96070349, 'Battlefield Earth (2000)'),
 (-0.76858485, 'Speed 2: Cruise Control (1997)'),
 (-0.73675376, 'Wild Wild West (1999)'),
 (-0.73655486, 'Anaconda (1997)'),
 ...]
'''
sorted(movie_ratings, key=itemgetter(0))[:15]

sorted(movie_ratings, key=lambda o: o[0], reverse=True)[:15]
'''
[(1.3070084, 'Shawshank Redemption, The (1994)'),
 (1.1196285, 'Godfather, The (1972)'),
 (1.0844109, 'Usual Suspects, The (1995)'),
 (0.96578616, "Schindler's List (1993)"),
 ...]
'''

movie_emb = to_np(m.i(V(topMovieIdx)))
movie_emb.shape*(3000, 50)
from sklearn.decomposition import PCA
pca = PCA(n_components=3)
movie_pca = pca.fit(movie_emb.T).components_
movie_pca.shape
'''
(3, 3000)
'''

fac0 = movie_pca[0] 
movie_comp = [(f, movie_names[i]) for f,i in zip(fac0, topMovies)]
sorted(movie_comp, key=itemgetter(0), reverse=True)[:10]
sorted(movie_comp, key=itemgetter(0), reverse=True)[:10]
'''
[(0.06748189, 'Independence Day (a.k.a. ID4) (1996)'),
 (0.061572548, 'Police Academy 4: Citizens on Patrol (1987)'),
 (0.061050549, 'Waterworld (1995)'),
 (0.057877172, 'Rocky V (1990)'),
 ...
]
'''
sorted(movie_comp, key=itemgetter(0))[:10]
'''
[(-0.078433245, 'Godfather: Part II, The (1974)'),
 (-0.072180331, 'Fargo (1996)'),
 (-0.071351372, 'Pulp Fiction (1994)'),
 (-0.068537779, 'Goodfellas (1990)'),
 ...
]
'''

fac1 = movie_pca[1]
movie_comp = [(f, movie_names[i]) for f,i in zip(fac1, topMovies)]
sorted(movie_comp, key=itemgetter(0), reverse=True)[:10]
'''
[(0.058975246, 'Bonfire of the Vanities (1990)'),
 (0.055992026, '2001: A Space Odyssey (1968)'),
 (0.054682467, 'Tank Girl (1995)'),
 (0.054429606, 'Purple Rose of Cairo, The (1985)'),
 ...]*sorted(movie_comp, key=itemgetter(0))[:10]*[(-0.1064609, 'Lord of the Rings: The Return of the King, The (2003)'),
 (-0.090635143, 'Aladdin (1992)'),
 (-0.089208141, 'Star Wars: Episode V - The Empire Strikes Back (1980)'),
 (-0.088854566, 'Star Wars: Episode IV - A New Hope (1977)'),
 ...]
'''

idxs = np.random.choice(len(topMovies), 50, replace=False)
X = fac0[idxs]
Y = fac1[idxs]
plt.figure(figsize=(15,15))
plt.scatter(X, Y)
for i, x, y in zip(topMovies[idxs], X, Y):
    plt.text(x,y,movie_names[i], color=np.random.rand(3)*0.7, fontsize=11)
plt.show()

# Here we generate some fake data
def lin(a,b,x): 
    return a*x+b
def gen_fake_data(n, a, b):
    x = s = np.random.uniform(0,1,n) 
    y = lin(a,b,x) + 0.1 * np.random.normal(0,3,n)
    return x, y
x, y = gen_fake_data(50, 3., 8.)
plt.scatter(x,y, s=8); plt.xlabel("x"); plt.ylabel("y");

def mse(y_hat, y): 
    return ((y_hat - y) ** 2).mean()
def mse_loss(a, b, x, y): 
    return mse(lin(a,b,x), y)

x, y = gen_fake_data(10000, 3., 8.) 
x,y = V(x),V(y)

a = V(np.random.randn(1), requires_grad=True) 
b = V(np.random.randn(1), requires_grad=True)

learning_rate = 1e-3
for t in range(10000):
    # Forward pass: compute predicted y using operations on Variables
    loss = mse_loss(a,b,x,y)
    if t % 1000 == 0: print(loss.data[0])
    # Computes the gradient of loss with respect to all Variables with requires_grad=True.
    # After this call a.grad and b.grad will be Variables holding the gradient
    # of the loss with respect to a and b respectively
    loss.backward()
    # Update a and b using gradient descent; a.data and b.data are Tensors,
    # a.grad and b.grad are Variables and a.grad.data and b.grad.data are Tensors
    a.data -= learning_rate * a.grad.data
    b.data -= learning_rate * b.grad.data
    # Zero the gradients
    a.grad.data.zero_()
    b.grad.data.zero_()

x, y = gen_fake_data(50, 3., 8.)
a_guess,b_guess = -1., 1.
mse_loss(y, a_guess, b_guess, x)
lr=0.01 
def upd():
     global a_guess, b_guess
     y_pred = lin(a_guess, b_guess, x)
     dydb = 2 * (y_pred - y)
     dyda = x*dydb
     a_guess -= lr*dyda.mean()
     b_guess -= lr*dydb.mean()

text = open(f'{PATH}nietzsche.txt').read()
print(text[:400])
'''
'PREFACE\n\n\nSUPPOSING that Truth is a woman--what then? Is there not ground\nfor suspecting that all philosophers, in so far as they have been\ndogmatists, have failed to understand women--that the terrible\nseriousness and clumsy importunity with which they have usually paid\ntheir addresses to Truth, have been unskilled and unseemly methods for\nwinning a woman? Certainly she has never allowed herself '
'''
chars = sorted(list(set(text))) 
vocab_size = len(chars)+1 
print('total chars:', vocab_size)
'''
total chars: 85
'''

chars.insert(0, "\0")

char_indices = dict((c, i) for i, c in enumerate(chars))
indices_char = dict((i, c) for i, c in enumerate(chars))

idx = [char_indices[c] for c in text]
idx[:10]
'''
[40, 42, 29, 30, 25, 27, 29, 1, 1, 1]
'''

cs = 3 
c1_dat = [idx[i]   for i in range(0, len(idx)-cs, cs)]
c2_dat = [idx[i+1] for i in range(0, len(idx)-cs, cs)]
c3_dat = [idx[i+2] for i in range(0, len(idx)-cs, cs)]
c4_dat = [idx[i+3] for i in range(0, len(idx)-cs, cs)]

x1 = np.stack(c1_dat) 
x2 = np.stack(c2_dat) 
x3 = np.stack(c3_dat) 
y = np.stack(c4_dat)

n_hidden = 256 
n_fac = 42

class Char3Model(nn.Module):
     def __init__(self, vocab_size, n_fac):
         super().__init__()
         self.e = nn.Embedding(vocab_size, n_fac)
         self.l_in = nn.Linear(n_fac, n_hidden)
         self.l_hidden = nn.Linear(n_hidden, n_hidden)
         self.l_out = nn.Linear(n_hidden, vocab_size) 
     
     def forward(self, c1, c2, c3):
         
         in1 = F.relu(self.l_in(self.e(c1)))
         in2 = F.relu(self.l_in(self.e(c2)))
         in3 = F.relu(self.l_in(self.e(c3)))
         h = V(torch.zeros(in1.size()).cuda())
         h = F.tanh(self.l_hidden(h+in1))
         h = F.tanh(self.l_hidden(h+in2))
         h = F.tanh(self.l_hidden(h+in3))
         return F.log_softmax(self.l_out(h))

md = ColumnarModelData.from_arrays('.', [-1], np.stack([x1,x2,x3], axis=1), y, bs=512)

m = Char3Model(vocab_size, n_fac).cuda()

it = iter(md.trn_dl)
*xs,yt = next(it)
t = m(*V(xs))

opt = optim.Adam(m.parameters(), 1e-2)

fit(m, md, 1, opt, F.nll_loss)
set_lrs(opt, 0.001)
fit(m, md, 1, opt, F.nll_loss)

def get_next(inp):
     idxs = T(np.array([char_indices[c] for c in inp]))
     p = m(*VV(idxs))
     i = np.argmax(to_np(p))
     return chars[i]

get_next('y. ')
'''
'T'
'''
get_next('ppl')
'''
'e'
'''
get_next(' th')
'''
'e'
'''
get_next('and')
'''
' '
'''