def check_gradien_on_captioning_rnn():
"""
perform numeric gradient checking on the CaptioningRNN class; you should see errors
around the order of e-6 or less.
"""
np.random.seed(231)
batch_size = 2
timesteps = 3
input_dim = 4
wordvec_dim = 5
hidden_dim = 6
word_to_idx = {'<NULL>': 0, 'cat': 2, 'dog': 3}
vocab_size = len(word_to_idx)
captions = np.random.randint(vocab_size, size=(batch_size, timesteps))
features = np.random.randn(batch_size, input_dim)
model = CaptioningRNN(word_to_idx,
input_dim=input_dim,
wordvec_dim=wordvec_dim,
hidden_dim=hidden_dim,
cell_type='rnn',
dtype=np.float64)
loss, grads = model.loss(features, captions)
for param_name in sorted(grads):
f = lambda _: model.loss(features, captions)[0]
param_grad_num = eval_numerical_gradient(f,
model.params[param_name],
verbose=False,
h=1e-6)
e = rel_error(param_grad_num, grads[param_name])
print('%s relative error: %e' % (param_name, e))
def check_lstm_captioning_model():
"""You should see a difference on the order of e-10 or less."""
N, D, W, H = 10, 20, 30, 40
word_to_idx = {'<NULL>': 0, 'cat': 2, 'dog': 3}
V = len(word_to_idx)
T = 13
model = CaptioningRNN(word_to_idx,
input_dim=D,
wordvec_dim=W,
hidden_dim=H,
cell_type='lstm',
dtype=np.float64)
# Set all model parameters to fixed values
for k, v in model.params.items():
model.params[k] = np.linspace(-1.4, 1.3, num=v.size).reshape(*v.shape)
features = np.linspace(-0.5, 1.7, num=N * D).reshape(N, D)
captions = (np.arange(N * T) % V).reshape(N, T)
loss, grads = model.loss(features, captions)
expected_loss = 9.82445935443
print('loss: ', loss)
print('expected loss: ', expected_loss)
print('difference: ', abs(loss - expected_loss))
def check_rnn_for_image_captioning():
"""
Now that you have implemented the necessary layers, you can combine them to build an
image captioning model. Open the file cs231n/classifiers/rnn.py and look at the
CaptioningRNN class.
Implement the forward and backward pass of the model in the loss function. For now
you only need to implement the case where cell_type='rnn' for vanialla RNNs; you will
implement the LSTM case later. After doing so, run the following to check your
forward pass using a small test case; you should see error on the order of e-10 or less.
"""
N, D, W, H = 10, 20, 30, 40
word_to_idx = {'<NULL>': 0, 'cat': 2, 'dog': 3}
V = len(word_to_idx)
T = 13
model = CaptioningRNN(word_to_idx,
input_dim=D,
wordvec_dim=W,
hidden_dim=H,
cell_type='rnn',
dtype=np.float64)
# Set all model parameters to fixed values
for k, v in model.params.items():
model.params[k] = np.linspace(-1.4, 1.3, num=v.size).reshape(*v.shape)
features = np.linspace(-1.5, 0.3, num=(N * D)).reshape(N, D)
captions = (np.arange(N * T) % V).reshape(N, T)
loss, grads = model.loss(features, captions)
expected_loss = 9.83235591003
print('loss: ', loss)
print('expected loss: ', expected_loss)
print('difference: ', abs(loss - expected_loss))
model = CaptioningRNN(word_to_idx,
input_dim=D,
wordvec_dim=W,
hidden_dim=H,
cell_type='lstm',
dtype=np.float64)
# Set all model parameters to fixed values
for k, v in model.params.iteritems():
model.params[k] = np.linspace(-1.4, 1.3, num=v.size).reshape(*v.shape)
features = np.linspace(-0.5, 1.7, num=N*D).reshape(N, D)
captions = (np.arange(N * T) % V).reshape(N, T)
loss, grads = model.loss(features, captions)
expected_loss = 9.82445935443
print 'loss: ', loss
print 'expected loss: ', expected_loss
print 'difference: ', abs(loss - expected_loss)
small_data = load_coco_data(max_train=50)
small_lstm_model = CaptioningRNN(
cell_type='lstm',
word_to_idx=data['word_to_idx'],
input_dim=data['train_features'].shape[1],
hidden_dim=512,
wordvec_dim=256,
dtype=np.float32,
model = CaptioningRNN(word_to_idx,
input_dim=D,
wordvec_dim=W,
hidden_dim=H,
cell_type='rnn',
dtype=np.float64)
# Set all model parameters to fixed values
for k, v in model.params.items():
model.params[k] = np.linspace(-1.4, 1.3, num=v.size).reshape(*v.shape)
features = np.linspace(-1.5, 0.3, num=(N * D)).reshape(N, D)
captions = (np.arange(N * T) % V).reshape(N, T)
loss, grads = model.loss(features, captions)
expected_loss = 9.83235591003
print('loss: ', loss)
print('expected loss: ', expected_loss)
print('difference: ', abs(loss - expected_loss))
# Run the following cell to perform numeric gradient checking on the `CaptioningRNN` class; you should errors around `5e-6` or less.
# In[ ]:
np.random.seed(231)
batch_size = 2
timesteps = 3
model = CaptioningRNN(word_to_idx,
input_dim=D,
wordvec_dim=W,
hidden_dim=H,
cell_type='rnn',
dtype=np.float64)
# Set all model parameters to fixed values
for k, v in model.params.iteritems():
model.params[k] = np.linspace(-1.4, 1.3, num=v.size).reshape(*v.shape)
features = np.linspace(-1.5, 0.3, num=(N * D)).reshape(N, D)
captions = (np.arange(N * T) % V).reshape(N, T)
loss, grads = model.loss(features, captions)
expected_loss = 9.83235591003
print 'loss: ', loss
print 'expected loss: ', expected_loss
print 'difference: ', abs(loss - expected_loss)
batch_size = 2
timesteps = 3
input_dim = 4
wordvec_dim = 5
hidden_dim = 6
word_to_idx = {'<NULL>': 0, 'cat': 2, 'dog': 3}
vocab_size = len(word_to_idx)
captions = np.random.randint(vocab_size, size=(batch_size, timesteps))
