Python mxnet.ndarray.log() Examples
The following are 22
code examples of mxnet.ndarray.log().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
mxnet.ndarray
, or try the search function
.
![](https://www.programcreek.com/common/static/images/search.png)
Example #1
Source File: utils.py From xfer with Apache License 2.0 | 5 votes |
def log_gaussian(x, mean, sigma): return -0.5 * np.log(2.0 * np.pi) - nd.log(sigma) - (x - mean) ** 2 / (2 * sigma ** 2)
Example #2
Source File: kaggle_k_fold_cross_validation.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def get_rmse_log(net, X_train, y_train): """Gets root mse between the logarithms of the prediction and the truth.""" num_train = X_train.shape[0] clipped_preds = nd.clip(net(X_train), 1, float('inf')) return np.sqrt(2 * nd.sum(square_loss( nd.log(clipped_preds), nd.log(y_train))).asscalar() / num_train)
Example #3
Source File: lstm_crf.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def _viterbi_decode(self, feats): backpointers = [] # Initialize the viterbi variables in log space vvars = nd.full((1, self.tagset_size), -10000.) vvars[0, self.tag2idx[START_TAG]] = 0 for feat in feats: bptrs_t = [] # holds the backpointers for this step viterbivars_t = [] # holds the viterbi variables for this step for next_tag in range(self.tagset_size): # next_tag_var[i] holds the viterbi variable for tag i at the # previous step, plus the score of transitioning # from tag i to next_tag. # We don't include the emission scores here because the max # does not depend on them (we add them in below) next_tag_var = vvars + self.transitions[next_tag] best_tag_id = argmax(next_tag_var) bptrs_t.append(best_tag_id) viterbivars_t.append(next_tag_var[0, best_tag_id]) # Now add in the emission scores, and assign vvars to the set # of viterbi variables we just computed vvars = (nd.concat(*viterbivars_t, dim=0) + feat).reshape((1, -1)) backpointers.append(bptrs_t) # Transition to STOP_TAG terminal_var = vvars + self.transitions[self.tag2idx[STOP_TAG]] best_tag_id = argmax(terminal_var) path_score = terminal_var[0, best_tag_id] # Follow the back pointers to decode the best path. best_path = [best_tag_id] for bptrs_t in reversed(backpointers): best_tag_id = bptrs_t[best_tag_id] best_path.append(best_tag_id) # Pop off the start tag (we dont want to return that to the caller) start = best_path.pop() assert start == self.tag2idx[START_TAG] # Sanity check best_path.reverse() return path_score, best_path
Example #4
Source File: lstm_crf.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def _forward_alg(self, feats): # Do the forward algorithm to compute the partition function alphas = [[-10000.] * self.tagset_size] alphas[0][self.tag2idx[START_TAG]] = 0. alphas = nd.array(alphas) # Iterate through the sentence for feat in feats: alphas_t = [] # The forward variables at this timestep for next_tag in range(self.tagset_size): # broadcast the emission score: it is the same regardless of # the previous tag emit_score = feat[next_tag].reshape((1, -1)) # the ith entry of trans_score is the score of transitioning to # next_tag from i trans_score = self.transitions[next_tag].reshape((1, -1)) # The ith entry of next_tag_var is the value for the # edge (i -> next_tag) before we do log-sum-exp next_tag_var = alphas + trans_score + emit_score # The forward variable for this tag is log-sum-exp of all the # scores. alphas_t.append(log_sum_exp(next_tag_var)) alphas = nd.concat(*alphas_t, dim=0).reshape((1, -1)) terminal_var = alphas + self.transitions[self.tag2idx[STOP_TAG]] alpha = log_sum_exp(terminal_var) return alpha
Example #5
Source File: lstm_crf.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def log_sum_exp(vec): max_score = nd.max(vec).asscalar() return nd.log(nd.sum(nd.exp(vec - max_score))) + max_score # Model
Example #6
Source File: lstm_crf.py From SNIPER-mxnet with Apache License 2.0 | 5 votes |
def prepare_sequence(seq, word2idx): return nd.array([word2idx[w] for w in seq]) # Compute log sum exp is numerically more stable than multiplying probabilities
Example #7
Source File: model.py From NER_BiLSTM_CRF_Chinese with Apache License 2.0 | 5 votes |
def log_sum_exp(vec): max_score = nd.max(vec).asscalar() return nd.log(nd.sum(nd.exp(vec - max_score))) + max_score
Example #8
Source File: var.py From xfer with Apache License 2.0 | 5 votes |
def KL(self, other_prob): if not self.is_conjugate(other_prob): raise ValueError("KL cannot be computed in closed form.") if (not len(self.shapes) == len(other_prob.shapes)) or \ (not np.all(np.array([s == o for s, o in zip(self.shapes, other_prob.shapes)]))): raise ValueError("KL cannot be computed: The 2 distributions have different support") raw_params_ext_var_posterior = self._replicate_shared_parameters() sigmas_var_posterior = transform_rhos(raw_params_ext_var_posterior[RHO]) raw_params_ext_prior = other_prob._replicate_shared_parameters() out = 0.0 for ii in range(len(self.shapes)): means_p = raw_params_ext_prior[MEAN][ii] var_p = raw_params_ext_prior["sigma"][ii] ** 2 means_q = raw_params_ext_var_posterior[MEAN][ii] var_q = sigmas_var_posterior[ii] ** 2 inc_means = (means_q - means_p) prec_p = 1.0 / var_p temp = 0.5 * (var_q*prec_p + ((inc_means ** 2) * prec_p) - 1.0 + nd.log(var_p) - nd.log(var_q)) if temp.shape == (1, 1): # If parameters are shared, multiply by the number of variables temp = temp * (self.shapes[ii][0] * self.shapes[ii][1]) out = out + nd.sum(temp) return out
Example #9
Source File: utils.py From xfer with Apache License 2.0 | 5 votes |
def softplus_inv_numpy(x): return np.log(np.exp(x) - 1.)
Example #10
Source File: utils.py From xfer with Apache License 2.0 | 5 votes |
def softplus_inv(x): return nd.log(nd.exp(x) - 1.)
Example #11
Source File: utils.py From xfer with Apache License 2.0 | 5 votes |
def softplus(x): return nd.log(1. + nd.exp(x))
Example #12
Source File: lstm_crf.py From dynamic-training-with-apache-mxnet-on-aws with Apache License 2.0 | 5 votes |
def prepare_sequence(seq, word2idx): return nd.array([word2idx[w] for w in seq]) # Compute log sum exp is numerically more stable than multiplying probabilities
Example #13
Source File: kaggle_k_fold_cross_validation.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def get_rmse_log(net, X_train, y_train): """Gets root mse between the logarithms of the prediction and the truth.""" num_train = X_train.shape[0] clipped_preds = nd.clip(net(X_train), 1, float('inf')) return np.sqrt(2 * nd.sum(square_loss( nd.log(clipped_preds), nd.log(y_train))).asscalar() / num_train)
Example #14
Source File: lstm_crf.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def _viterbi_decode(self, feats): backpointers = [] # Initialize the viterbi variables in log space vvars = nd.full((1, self.tagset_size), -10000.) vvars[0, self.tag2idx[START_TAG]] = 0 for feat in feats: bptrs_t = [] # holds the backpointers for this step viterbivars_t = [] # holds the viterbi variables for this step for next_tag in range(self.tagset_size): # next_tag_var[i] holds the viterbi variable for tag i at the # previous step, plus the score of transitioning # from tag i to next_tag. # We don't include the emission scores here because the max # does not depend on them (we add them in below) next_tag_var = vvars + self.transitions.data()[next_tag] best_tag_id = argmax(next_tag_var) bptrs_t.append(best_tag_id) viterbivars_t.append(next_tag_var[0, best_tag_id]) # Now add in the emission scores, and assign vvars to the set # of viterbi variables we just computed vvars = (nd.concat(*viterbivars_t, dim=0) + feat).reshape((1, -1)) backpointers.append(bptrs_t) # Transition to STOP_TAG terminal_var = vvars + self.transitions.data()[self.tag2idx[STOP_TAG]] best_tag_id = argmax(terminal_var) path_score = terminal_var[0, best_tag_id] # Follow the back pointers to decode the best path. best_path = [best_tag_id] for bptrs_t in reversed(backpointers): best_tag_id = bptrs_t[best_tag_id] best_path.append(best_tag_id) # Pop off the start tag (we dont want to return that to the caller) start = best_path.pop() assert start == self.tag2idx[START_TAG] # Sanity check best_path.reverse() return path_score, best_path
Example #15
Source File: lstm_crf.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def _forward_alg(self, feats): # Do the forward algorithm to compute the partition function alphas = [[-10000.] * self.tagset_size] alphas[0][self.tag2idx[START_TAG]] = 0. alphas = nd.array(alphas) # Iterate through the sentence for feat in feats: alphas_t = [] # The forward variables at this timestep for next_tag in range(self.tagset_size): # broadcast the emission score: it is the same regardless of # the previous tag emit_score = feat[next_tag].reshape((1, -1)) # the ith entry of trans_score is the score of transitioning to # next_tag from i trans_score = self.transitions.data()[next_tag].reshape((1, -1)) # The ith entry of next_tag_var is the value for the # edge (i -> next_tag) before we do log-sum-exp next_tag_var = alphas + trans_score + emit_score # The forward variable for this tag is log-sum-exp of all the # scores. alphas_t.append(log_sum_exp(next_tag_var)) alphas = nd.concat(*alphas_t, dim=0).reshape((1, -1)) terminal_var = alphas + self.transitions.data()[self.tag2idx[STOP_TAG]] alpha = log_sum_exp(terminal_var) return alpha
Example #16
Source File: lstm_crf.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def log_sum_exp(vec): max_score = nd.max(vec).asscalar() return nd.log(nd.sum(nd.exp(vec - max_score))) + max_score # Model
Example #17
Source File: lstm_crf.py From training_results_v0.6 with Apache License 2.0 | 5 votes |
def prepare_sequence(seq, word2idx): return nd.array([word2idx[w] for w in seq]) # Compute log sum exp is numerically more stable than multiplying probabilities
Example #18
Source File: tensor_models.py From dgl with Apache License 2.0 | 5 votes |
def logsigmoid(val): max_elem = nd.maximum(0., -val) z = nd.exp(-max_elem) + nd.exp(-val - max_elem) return -(max_elem + nd.log(z))
Example #19
Source File: kaggle_k_fold_cross_validation.py From dynamic-training-with-apache-mxnet-on-aws with Apache License 2.0 | 5 votes |
def get_rmse_log(net, X_train, y_train): """Gets root mse between the logarithms of the prediction and the truth.""" num_train = X_train.shape[0] clipped_preds = nd.clip(net(X_train), 1, float('inf')) return np.sqrt(2 * nd.sum(square_loss( nd.log(clipped_preds), nd.log(y_train))).asscalar() / num_train)
Example #20
Source File: lstm_crf.py From dynamic-training-with-apache-mxnet-on-aws with Apache License 2.0 | 5 votes |
def _viterbi_decode(self, feats): backpointers = [] # Initialize the viterbi variables in log space vvars = nd.full((1, self.tagset_size), -10000.) vvars[0, self.tag2idx[START_TAG]] = 0 for feat in feats: bptrs_t = [] # holds the backpointers for this step viterbivars_t = [] # holds the viterbi variables for this step for next_tag in range(self.tagset_size): # next_tag_var[i] holds the viterbi variable for tag i at the # previous step, plus the score of transitioning # from tag i to next_tag. # We don't include the emission scores here because the max # does not depend on them (we add them in below) next_tag_var = vvars + self.transitions.data()[next_tag] best_tag_id = argmax(next_tag_var) bptrs_t.append(best_tag_id) viterbivars_t.append(next_tag_var[0, best_tag_id]) # Now add in the emission scores, and assign vvars to the set # of viterbi variables we just computed vvars = (nd.concat(*viterbivars_t, dim=0) + feat).reshape((1, -1)) backpointers.append(bptrs_t) # Transition to STOP_TAG terminal_var = vvars + self.transitions.data()[self.tag2idx[STOP_TAG]] best_tag_id = argmax(terminal_var) path_score = terminal_var[0, best_tag_id] # Follow the back pointers to decode the best path. best_path = [best_tag_id] for bptrs_t in reversed(backpointers): best_tag_id = bptrs_t[best_tag_id] best_path.append(best_tag_id) # Pop off the start tag (we dont want to return that to the caller) start = best_path.pop() assert start == self.tag2idx[START_TAG] # Sanity check best_path.reverse() return path_score, best_path
Example #21
Source File: lstm_crf.py From dynamic-training-with-apache-mxnet-on-aws with Apache License 2.0 | 5 votes |
def _forward_alg(self, feats): # Do the forward algorithm to compute the partition function alphas = [[-10000.] * self.tagset_size] alphas[0][self.tag2idx[START_TAG]] = 0. alphas = nd.array(alphas) # Iterate through the sentence for feat in feats: alphas_t = [] # The forward variables at this timestep for next_tag in range(self.tagset_size): # broadcast the emission score: it is the same regardless of # the previous tag emit_score = feat[next_tag].reshape((1, -1)) # the ith entry of trans_score is the score of transitioning to # next_tag from i trans_score = self.transitions.data()[next_tag].reshape((1, -1)) # The ith entry of next_tag_var is the value for the # edge (i -> next_tag) before we do log-sum-exp next_tag_var = alphas + trans_score + emit_score # The forward variable for this tag is log-sum-exp of all the # scores. alphas_t.append(log_sum_exp(next_tag_var)) alphas = nd.concat(*alphas_t, dim=0).reshape((1, -1)) terminal_var = alphas + self.transitions.data()[self.tag2idx[STOP_TAG]] alpha = log_sum_exp(terminal_var) return alpha
Example #22
Source File: lstm_crf.py From dynamic-training-with-apache-mxnet-on-aws with Apache License 2.0 | 5 votes |
def log_sum_exp(vec): max_score = nd.max(vec).asscalar() return nd.log(nd.sum(nd.exp(vec - max_score))) + max_score # Model