[go: nahoru, domu]
Skip to content

Commit

Permalink
none
Browse files Browse the repository at this point in the history
  • Loading branch information
@CC-cyf
CC-cyf committed Sep 19, 2019
1 parent 20c129a commit 1c18160
Show file tree
Hide file tree
Showing 9 changed files with 1,922 additions and 0 deletions.
23 changes: 23 additions & 0 deletions w2v/InitNet.c
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
void InitNet() {
long long a, b;
unsigned long long next_random = 1;
a = posix_memalign((void **)&syn0, 128, (long long)vocab_size * layer1_size * sizeof(real));
if (syn0 == NULL) {printf("Memory allocation failed\n"); exit(1);}
if (hs) {
a = posix_memalign((void **)&syn1, 128, (long long)vocab_size * layer1_size * sizeof(real));
if (syn1 == NULL) {printf("Memory allocation failed\n"); exit(1);}
for (a = 0; a < vocab_size; a++) for (b = 0; b < layer1_size; b++)
syn1[a * layer1_size + b] = 0;
}
if (negative>0) {
a = posix_memalign((void **)&syn1neg, 128, (long long)vocab_size * layer1_size * sizeof(real));
if (syn1neg == NULL) {printf("Memory allocation failed\n"); exit(1);}
for (a = 0; a < vocab_size; a++) for (b = 0; b < layer1_size; b++)
syn1neg[a * layer1_size + b] = 0;
}
for (a = 0; a < vocab_size; a++) for (b = 0; b < layer1_size; b++) {
next_random = next_random * (unsigned long long)25214903917 + 11;
syn0[a * layer1_size + b] = (((next_random & 0xFFFF) / (real)65536) - 0.5) / layer1_size;
}
CreateBinaryTree();
}
70 changes: 70 additions & 0 deletions w2v/TrainModel.c
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
void TrainModel() {
long a, b, c, d;
FILE *fo;
pthread_t *pt = (pthread_t *)malloc(num_threads * sizeof(pthread_t));
printf("Starting training using file %s\n", train_file);
starting_alpha = alpha;
if (read_vocab_file[0] != 0) ReadVocab(); else LearnVocabFromTrainFile();
if (save_vocab_file[0] != 0) SaveVocab();
if (output_file[0] == 0) return;
InitNet();
if (negative > 0) InitUnigramTable();
start = clock();
for (a = 0; a < num_threads; a++) pthread_create(&pt[a], NULL, TrainModelThread, (void *)a);
for (a = 0; a < num_threads; a++) pthread_join(pt[a], NULL);
fo = fopen(output_file, "wb");
if (classes == 0) {
// Save the word vectors
fprintf(fo, "%lld %lld\n", vocab_size, layer1_size);
for (a = 0; a < vocab_size; a++) {
fprintf(fo, "%s ", vocab[a].word);
if (binary) for (b = 0; b < layer1_size; b++) fwrite(&syn0[a * layer1_size + b], sizeof(real), 1, fo);
else for (b = 0; b < layer1_size; b++) fprintf(fo, "%lf ", syn0[a * layer1_size + b]);
fprintf(fo, "\n");
}
} else {
// Run K-means on the word vectors
int clcn = classes, iter = 10, closeid;
int *centcn = (int *)malloc(classes * sizeof(int));
int *cl = (int *)calloc(vocab_size, sizeof(int));
real closev, x;
real *cent = (real *)calloc(classes * layer1_size, sizeof(real));
for (a = 0; a < vocab_size; a++) cl[a] = a % clcn;
for (a = 0; a < iter; a++) {
for (b = 0; b < clcn * layer1_size; b++) cent[b] = 0;
for (b = 0; b < clcn; b++) centcn[b] = 1;
for (c = 0; c < vocab_size; c++) {
for (d = 0; d < layer1_size; d++) cent[layer1_size * cl[c] + d] += syn0[c * layer1_size + d];
centcn[cl[c]]++;
}
for (b = 0; b < clcn; b++) {
closev = 0;
for (c = 0; c < layer1_size; c++) {
cent[layer1_size * b + c] /= centcn[b];
closev += cent[layer1_size * b + c] * cent[layer1_size * b + c];
}
closev = sqrt(closev);
for (c = 0; c < layer1_size; c++) cent[layer1_size * b + c] /= closev;
}
for (c = 0; c < vocab_size; c++) {
closev = -10;
closeid = 0;
for (d = 0; d < clcn; d++) {
x = 0;
for (b = 0; b < layer1_size; b++) x += cent[layer1_size * d + b] * syn0[c * layer1_size + b];
if (x > closev) {
closev = x;
closeid = d;
}
}
cl[c] = closeid;
}
}
// Save the K-means classes
for (a = 0; a < vocab_size; a++) fprintf(fo, "%s %d\n", vocab[a].word, cl[a]);
free(centcn);
free(cent);
free(cl);
}
fclose(fo);
}
183 changes: 183 additions & 0 deletions w2v/TrainModelThread.c
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,183 @@

void *TrainModelThread(void *id) {
long long a, b, d, cw, word, last_word, sentence_length = 0, sentence_position = 0;
long long word_count = 0, last_word_count = 0, sen[MAX_SENTENCE_LENGTH + 1];
long long l1, l2, c, target, label, local_iter = iter;
unsigned long long next_random = (long long)id;
char eof = 0;
real f, g;
clock_t now;
real *neu1 = (real *)calloc(layer1_size, sizeof(real));
real *neu1e = (real *)calloc(layer1_size, sizeof(real));
FILE *fi = fopen(train_file, "rb");
fseek(fi, file_size / (long long)num_threads * (long long)id, SEEK_SET);
while (1) {
if (word_count - last_word_count > 10000) {
word_count_actual += word_count - last_word_count;
last_word_count = word_count;
if ((debug_mode > 1)) {
now=clock();
printf("%cAlpha: %f Progress: %.2f%% Words/thread/sec: %.2fk ", 13, alpha,
word_count_actual / (real)(iter * train_words + 1) * 100,
word_count_actual / ((real)(now - start + 1) / (real)CLOCKS_PER_SEC * 1000));
fflush(stdout);
}
alpha = starting_alpha * (1 - word_count_actual / (real)(iter * train_words + 1));
if (alpha < starting_alpha * 0.0001) alpha = starting_alpha * 0.0001;
}
if (sentence_length == 0) {
while (1) {
word = ReadWordIndex(fi, &eof);
if (eof) break;
if (word == -1) continue;
word_count++;
if (word == 0) break;
// The subsampling randomly discards frequent words while keeping the ranking same
if (sample > 0) {
real ran = (sqrt(vocab[word].cn / (sample * train_words)) + 1) * (sample * train_words) / vocab[word].cn;
next_random = next_random * (unsigned long long)25214903917 + 11;
if (ran < (next_random & 0xFFFF) / (real)65536) continue;
}
sen[sentence_length] = word;
sentence_length++;
if (sentence_length >= MAX_SENTENCE_LENGTH) break;
}
sentence_position = 0;
}
if (eof || (word_count > train_words / num_threads)) {
word_count_actual += word_count - last_word_count;
local_iter--;
if (local_iter == 0) break;
word_count = 0;
last_word_count = 0;
sentence_length = 0;
fseek(fi, file_size / (long long)num_threads * (long long)id, SEEK_SET);
continue;
}
word = sen[sentence_position];
if (word == -1) continue;
for (c = 0; c < layer1_size; c++) neu1[c] = 0;
for (c = 0; c < layer1_size; c++) neu1e[c] = 0;
next_random = next_random * (unsigned long long)25214903917 + 11;
b = next_random % window;
if (cbow) { //train the cbow architecture
// in -> hidden
cw = 0;
for (a = b; a < window * 2 + 1 - b; a++) if (a != window) {
c = sentence_position - window + a;
if (c < 0) continue;
if (c >= sentence_length) continue;
last_word = sen[c];
if (last_word == -1) continue;
for (c = 0; c < layer1_size; c++) neu1[c] += syn0[c + last_word * layer1_size];
cw++;
}
if (cw) {
for (c = 0; c < layer1_size; c++) neu1[c] /= cw;
if (hs) for (d = 0; d < vocab[word].codelen; d++) {
f = 0;
l2 = vocab[word].point[d] * layer1_size;
// Propagate hidden -> output
for (c = 0; c < layer1_size; c++) f += neu1[c] * syn1[c + l2];
if (f <= -MAX_EXP) continue;
else if (f >= MAX_EXP) continue;
else f = expTable[(int)((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))];
// 'g' is the gradient multiplied by the learning rate
g = (1 - vocab[word].code[d] - f) * alpha;
// Propagate errors output -> hidden
for (c = 0; c < layer1_size; c++) neu1e[c] += g * syn1[c + l2];
// Learn weights hidden -> output
for (c = 0; c < layer1_size; c++) syn1[c + l2] += g * neu1[c];
}
// NEGATIVE SAMPLING
if (negative > 0) for (d = 0; d < negative + 1; d++) {
if (d == 0) {
target = word;
label = 1;
} else {
next_random = next_random * (unsigned long long)25214903917 + 11;
target = table[(next_random >> 16) % table_size];
if (target == 0) target = next_random % (vocab_size - 1) + 1;
if (target == word) continue;
label = 0;
}
l2 = target * layer1_size;
f = 0;
for (c = 0; c < layer1_size; c++) f += neu1[c] * syn1neg[c + l2];
if (f > MAX_EXP) g = (label - 1) * alpha;
else if (f < -MAX_EXP) g = (label - 0) * alpha;
else g = (label - expTable[(int)((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))]) * alpha;
for (c = 0; c < layer1_size; c++) neu1e[c] += g * syn1neg[c + l2];
for (c = 0; c < layer1_size; c++) syn1neg[c + l2] += g * neu1[c];
}
// hidden -> in
for (a = b; a < window * 2 + 1 - b; a++) if (a != window) {
c = sentence_position - window + a;
if (c < 0) continue;
if (c >= sentence_length) continue;
last_word = sen[c];
if (last_word == -1) continue;
for (c = 0; c < layer1_size; c++) syn0[c + last_word * layer1_size] += neu1e[c];
}
}
} else { //train skip-gram
for (a = b; a < window * 2 + 1 - b; a++) if (a != window) {
c = sentence_position - window + a;
if (c < 0) continue;
if (c >= sentence_length) continue;
last_word = sen[c];
if (last_word == -1) continue;
l1 = last_word * layer1_size;
for (c = 0; c < layer1_size; c++) neu1e[c] = 0;
// HIERARCHICAL SOFTMAX
if (hs) for (d = 0; d < vocab[word].codelen; d++) {
f = 0;
l2 = vocab[word].point[d] * layer1_size;
// Propagate hidden -> output
for (c = 0; c < layer1_size; c++) f += syn0[c + l1] * syn1[c + l2];
if (f <= -MAX_EXP) continue;
else if (f >= MAX_EXP) continue;
else f = expTable[(int)((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))];
// 'g' is the gradient multiplied by the learning rate
g = (1 - vocab[word].code[d] - f) * alpha;
// Propagate errors output -> hidden
for (c = 0; c < layer1_size; c++) neu1e[c] += g * syn1[c + l2];
// Learn weights hidden -> output
for (c = 0; c < layer1_size; c++) syn1[c + l2] += g * syn0[c + l1];
}
// NEGATIVE SAMPLING
if (negative > 0) for (d = 0; d < negative + 1; d++) {
if (d == 0) {
target = word;
label = 1;
} else {
next_random = next_random * (unsigned long long)25214903917 + 11;
target = table[(next_random >> 16) % table_size];
if (target == 0) target = next_random % (vocab_size - 1) + 1;
if (target == word) continue;
label = 0;
}
l2 = target * layer1_size;
f = 0;
for (c = 0; c < layer1_size; c++) f += syn0[c + l1] * syn1neg[c + l2];
if (f > MAX_EXP) g = (label - 1) * alpha;
else if (f < -MAX_EXP) g = (label - 0) * alpha;
else g = (label - expTable[(int)((f + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2))]) * alpha;
for (c = 0; c < layer1_size; c++) neu1e[c] += g * syn1neg[c + l2];
for (c = 0; c < layer1_size; c++) syn1neg[c + l2] += g * syn0[c + l1];
}
// Learn weights input -> hidden
for (c = 0; c < layer1_size; c++) syn0[c + l1] += neu1e[c];
}
}
sentence_position++;
if (sentence_position >= sentence_length) {
sentence_length = 0;
continue;
}
}
fclose(fi);
free(neu1);
free(neu1e);
pthread_exit(NULL);
}
Loading

0 comments on commit 1c18160

Please sign in to comment.