faiss 0.1.5 → 0.2.2

data/vendor/faiss/faiss/IndexBinaryIVF.h

@@ -10,15 +10,13 @@
 #ifndef FAISS_INDEX_BINARY_IVF_H
 #define FAISS_INDEX_BINARY_IVF_H
 
-
 #include <vector>
 
+#include <faiss/Clustering.h>
 #include <faiss/IndexBinary.h>
 #include <faiss/IndexIVF.h>
-#include <faiss/Clustering.h>
 #include <faiss/utils/Heap.h>
 
-
 namespace faiss {
 
 struct BinaryInvertedListScanner;
@@ -34,11 +32,11 @@ struct BinaryInvertedListScanner;
  */
 struct IndexBinaryIVF : IndexBinary {
     /// Access to the actual data
-    InvertedLists *invlists;
+    InvertedLists* invlists;
     bool own_invlists;
 
-    size_t nprobe;            ///< number of probes at query time
-    size_t max_codes;         ///< max nb of codes to visit to do a query
+    size_t nprobe;    ///< number of probes at query time
+    size_t max_codes; ///< max nb of codes to visit to do a query
 
     /** Select between using a heap or counting to select the k smallest values
      * when scanning inverted lists.
@@ -48,20 +46,20 @@ struct IndexBinaryIVF : IndexBinary {
     /// map for direct access to the elements. Enables reconstruct().
     DirectMap direct_map;
 
-    IndexBinary *quantizer;   ///< quantizer that maps vectors to inverted lists
-    size_t nlist;             ///< number of possible key values
+    IndexBinary* quantizer; ///< quantizer that maps vectors to inverted lists
+    size_t nlist;           ///< number of possible key values
 
-    bool own_fields;          ///< whether object owns the quantizer
+    bool own_fields; ///< whether object owns the quantizer
 
     ClusteringParameters cp; ///< to override default clustering params
-    Index *clustering_index; ///< to override index used during clustering
+    Index* clustering_index; ///< to override index used during clustering
 
     /** The Inverted file takes a quantizer (an IndexBinary) on input,
      * which implements the function mapping a vector to a list
      * identifier. The pointer is borrowed: the quantizer should not
      * be deleted while the IndexBinaryIVF is in use.
      */
-    IndexBinaryIVF(IndexBinary *quantizer, size_t d, size_t nlist);
+    IndexBinaryIVF(IndexBinary* quantizer, size_t d, size_t nlist);
 
     IndexBinaryIVF();
 
@@ -70,15 +68,23 @@ struct IndexBinaryIVF : IndexBinary {
     void reset() override;
 
     /// Trains the quantizer
-    void train(idx_t n, const uint8_t *x) override;
+    void train(idx_t n, const uint8_t* x) override;
 
-    void add(idx_t n, const uint8_t *x) override;
+    void add(idx_t n, const uint8_t* x) override;
 
-    void add_with_ids(idx_t n, const uint8_t *x, const idx_t *xids) override;
+    void add_with_ids(idx_t n, const uint8_t* x, const idx_t* xids) override;
 
-    /// same as add_with_ids, with precomputed coarse quantizer
-    void add_core (idx_t n, const uint8_t * x, const idx_t *xids,
-                   const idx_t *precomputed_idx);
+    /** Implementation of vector addition where the vector assignments are
+     * predefined.
+     *
+     * @param precomputed_idx    quantization indices for the input vectors
+     * (size n)
+     */
+    void add_core(
+            idx_t n,
+            const uint8_t* x,
+            const idx_t* xids,
+            const idx_t* precomputed_idx);
 
     /** Search a set of vectors, that are pre-quantized by the IVF
      *  quantizer. Fill in the corresponding heaps with the query
@@ -97,25 +103,43 @@ struct IndexBinaryIVF : IndexBinary {
      *                     instead of ids (used for reranking).
      * @param params used to override the object's search parameters
      */
-    void search_preassigned(idx_t n, const uint8_t *x, idx_t k,
-                            const idx_t *assign,
-                            const int32_t *centroid_dis,
-                            int32_t *distances, idx_t *labels,
-                            bool store_pairs,
-                            const IVFSearchParameters *params=nullptr
-                            ) const;
-
-    virtual BinaryInvertedListScanner *get_InvertedListScanner (
-                                         bool store_pairs=false) const;
+    void search_preassigned(
+            idx_t n,
+            const uint8_t* x,
+            idx_t k,
+            const idx_t* assign,
+            const int32_t* centroid_dis,
+            int32_t* distances,
+            idx_t* labels,
+            bool store_pairs,
+            const IVFSearchParameters* params = nullptr) const;
+
+    virtual BinaryInvertedListScanner* get_InvertedListScanner(
+            bool store_pairs = false) const;
 
     /** assign the vectors, then call search_preassign */
-    void search(idx_t n, const uint8_t *x, idx_t k,
-                int32_t *distances, idx_t *labels) const override;
-
-    void range_search(idx_t n, const uint8_t *x, int radius,
-                      RangeSearchResult *result) const override;
-
-    void reconstruct(idx_t key, uint8_t *recons) const override;
+    void search(
+            idx_t n,
+            const uint8_t* x,
+            idx_t k,
+            int32_t* distances,
+            idx_t* labels) const override;
+
+    void range_search(
+            idx_t n,
+            const uint8_t* x,
+            int radius,
+            RangeSearchResult* result) const override;
+
+    void range_search_preassigned(
+            idx_t n,
+            const uint8_t* x,
+            int radius,
+            const idx_t* assign,
+            const int32_t* centroid_dis,
+            RangeSearchResult* result) const;
+
+    void reconstruct(idx_t key, uint8_t* recons) const override;
 
     /** Reconstruct a subset of the indexed vectors.
      *
@@ -126,7 +150,7 @@ struct IndexBinaryIVF : IndexBinary {
      * @param ni     nb of vectors to reconstruct
      * @param recons output array of reconstructed vectors, size ni * d / 8
      */
-    void reconstruct_n(idx_t i0, idx_t ni, uint8_t *recons) const override;
+    void reconstruct_n(idx_t i0, idx_t ni, uint8_t* recons) const override;
 
     /** Similar to search, but also reconstructs the stored vectors (or an
      * approximation in the case of lossy coding) for the search results.
@@ -137,9 +161,13 @@ struct IndexBinaryIVF : IndexBinary {
      *
      * @param recons      reconstructed vectors size (n, k, d / 8)
      */
-    void search_and_reconstruct(idx_t n, const uint8_t *x, idx_t k,
-                                int32_t *distances, idx_t *labels,
-                                uint8_t *recons) const override;
+    void search_and_reconstruct(
+            idx_t n,
+            const uint8_t* x,
+            idx_t k,
+            int32_t* distances,
+            idx_t* labels,
+            uint8_t* recons) const override;
 
     /** Reconstruct a vector given the location in terms of (inv list index +
      * inv list offset) instead of the id.
@@ -148,9 +176,10 @@ struct IndexBinaryIVF : IndexBinary {
      * the inv list offset is computed by search_preassigned() with
      * `store_pairs` set.
      */
-    virtual void reconstruct_from_offset(idx_t list_no, idx_t offset,
-                                         uint8_t* recons) const;
-
+    virtual void reconstruct_from_offset(
+            idx_t list_no,
+            idx_t offset,
+            uint8_t* recons) const;
 
     /// Dataset manipulation functions
     size_t remove_ids(const IDSelector& sel) override;
@@ -160,34 +189,33 @@ struct IndexBinaryIVF : IndexBinary {
      * sequential ids, this would be this->ntotal */
     virtual void merge_from(IndexBinaryIVF& other, idx_t add_id);
 
-    size_t get_list_size(size_t list_no) const
-    { return invlists->list_size(list_no); }
+    size_t get_list_size(size_t list_no) const {
+        return invlists->list_size(list_no);
+    }
 
     /** intialize a direct map
      *
      * @param new_maintain_direct_map    if true, create a direct map,
      *                                   else clear it
      */
-    void make_direct_map(bool new_maintain_direct_map=true);
+    void make_direct_map(bool new_maintain_direct_map = true);
 
-    void set_direct_map_type (DirectMap::Type type);
+    void set_direct_map_type(DirectMap::Type type);
 
-    void replace_invlists(InvertedLists *il, bool own=false);
+    void replace_invlists(InvertedLists* il, bool own = false);
 };
 
-
 struct BinaryInvertedListScanner {
-
     using idx_t = Index::idx_t;
 
     /// from now on we handle this query.
-    virtual void set_query (const uint8_t *query_vector) = 0;
+    virtual void set_query(const uint8_t* query_vector) = 0;
 
     /// following codes come from this inverted list
-    virtual void set_list (idx_t list_no, uint8_t coarse_dis) = 0;
+    virtual void set_list(idx_t list_no, uint8_t coarse_dis) = 0;
 
     /// compute a single query-to-code distance
-    virtual uint32_t distance_to_code (const uint8_t *code) const = 0;
+    virtual uint32_t distance_to_code(const uint8_t* code) const = 0;
 
     /** compute the distances to codes. (distances, labels) should be
      * organized as a min- or max-heap
@@ -199,23 +227,24 @@ struct BinaryInvertedListScanner {
      * @param labels     heap labels (size k)
      * @param k          heap size
      */
-    virtual size_t scan_codes (size_t n,
-                               const uint8_t *codes,
-                               const idx_t *ids,
-                               int32_t *distances, idx_t *labels,
-                               size_t k) const = 0;
-
-    virtual void scan_codes_range (size_t n,
-                                   const uint8_t *codes,
-                                   const idx_t *ids,
-                                   int radius,
-                                   RangeQueryResult &result) const = 0;
-
-    virtual ~BinaryInvertedListScanner () {}
-
+    virtual size_t scan_codes(
+            size_t n,
+            const uint8_t* codes,
+            const idx_t* ids,
+            int32_t* distances,
+            idx_t* labels,
+            size_t k) const = 0;
+
+    virtual void scan_codes_range(
+            size_t n,
+            const uint8_t* codes,
+            const idx_t* ids,
+            int radius,
+            RangeQueryResult& result) const = 0;
+
+    virtual ~BinaryInvertedListScanner() {}
 };
 
+} // namespace faiss
 
-}  // namespace faiss
-
-#endif  // FAISS_INDEX_BINARY_IVF_H
+#endif // FAISS_INDEX_BINARY_IVF_H

data/vendor/faiss/faiss/IndexFlat.cpp

@@ -9,108 +9,96 @@
 
 #include <faiss/IndexFlat.h>
 
-#include <cstring>
+#include <faiss/impl/AuxIndexStructures.h>
+#include <faiss/impl/FaissAssert.h>
+#include <faiss/utils/Heap.h>
 #include <faiss/utils/distances.h>
 #include <faiss/utils/extra_distances.h>
 #include <faiss/utils/utils.h>
-#include <faiss/utils/Heap.h>
-#include <faiss/impl/FaissAssert.h>
-#include <faiss/impl/AuxIndexStructures.h>
-
+#include <cstring>
 
 namespace faiss {
 
-IndexFlat::IndexFlat (idx_t d, MetricType metric):
-            Index(d, metric)
-{
-}
-
+IndexFlat::IndexFlat(idx_t d, MetricType metric) : Index(d, metric) {}
 
-
-void IndexFlat::add (idx_t n, const float *x) {
+void IndexFlat::add(idx_t n, const float* x) {
     xb.insert(xb.end(), x, x + n * d);
     ntotal += n;
 }
 
-
 void IndexFlat::reset() {
     xb.clear();
     ntotal = 0;
 }
 
+void IndexFlat::search(
+        idx_t n,
+        const float* x,
+        idx_t k,
+        float* distances,
+        idx_t* labels) const {
+    FAISS_THROW_IF_NOT(k > 0);
 
-void IndexFlat::search (idx_t n, const float *x, idx_t k,
-                               float *distances, idx_t *labels) const
-{
     // we see the distances and labels as heaps
 
     if (metric_type == METRIC_INNER_PRODUCT) {
-        float_minheap_array_t res = {
-            size_t(n), size_t(k), labels, distances};
-        knn_inner_product (x, xb.data(), d, n, ntotal, &res);
+        float_minheap_array_t res = {size_t(n), size_t(k), labels, distances};
+        knn_inner_product(x, xb.data(), d, n, ntotal, &res);
     } else if (metric_type == METRIC_L2) {
-        float_maxheap_array_t res = {
-            size_t(n), size_t(k), labels, distances};
-        knn_L2sqr (x, xb.data(), d, n, ntotal, &res);
+        float_maxheap_array_t res = {size_t(n), size_t(k), labels, distances};
+        knn_L2sqr(x, xb.data(), d, n, ntotal, &res);
     } else {
-        float_maxheap_array_t res = {
-            size_t(n), size_t(k), labels, distances};
-        knn_extra_metrics (x, xb.data(), d, n, ntotal,
-                           metric_type, metric_arg,
-                           &res);
+        float_maxheap_array_t res = {size_t(n), size_t(k), labels, distances};
+        knn_extra_metrics(
+                x, xb.data(), d, n, ntotal, metric_type, metric_arg, &res);
     }
 }
 
-void IndexFlat::range_search (idx_t n, const float *x, float radius,
-                              RangeSearchResult *result) const
-{
+void IndexFlat::range_search(
+        idx_t n,
+        const float* x,
+        float radius,
+        RangeSearchResult* result) const {
     switch (metric_type) {
-    case METRIC_INNER_PRODUCT:
-        range_search_inner_product (x, xb.data(), d, n, ntotal,
-                                    radius, result);
-        break;
-    case METRIC_L2:
-        range_search_L2sqr (x, xb.data(), d, n, ntotal, radius, result);
-        break;
-    default:
-        FAISS_THROW_MSG("metric type not supported");
+        case METRIC_INNER_PRODUCT:
+            range_search_inner_product(
+                    x, xb.data(), d, n, ntotal, radius, result);
+            break;
+        case METRIC_L2:
+            range_search_L2sqr(x, xb.data(), d, n, ntotal, radius, result);
+            break;
+        default:
+            FAISS_THROW_MSG("metric type not supported");
     }
 }
 
-
-void IndexFlat::compute_distance_subset (
-            idx_t n,
-            const float *x,
-            idx_t k,
-            float *distances,
-            const idx_t *labels) const
-{
+void IndexFlat::compute_distance_subset(
+        idx_t n,
+        const float* x,
+        idx_t k,
+        float* distances,
+        const idx_t* labels) const {
     switch (metric_type) {
         case METRIC_INNER_PRODUCT:
-            fvec_inner_products_by_idx (
-                 distances,
-                 x, xb.data(), labels, d, n, k);
+            fvec_inner_products_by_idx(
+                    distances, x, xb.data(), labels, d, n, k);
             break;
         case METRIC_L2:
-            fvec_L2sqr_by_idx (
-                 distances,
-                 x, xb.data(), labels, d, n, k);
+            fvec_L2sqr_by_idx(distances, x, xb.data(), labels, d, n, k);
             break;
         default:
             FAISS_THROW_MSG("metric type not supported");
     }
-
 }
 
-size_t IndexFlat::remove_ids (const IDSelector & sel)
-{
+size_t IndexFlat::remove_ids(const IDSelector& sel) {
     idx_t j = 0;
     for (idx_t i = 0; i < ntotal; i++) {
-        if (sel.is_member (i)) {
+        if (sel.is_member(i)) {
             // should be removed
         } else {
             if (i > j) {
-                memmove (&xb[d * j], &xb[d * i], sizeof(xb[0]) * d);
+                memmove(&xb[d * j], &xb[d * i], sizeof(xb[0]) * d);
             }
             j++;
         }
@@ -118,23 +106,21 @@ size_t IndexFlat::remove_ids (const IDSelector & sel)
     size_t nremove = ntotal - j;
     if (nremove > 0) {
         ntotal = j;
-        xb.resize (ntotal * d);
+        xb.resize(ntotal * d);
     }
     return nremove;
 }
 
-
 namespace {
 
-
 struct FlatL2Dis : DistanceComputer {
     size_t d;
     Index::idx_t nb;
-    const float *q;
-    const float *b;
+    const float* q;
+    const float* b;
     size_t ndis;
 
-    float operator () (idx_t i) override {
+    float operator()(idx_t i) override {
         ndis++;
         return fvec_L2sqr(q, b + i * d, d);
     }
@@ -143,14 +129,14 @@ struct FlatL2Dis : DistanceComputer {
         return fvec_L2sqr(b + j * d, b + i * d, d);
     }
 
-    explicit FlatL2Dis(const IndexFlat& storage, const float *q = nullptr)
-        : d(storage.d),
-          nb(storage.ntotal),
-          q(q),
-          b(storage.xb.data()),
-          ndis(0) {}
+    explicit FlatL2Dis(const IndexFlat& storage, const float* q = nullptr)
+            : d(storage.d),
+              nb(storage.ntotal),
+              q(q),
+              b(storage.xb.data()),
+              ndis(0) {}
 
-    void set_query(const float *x) override {
+    void set_query(const float* x) override {
         q = x;
     }
 };
@@ -158,128 +144,106 @@ struct FlatL2Dis : DistanceComputer {
 struct FlatIPDis : DistanceComputer {
     size_t d;
     Index::idx_t nb;
-    const float *q;
-    const float *b;
+    const float* q;
+    const float* b;
     size_t ndis;
 
-    float operator () (idx_t i) override {
+    float operator()(idx_t i) override {
         ndis++;
-        return fvec_inner_product (q, b + i * d, d);
+        return fvec_inner_product(q, b + i * d, d);
     }
 
     float symmetric_dis(idx_t i, idx_t j) override {
-        return fvec_inner_product (b + j * d, b + i * d, d);
+        return fvec_inner_product(b + j * d, b + i * d, d);
     }
 
-    explicit FlatIPDis(const IndexFlat& storage, const float *q = nullptr)
-        : d(storage.d),
-          nb(storage.ntotal),
-          q(q),
-          b(storage.xb.data()),
-          ndis(0) {}
+    explicit FlatIPDis(const IndexFlat& storage, const float* q = nullptr)
+            : d(storage.d),
+              nb(storage.ntotal),
+              q(q),
+              b(storage.xb.data()),
+              ndis(0) {}
 
-    void set_query(const float *x) override {
+    void set_query(const float* x) override {
         q = x;
     }
 };
 
+} // namespace
 
-
-
-}  // namespace
-
-
-DistanceComputer * IndexFlat::get_distance_computer() const {
+DistanceComputer* IndexFlat::get_distance_computer() const {
     if (metric_type == METRIC_L2) {
         return new FlatL2Dis(*this);
     } else if (metric_type == METRIC_INNER_PRODUCT) {
         return new FlatIPDis(*this);
     } else {
-        return get_extra_distance_computer (d, metric_type, metric_arg,
-                                            ntotal, xb.data());
+        return get_extra_distance_computer(
+                d, metric_type, metric_arg, ntotal, xb.data());
     }
 }
 
-
-void IndexFlat::reconstruct (idx_t key, float * recons) const
-{
-    memcpy (recons, &(xb[key * d]), sizeof(*recons) * d);
+void IndexFlat::reconstruct(idx_t key, float* recons) const {
+    memcpy(recons, &(xb[key * d]), sizeof(*recons) * d);
 }
 
-
 /* The standalone codec interface */
-size_t IndexFlat::sa_code_size () const
-{
+size_t IndexFlat::sa_code_size() const {
     return sizeof(float) * d;
 }
 
-void IndexFlat::sa_encode (idx_t n, const float *x, uint8_t *bytes) const
-{
-    memcpy (bytes, x, sizeof(float) * d * n);
+void IndexFlat::sa_encode(idx_t n, const float* x, uint8_t* bytes) const {
+    memcpy(bytes, x, sizeof(float) * d * n);
 }
 
-void IndexFlat::sa_decode (idx_t n, const uint8_t *bytes, float *x) const
-{
-    memcpy (x, bytes, sizeof(float) * d * n);
+void IndexFlat::sa_decode(idx_t n, const uint8_t* bytes, float* x) const {
+    memcpy(x, bytes, sizeof(float) * d * n);
 }
 
-
-
-
-
-
 /***************************************************
  * IndexFlat1D
  ***************************************************/
 
-
-IndexFlat1D::IndexFlat1D (bool continuous_update):
-    IndexFlatL2 (1),
-    continuous_update (continuous_update)
-{
-}
+IndexFlat1D::IndexFlat1D(bool continuous_update)
+        : IndexFlatL2(1), continuous_update(continuous_update) {}
 
 /// if not continuous_update, call this between the last add and
 /// the first search
-void IndexFlat1D::update_permutation ()
-{
-    perm.resize (ntotal);
+void IndexFlat1D::update_permutation() {
+    perm.resize(ntotal);
     if (ntotal < 1000000) {
-        fvec_argsort (ntotal, xb.data(), (size_t*)perm.data());
+        fvec_argsort(ntotal, xb.data(), (size_t*)perm.data());
     } else {
-        fvec_argsort_parallel (ntotal, xb.data(), (size_t*)perm.data());
+        fvec_argsort_parallel(ntotal, xb.data(), (size_t*)perm.data());
     }
 }
 
-void IndexFlat1D::add (idx_t n, const float *x)
-{
-    IndexFlatL2::add (n, x);
+void IndexFlat1D::add(idx_t n, const float* x) {
+    IndexFlatL2::add(n, x);
     if (continuous_update)
         update_permutation();
 }
 
-void IndexFlat1D::reset()
-{
+void IndexFlat1D::reset() {
     IndexFlatL2::reset();
     perm.clear();
 }
 
-void IndexFlat1D::search (
-            idx_t n,
-            const float *x,
-            idx_t k,
-            float *distances,
-            idx_t *labels) const
-{
-    FAISS_THROW_IF_NOT_MSG (perm.size() == ntotal,
-                    "Call update_permutation before search");
+void IndexFlat1D::search(
+        idx_t n,
+        const float* x,
+        idx_t k,
+        float* distances,
+        idx_t* labels) const {
+    FAISS_THROW_IF_NOT(k > 0);
+
+    FAISS_THROW_IF_NOT_MSG(
+            perm.size() == ntotal, "Call update_permutation before search");
 
 #pragma omp parallel for
     for (idx_t i = 0; i < n; i++) {
-
         float q = x[i]; // query
-        float *D = distances + i * k;
-        idx_t *I = labels + i * k;
+        float* D = distances + i * k;
+        idx_t* I = labels + i * k;
 
         // binary search
         idx_t i0 = 0, i1 = ntotal;
@@ -297,8 +261,10 @@ void IndexFlat1D::search (
 
         while (i0 + 1 < i1) {
             idx_t imed = (i0 + i1) / 2;
-            if (xb[perm[imed]] <= q) i0 = imed;
-            else                    i1 = imed;
+            if (xb[perm[imed]] <= q)
+                i0 = imed;
+            else
+                i1 = imed;
         }
 
         // query is between xb[perm[i0]] and xb[perm[i1]]
@@ -311,13 +277,19 @@ void IndexFlat1D::search (
             if (q - xleft < xright - q) {
                 D[wp] = q - xleft;
                 I[wp] = perm[i0];
-                i0--; wp++;
-                if (i0 < 0) { goto finish_right; }
+                i0--;
+                wp++;
+                if (i0 < 0) {
+                    goto finish_right;
+                }
             } else {
                 D[wp] = xright - q;
                 I[wp] = perm[i1];
-                i1++; wp++;
-                if (i1 >= ntotal) { goto finish_left; }
+                i1++;
+                wp++;
+                if (i1 >= ntotal) {
+                    goto finish_left;
+                }
             }
         }
         goto done;
@@ -350,11 +322,8 @@ void IndexFlat1D::search (
             }
             wp++;
         }
-    done:  ;
+    done:;
     }
-
 }
 
-
-
 } // namespace faiss