nextrec 0.2.1__py3-none-any.whl → 0.2.2__py3-none-any.whl

nextrec-0.2.2.dist-info/RECORD

@@ -0,0 +1,53 @@
+nextrec/__init__.py,sha256=CvocnY2uBp0cjNkhrT6ogw0q2bN9s1GNp754FLO-7lo,1117
+nextrec/__version__.py,sha256=m6kyaNpwBcP1XYcqrelX2oS3PJuOnElOcRdBa9pEb8c,22
+nextrec/basic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nextrec/basic/activation.py,sha256=9EfYmwE0brTSKwx_0FIGQ_rybFBT9n_G-UWA7NAhMsI,2804
+nextrec/basic/callback.py,sha256=qkq3k8rP0g4BW2C3FSCdVt_CyCcJwJ-rUXjhT2p4LP8,1035
+nextrec/basic/features.py,sha256=qNrGm74R6K7dw-kJdA2Sbp_Tjb_oDOo1a2JCfyOaYtw,3957
+nextrec/basic/layers.py,sha256=mDNApSlPkmPSnIPj3BDHfDEjviLybWuSGrh61Zog2uk,38290
+nextrec/basic/loggers.py,sha256=x8lzyyK-uqBN5XGOm1Cb33dmfc2bl114n6QeFTtE54k,3752
+nextrec/basic/metrics.py,sha256=w8tGe2tTbBNz9A1TNZF3jSpxcNC6QvFP5I0lWRd0Nw4,20398
+nextrec/basic/model.py,sha256=r3yWw2RMk-_Ap9hXKzyp7-TKpSaPtqRzpABaJkCrT9M,66336
+nextrec/basic/session.py,sha256=2kogEjgKAN1_ygelbwoqOs187BAcUnDTqXG1w_Pgb9I,4791
+nextrec/data/__init__.py,sha256=SOD64AkPykwKgm0CT89aDcHeiiDQlOOAkLDsAjYiqAM,814
+nextrec/data/data_utils.py,sha256=vGZ378YM_JQXO9npRB7JqojJx1ovjbJCWI-7lQJkicA,6298
+nextrec/data/dataloader.py,sha256=T0i2f5KMohd-hkgTPBNCPy9xaziRrUwYd01oI8GIEI8,20450
+nextrec/data/preprocessor.py,sha256=LzuBeBHcp6nnm7oaHDV-SZNk92ev8xjCj4r-thakRMw,42288
+nextrec/loss/__init__.py,sha256=t-wkqxcu5wdYlrb67-CxX9aOGom0CpMJK8Fe8KGDSEE,857
+nextrec/loss/listwise.py,sha256=LcYIPf6PGRtjV_AoWaAyp3rse904S2MghE5t032I07I,5628
+nextrec/loss/loss_utils.py,sha256=LnTkpMTS2bhbq4Lsjf3AUn1uBaOg1TaH5VO2R8hwARc,5324
+nextrec/loss/pairwise.py,sha256=RuQuTE-EkLaHQvT9m0CTAXxneTnVQLF1Pi9wblEClI8,3289
+nextrec/loss/pointwise.py,sha256=6QveizdohzQTxAoBKTVSoCBpp-fy3JC8vCjImXa7jL0,7157
+nextrec/models/generative/hstu.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nextrec/models/generative/tiger.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+nextrec/models/match/__init__.py,sha256=ASZB5abqKPhDbk8NErNNNa0DHuWpsVxvUtyEn5XMx6Y,215
+nextrec/models/match/dssm.py,sha256=e0hUqNLJVwTRVz4F4EiO8KLOOprKRBDtI4ID6Y1Tc60,8232
+nextrec/models/match/dssm_v2.py,sha256=ywtqTy3YN9ke_7kzcDp7Fhtldw9RJz6yfewxALJb6Z0,7189
+nextrec/models/match/mind.py,sha256=XSUDlZ-V95JXHHBDUl5sz99SaVuQKDvf3TArVjwUexs,9417
+nextrec/models/match/sdm.py,sha256=96yfMQ6arP6JRhAkDTGEjlBiTteznMykrDV_3jqvvVk,10920
+nextrec/models/match/youtube_dnn.py,sha256=pnrz9LYu65Fj4neOriFF45B5k2-yYiiREtQICxxYXZ0,7546
+nextrec/models/multi_task/esmm.py,sha256=E9B6TlpnPUeyldTofyFg4B7SKByyxbiW2fUGHLOryO4,4883
+nextrec/models/multi_task/mmoe.py,sha256=zhQr43Vfz7Kgi6B9pKPmaenp_38a_D7w4VvlpwCyF6Y,6165
+nextrec/models/multi_task/ple.py,sha256=otP6oLgzrJhwkLFItzNE-AtIPouObDkafRvWzTCxfNo,11335
+nextrec/models/multi_task/share_bottom.py,sha256=LL5HBVlvvBzHV2fLBRQMGIwpqmlxILTgU4c51XyTCo4,4517
+nextrec/models/ranking/__init__.py,sha256=-qe34zQEVwmxeTPGYCa6gbql9quT8DwB7-buHfA7Iig,428
+nextrec/models/ranking/afm.py,sha256=r9m1nEnc0m5d4pMtOxRMqOaXaBNCEkjJBFB-5wSHeFA,4540
+nextrec/models/ranking/autoint.py,sha256=GYzRynjn6Csq4b3qYIFWxLQ4Yl57_OQBeF2IY0Zhr9Q,5654
+nextrec/models/ranking/dcn.py,sha256=dUV5GbHypBGc9vVozk6aGYfIXq23c0deX-HFnIhZueg,4208
+nextrec/models/ranking/deepfm.py,sha256=y28yJxF__TZR3O1G2ufKZVtBRLgCgmlXWqvPgLzwm3U,3510
+nextrec/models/ranking/dien.py,sha256=E6s9TDwQfGSwtzzh8hG2F5gwgVxzVZPcptYvHLNzOLA,8475
+nextrec/models/ranking/din.py,sha256=j5tkT5k91CbsMlMr5vJOySrcY2_rFGxmEgJJ0McW7-Q,7196
+nextrec/models/ranking/fibinet.py,sha256=X6CbQbritvq5jql_Tvs4bn_tRla2zpWPplftZv8k6f0,4853
+nextrec/models/ranking/fm.py,sha256=3Qx_Fgowegr6UPQtEeTmHtOrbWzkvqH94ZTjOqRLu-E,2961
+nextrec/models/ranking/masknet.py,sha256=Bu0mZl2vKqcGnqCuUjPHjPRd1f-cDTeVwFj8Y_6v3C8,4639
+nextrec/models/ranking/pnn.py,sha256=5RxIKdxD0XcGq-b_QDdwGRwk6b_5BQjyMvCw3Ibv2Kk,4957
+nextrec/models/ranking/widedeep.py,sha256=b6ctElaZPv5WSYDA4piYUBo3je0eJpWpWECwcuWavM4,3716
+nextrec/models/ranking/xdeepfm.py,sha256=I00J5tfE4tPluqeW-qrNtE4V_9fC7-rgFvA0Fxqka7o,4274
+nextrec/utils/__init__.py,sha256=6x3OZbqks2gtgJd00y_-Y8QiAT42x5t14ARHQ-ULQDo,350
+nextrec/utils/embedding.py,sha256=yxYSdFx0cJITh3Gf-K4SdhwRtKGcI0jOsyBgZ0NLa_c,465
+nextrec/utils/initializer.py,sha256=ffYOs5QuIns_d_-5e40iNtg6s1ftgREJN-ueq_NbDQE,1647
+nextrec/utils/optimizer.py,sha256=85ifoy2IQgjPHOqLqr1ho7XBGE_0ry1yEB9efS6C2lM,2446
+nextrec-0.2.2.dist-info/METADATA,sha256=lAhtUMV17TjgvjOuKZph_it7O02Ld1gKA0mc0k44oNQ,11425
+nextrec-0.2.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+nextrec-0.2.2.dist-info/licenses/LICENSE,sha256=2fQfVKeafywkni7MYHyClC6RGGC3laLTXCNBx-ubtp0,1064
+nextrec-0.2.2.dist-info/RECORD,,

nextrec/loss/match_losses.py

@@ -1,293 +0,0 @@
-"""
-Loss functions for matching tasks
-
-Date: create on 13/11/2025
-Author: Yang Zhou,zyaztec@gmail.com
-"""
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from typing import Optional
-
-
-class BPRLoss(nn.Module):
-    def __init__(self, reduction: str = 'mean'):
-        super(BPRLoss, self).__init__()
-        self.reduction = reduction
-    
-    def forward(self, pos_score: torch.Tensor, neg_score: torch.Tensor) -> torch.Tensor:
-        if neg_score.dim() == 2:
-            pos_score = pos_score.unsqueeze(1)  # [batch_size, 1]
-            diff = pos_score - neg_score  # [batch_size, num_neg]
-            loss = -torch.log(torch.sigmoid(diff) + 1e-8)
-            if self.reduction == 'mean':
-                return loss.mean()
-            elif self.reduction == 'sum':
-                return loss.sum()
-            else:
-                return loss
-        else:
-            diff = pos_score - neg_score
-            loss = -torch.log(torch.sigmoid(diff) + 1e-8)
-            if self.reduction == 'mean':
-                return loss.mean()
-            elif self.reduction == 'sum':
-                return loss.sum()
-            else:
-                return loss
-
-
-class HingeLoss(nn.Module): 
-    def __init__(self, margin: float = 1.0, reduction: str = 'mean'):
-        super(HingeLoss, self).__init__()
-        self.margin = margin
-        self.reduction = reduction
-    
-    def forward(self, pos_score: torch.Tensor, neg_score: torch.Tensor) -> torch.Tensor:
-        if neg_score.dim() == 2:
-            pos_score = pos_score.unsqueeze(1)  # [batch_size, 1]
-        
-        diff = pos_score - neg_score
-        loss = torch.clamp(self.margin - diff, min=0)
-        
-        if self.reduction == 'mean':
-            return loss.mean()
-        elif self.reduction == 'sum':
-            return loss.sum()
-        else:
-            return loss
-
-
-class TripletLoss(nn.Module):
-    def __init__(self, margin: float = 1.0, reduction: str = 'mean', distance: str = 'euclidean'):
-        super(TripletLoss, self).__init__()
-        self.margin = margin
-        self.reduction = reduction
-        self.distance = distance
-    
-    def forward(self, anchor: torch.Tensor, positive: torch.Tensor, negative: torch.Tensor) -> torch.Tensor:
-        if self.distance == 'euclidean':
-            pos_dist = torch.sum((anchor - positive) ** 2, dim=-1)
-            
-            if negative.dim() == 3:
-                anchor_expanded = anchor.unsqueeze(1)  # [batch_size, 1, dim]
-                neg_dist = torch.sum((anchor_expanded - negative) ** 2, dim=-1)  # [batch_size, num_neg]
-            else:
-                neg_dist = torch.sum((anchor - negative) ** 2, dim=-1)
-            
-            if neg_dist.dim() == 2:
-                pos_dist = pos_dist.unsqueeze(1)  # [batch_size, 1]
-        
-        elif self.distance == 'cosine':
-            pos_dist = 1 - F.cosine_similarity(anchor, positive, dim=-1)
-            
-            if negative.dim() == 3:
-                anchor_expanded = anchor.unsqueeze(1)  # [batch_size, 1, dim]
-                neg_dist = 1 - F.cosine_similarity(anchor_expanded, negative, dim=-1)
-            else:
-                neg_dist = 1 - F.cosine_similarity(anchor, negative, dim=-1)
-            
-            if neg_dist.dim() == 2:
-                pos_dist = pos_dist.unsqueeze(1)
-        else:
-            raise ValueError(f"Unsupported distance: {self.distance}")
-        
-        loss = torch.clamp(pos_dist - neg_dist + self.margin, min=0)
-        
-        if self.reduction == 'mean':
-            return loss.mean()
-        elif self.reduction == 'sum':
-            return loss.sum()
-        else:
-            return loss
-
-
-class SampledSoftmaxLoss(nn.Module):
-    def __init__(self, reduction: str = 'mean'):
-        super(SampledSoftmaxLoss, self).__init__()
-        self.reduction = reduction
-    
-    def forward(self, pos_logits: torch.Tensor, neg_logits: torch.Tensor) -> torch.Tensor:
-        pos_logits = pos_logits.unsqueeze(1)  # [batch_size, 1]
-        all_logits = torch.cat([pos_logits, neg_logits], dim=1)  # [batch_size, 1 + num_neg]
-        targets = torch.zeros(all_logits.size(0), dtype=torch.long, device=all_logits.device)
-        loss = F.cross_entropy(all_logits, targets, reduction=self.reduction)
-        
-        return loss
-
-
-class CosineContrastiveLoss(nn.Module):
-    def __init__(self, margin: float = 0.5, reduction: str = 'mean'):
-        super(CosineContrastiveLoss, self).__init__()
-        self.margin = margin
-        self.reduction = reduction
-    
-    def forward(self, user_emb: torch.Tensor, item_emb: torch.Tensor, labels: torch.Tensor) -> torch.Tensor:
-        similarity = F.cosine_similarity(user_emb, item_emb, dim=-1)
-        pos_loss = (1 - similarity) * labels
-
-        neg_loss = torch.clamp(similarity - self.margin, min=0) * (1 - labels)
-        
-        loss = pos_loss + neg_loss
-        
-        if self.reduction == 'mean':
-            return loss.mean()
-        elif self.reduction == 'sum':
-            return loss.sum()
-        else:
-            return loss
-
-
-class InfoNCELoss(nn.Module):
-    def __init__(self, temperature: float = 0.07, reduction: str = 'mean'):
-        super(InfoNCELoss, self).__init__()
-        self.temperature = temperature
-        self.reduction = reduction
-    
-    def forward(self, query: torch.Tensor, pos_key: torch.Tensor, neg_keys: torch.Tensor) -> torch.Tensor:
-        pos_sim = torch.sum(query * pos_key, dim=-1) / self.temperature  # [batch_size]
-        pos_sim = pos_sim.unsqueeze(1)  # [batch_size, 1]
-        query_expanded = query.unsqueeze(1)  # [batch_size, 1, dim]
-        neg_sim = torch.sum(query_expanded * neg_keys, dim=-1) / self.temperature  # [batch_size, num_neg]
-        logits = torch.cat([pos_sim, neg_sim], dim=1)  # [batch_size, 1 + num_neg]
-        labels = torch.zeros(logits.size(0), dtype=torch.long, device=logits.device)
-
-        loss = F.cross_entropy(logits, labels, reduction=self.reduction)
-        
-        return loss
-
-
-class ListNetLoss(nn.Module):
-    """
-    ListNet loss using top-1 probability distribution
-    Reference: Cao et al. Learning to Rank: From Pairwise Approach to Listwise Approach (ICML 2007)
-    """
-    def __init__(self, temperature: float = 1.0, reduction: str = 'mean'):
-        super(ListNetLoss, self).__init__()
-        self.temperature = temperature
-        self.reduction = reduction
-    
-    def forward(self, scores: torch.Tensor, labels: torch.Tensor) -> torch.Tensor:
-        # Convert scores and labels to probability distributions
-        pred_probs = F.softmax(scores / self.temperature, dim=1)
-        true_probs = F.softmax(labels / self.temperature, dim=1)
-        
-        # Cross entropy between two distributions
-        loss = -torch.sum(true_probs * torch.log(pred_probs + 1e-10), dim=1)
-        
-        if self.reduction == 'mean':
-            return loss.mean()
-        elif self.reduction == 'sum':
-            return loss.sum()
-        else:
-            return loss
-
-
-class ListMLELoss(nn.Module):
-    """
-    ListMLE (Maximum Likelihood Estimation) loss
-    Reference: Xia et al. Listwise approach to learning to rank: theory and algorithm (ICML 2008)
-    """
-    def __init__(self, reduction: str = 'mean'):
-        super(ListMLELoss, self).__init__()
-        self.reduction = reduction
-    
-    def forward(self, scores: torch.Tensor, labels: torch.Tensor) -> torch.Tensor:
-        # Sort by labels in descending order to get ground truth ranking
-        sorted_labels, sorted_indices = torch.sort(labels, descending=True, dim=1)
-        
-        # Reorder scores according to ground truth ranking
-        batch_size, list_size = scores.shape
-        batch_indices = torch.arange(batch_size, device=scores.device).unsqueeze(1).expand(-1, list_size)
-        sorted_scores = scores[batch_indices, sorted_indices]
-        
-        # Compute log likelihood
-        # For each position, compute log(exp(score_i) / sum(exp(score_j) for j >= i))
-        loss = torch.tensor(0.0, device=scores.device)
-        for i in range(list_size):
-            # Log-sum-exp trick for numerical stability
-            remaining_scores = sorted_scores[:, i:]
-            log_sum_exp = torch.logsumexp(remaining_scores, dim=1)
-            loss = loss + (log_sum_exp - sorted_scores[:, i]).sum()
-        
-        if self.reduction == 'mean':
-            return loss / batch_size
-        elif self.reduction == 'sum':
-            return loss
-        else:
-            return loss / batch_size
-
-
-class ApproxNDCGLoss(nn.Module):
-    """
-    Approximate NDCG loss for learning to rank.
-    Reference: Qin et al. "A General Approximation Framework for Direct Optimization of
-    Information Retrieval Measures" (Information Retrieval 2010).
-    """
-    def __init__(self, temperature: float = 1.0, reduction: str = 'mean'):
-        super(ApproxNDCGLoss, self).__init__()
-        self.temperature = temperature
-        self.reduction = reduction
-    
-    def _dcg(self, relevance: torch.Tensor, k: Optional[int] = None) -> torch.Tensor:
-        if k is not None:
-            relevance = relevance[:, :k]
-        
-        # DCG = sum(rel_i / log2(i + 2)) for i in range(list_size)
-        positions = torch.arange(1, relevance.size(1) + 1, device=relevance.device, dtype=torch.float32)
-        discounts = torch.log2(positions + 1.0)
-        dcg = torch.sum(relevance / discounts, dim=1)
-        
-        return dcg
-    
-    def forward(self, scores: torch.Tensor, labels: torch.Tensor, k: Optional[int] = None) -> torch.Tensor:
-        """
-        Args:
-            scores: Predicted scores [batch_size, list_size]
-            labels: Ground truth relevance labels [batch_size, list_size]
-            k: Top-k items for NDCG@k (if None, use all items)
-        
-        Returns:
-            Approximate NDCG loss (1 - NDCG)
-        """
-        batch_size = scores.size(0)
-        
-        # Use differentiable sorting approximation with softmax
-        # Create pairwise comparison matrix
-        scores_expanded = scores.unsqueeze(2)  # [batch_size, list_size, 1]
-        scores_tiled = scores.unsqueeze(1)     # [batch_size, 1, list_size]
-        
-        # Compute pairwise probabilities using sigmoid
-        pairwise_diff = (scores_expanded - scores_tiled) / self.temperature
-        pairwise_probs = torch.sigmoid(pairwise_diff)  # [batch_size, list_size, list_size]
-        
-        # Approximate ranking positions
-        # ranking_probs[i, j] ≈ probability that item i is ranked at position j
-        # We use softmax approximation for differentiable ranking
-        ranking_weights = F.softmax(scores / self.temperature, dim=1)
-        
-        # Sort labels to get ideal DCG
-        ideal_labels, _ = torch.sort(labels, descending=True, dim=1)
-        ideal_dcg = self._dcg(ideal_labels, k)
-        
-        # Compute approximate DCG using soft ranking
-        # Weight each item's relevance by its soft ranking position
-        positions = torch.arange(1, scores.size(1) + 1, device=scores.device, dtype=torch.float32)
-        discounts = 1.0 / torch.log2(positions + 1.0)
-        
-        # Approximate DCG by weighting relevance with ranking probabilities
-        approx_dcg = torch.sum(labels * ranking_weights * discounts, dim=1)
-        
-        # Normalize by ideal DCG to get NDCG
-        ndcg = approx_dcg / (ideal_dcg + 1e-10)
-        
-        # Loss is 1 - NDCG (we want to maximize NDCG, so minimize 1 - NDCG)
-        loss = 1.0 - ndcg
-        
-        if self.reduction == 'mean':
-            return loss.mean()
-        elif self.reduction == 'sum':
-            return loss.sum()
-        else:
-            return loss

nextrec-0.2.1.dist-info/RECORD

@@ -1,54 +0,0 @@
-nextrec/__init__.py,sha256=CvocnY2uBp0cjNkhrT6ogw0q2bN9s1GNp754FLO-7lo,1117
-nextrec/__version__.py,sha256=HfjVOrpTnmZ-xVFCYSVmX50EXaBQeJteUHG-PD6iQs8,22
-nextrec/basic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nextrec/basic/activation.py,sha256=9EfYmwE0brTSKwx_0FIGQ_rybFBT9n_G-UWA7NAhMsI,2804
-nextrec/basic/callback.py,sha256=qkq3k8rP0g4BW2C3FSCdVt_CyCcJwJ-rUXjhT2p4LP8,1035
-nextrec/basic/features.py,sha256=qNrGm74R6K7dw-kJdA2Sbp_Tjb_oDOo1a2JCfyOaYtw,3957
-nextrec/basic/layers.py,sha256=7cmTfYuYsehS9nEm-MmJJKfCqg0fESdNupI8Hfh_wkw,38296
-nextrec/basic/loggers.py,sha256=x8lzyyK-uqBN5XGOm1Cb33dmfc2bl114n6QeFTtE54k,3752
-nextrec/basic/metrics.py,sha256=w8tGe2tTbBNz9A1TNZF3jSpxcNC6QvFP5I0lWRd0Nw4,20398
-nextrec/basic/model.py,sha256=7DEEm0X8w1mNi2wuKFOYOGIh3ELdtBY4PTUMOQcoRCo,65161
-nextrec/basic/session.py,sha256=2kogEjgKAN1_ygelbwoqOs187BAcUnDTqXG1w_Pgb9I,4791
-nextrec/data/__init__.py,sha256=SOD64AkPykwKgm0CT89aDcHeiiDQlOOAkLDsAjYiqAM,814
-nextrec/data/data_utils.py,sha256=vGZ378YM_JQXO9npRB7JqojJx1ovjbJCWI-7lQJkicA,6298
-nextrec/data/dataloader.py,sha256=T0i2f5KMohd-hkgTPBNCPy9xaziRrUwYd01oI8GIEI8,20450
-nextrec/data/preprocessor.py,sha256=LzuBeBHcp6nnm7oaHDV-SZNk92ev8xjCj4r-thakRMw,42288
-nextrec/loss/__init__.py,sha256=kBanUB5rxQKwXTd6f-2hOI_CF7cp_MClAwAeVXIkpig,647
-nextrec/loss/listwise.py,sha256=tsupeCM4JPow-Y_J6qPs_bkgAKjdyutrbcsLthtqYd8,106
-nextrec/loss/loss_utils.py,sha256=MsHC8NYRHGVQN6uvHV7ICWoeAlVrN50wJ3hoCgtAr9c,4748
-nextrec/loss/match_losses.py,sha256=VacNGEJhrZGIDvEyThg5fdI1BQ7Ai9MjrL0BciJlAD0,11640
-nextrec/loss/pairwise.py,sha256=7ayKcGNz_DOBOVQp8NNNtE7bQW87Z9dgZeejFVG-G74,106
-nextrec/loss/pointwise.py,sha256=25ZQqKjE5cwCnBjK5P4c_b4jvjVBVy7mDVQSYlehShs,107
-nextrec/models/generative/hstu.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nextrec/models/generative/tiger.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nextrec/models/match/__init__.py,sha256=ASZB5abqKPhDbk8NErNNNa0DHuWpsVxvUtyEn5XMx6Y,215
-nextrec/models/match/dssm.py,sha256=5Ap0Bvo4FQJMd3jgXUPMJXkq-60ekXPQcAVRxLn5x_4,7679
-nextrec/models/match/dssm_v2.py,sha256=gxQUeZkbDfKi8wgEQ2a6KSaJ21ALnHRcucLYVSyiMPE,6381
-nextrec/models/match/mind.py,sha256=w3E1pswsIHgh6QisCoM19h3iMNRlycMTYRcEBK7A9eI,8712
-nextrec/models/match/sdm.py,sha256=neb0jbzaqm_rvlhrXmt9-blhNLE7Dgt0FoG6hAhKNcI,10216
-nextrec/models/match/youtube_dnn.py,sha256=hFwRTCLXe_DiQTNyMMwQ3IVRtY2GDKUfIGm0oGOKv_4,6804
-nextrec/models/multi_task/esmm.py,sha256=ku1MP10hrVrqHa6Gj78VlB5i7028kKUk9CqNRepKY8s,4790
-nextrec/models/multi_task/mmoe.py,sha256=qsQeKJiwwGVieS9zvoqzyqTOTzmIUIUqYZA11m9vaYY,6072
-nextrec/models/multi_task/ple.py,sha256=kFL9oLD571SqUXdBHbOr50TsSKJQL6OjdaFKaAqO8cU,11242
-nextrec/models/multi_task/share_bottom.py,sha256=aobFNBo06oS0s0EwxMmkBd7wn-xTq_QUAgIchVxT2Jo,4424
-nextrec/models/ranking/__init__.py,sha256=GMn3R5TkE9W17dzHuQoASJsQCoM_EIHuUhnMS2jMdZw,291
-nextrec/models/ranking/afm.py,sha256=fi9Iir3aQ4wAb9eEzo1HhJp34O9d4Jk17auzQkMZQ0E,4439
-nextrec/models/ranking/autoint.py,sha256=FejNRTZkAN6z0aIzQTkqOcc3yBQ9UzHhAM2PkxYOYJM,5553
-nextrec/models/ranking/dcn.py,sha256=gkjSMpor3fMs1HHJZErJXMd-EDblcIpQIDDGLt6CKxs,4107
-nextrec/models/ranking/deepfm.py,sha256=1e4_4QQiF3EDL9uhVLbPu4pO8jcsik0EyB8vRDTSRjc,3409
-nextrec/models/ranking/dien.py,sha256=QEs5xAjlxtHN_18VjqjhnAn-1aV5PI517WklvGMpxVM,8374
-nextrec/models/ranking/din.py,sha256=tnVu8bKGq65N0jEufGctZYXpKl2SHtJ6vlX7uxG3oQQ,7095
-nextrec/models/ranking/fibinet.py,sha256=p_VTiAMu2DZztHG-bqgvtlaKVmedo8m3NezSc1RHIGw,4752
-nextrec/models/ranking/fm.py,sha256=5u-KMpWbsuLNAqDQhwDAmlWCawEXcYVH0bNHHzVfzhE,2860
-nextrec/models/ranking/masknet.py,sha256=gjFcr1J0t5eBZfCYxkqvwyeEAEWQiRdtl43aKNNSA04,4538
-nextrec/models/ranking/pnn.py,sha256=iWVe04llFz6n4eBoujSB-WIFdefYk7hKoGe5XrkzOTo,4856
-nextrec/models/ranking/widedeep.py,sha256=PsoytJ-FWCBjW8-arvHRlJK7yXdtHCWYQ20P8W5luaQ,3615
-nextrec/models/ranking/xdeepfm.py,sha256=DOYpLBu5srDxt9aie_Wyiz7FVf1vzZISoVPfDT-AjiY,4173
-nextrec/utils/__init__.py,sha256=powarTEoywgO_htDi5a6O1rfiFBOz5wAIIpVMbCW0zs,368
-nextrec/utils/embedding.py,sha256=yxYSdFx0cJITh3Gf-K4SdhwRtKGcI0jOsyBgZ0NLa_c,465
-nextrec/utils/initializer.py,sha256=KxxC3rg5ydRWgcyfcdCFoqs9nVJOznSMWeJUWMPUff4,1656
-nextrec/utils/optimizer.py,sha256=CGsinqNZJZh8GqCYM9MkXjwGn2s_XyvAb4x_7ztOzB8,2464
-nextrec-0.2.1.dist-info/METADATA,sha256=KSReK5CVknLvuF_-0fSRs6Fzof3G9jHBBW4oRrjOotQ,11425
-nextrec-0.2.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-nextrec-0.2.1.dist-info/licenses/LICENSE,sha256=2fQfVKeafywkni7MYHyClC6RGGC3laLTXCNBx-ubtp0,1064
-nextrec-0.2.1.dist-info/RECORD,,