dsipts 1.1.6__tar.gz → 1.1.7__tar.gz

{dsipts-1.1.6 → dsipts-1.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dsipts
-Version: 1.1.6
+Version: 1.1.7
 Summary: Unified library for timeseries modelling
 Author-email: Andrea Gobbi <agobbi@fbk.eu>
 Project-URL: Homepage, https://github.com/DSIP-FBK/DSIPTS
@@ -128,10 +128,14 @@ or attention based models:
 ## Install
 Clone the repo (gitlab or github)
 The library is structured to work with [uv](https://github.com/astral-sh/uv). After installing `uv` just run  
-```
+```bash
 uv pip install .
 ```
-The pip package wi
+You can install also the package from pip (be sure that the python version is less than 3.12, still sperimental):
+```bash
+uv venv --python 3.11
+uv pip install dsipts
+```
 
 
 ## For developers

{dsipts-1.1.6 → dsipts-1.1.7}/README.md

@@ -96,10 +96,14 @@ or attention based models:
 ## Install
 Clone the repo (gitlab or github)
 The library is structured to work with [uv](https://github.com/astral-sh/uv). After installing `uv` just run  
-```
+```bash
 uv pip install .
 ```
-The pip package wi
+You can install also the package from pip (be sure that the python version is less than 3.12, still sperimental):
+```bash
+uv venv --python 3.11
+uv pip install dsipts
+```
 
 
 ## For developers

{dsipts-1.1.6 → dsipts-1.1.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dsipts"
-version = "1.1.6"
+version = "1.1.7"
 description = "Unified library for timeseries modelling"
 readme = "README.md"
 requires-python = "==3.11.13"

{dsipts-1.1.6 → dsipts-1.1.7}/src/dsipts/data_structure/data_structure.py

@@ -800,6 +800,7 @@ class TimeSeries():
                                 callbacks=[checkpoint_callback,mc],
                                 auto_lr_find=auto_lr_find, 
                                 accelerator=accelerator,
+                                log_every_n_steps=5,
                                 devices=devices,
                                 strategy=strategy,
                                 enable_progress_bar=False,
@@ -813,6 +814,7 @@ class TimeSeries():
                                 callbacks=[checkpoint_callback,mc],
                                 strategy='auto',
                                 devices=devices,
+                                log_every_n_steps=5,
                                 enable_progress_bar=False,
                                 precision=precision,
                                 gradient_clip_val=gradient_clip_val,

{dsipts-1.1.6 → dsipts-1.1.7}/src/dsipts/models/DilatedConv.py

@@ -231,28 +231,11 @@ class DilatedConv(Base):
                                             activation(),
                                             nn.Linear(hidden_RNN//4,1)))
         
+        self.return_additional_loss = True
         
 
         
 
-    def training_step(self, batch, batch_idx):
-        """
-        pythotrch lightening stuff
-        
-        :meta private:
-        """
-        y_hat,score = self(batch)
-        return self.compute_loss(batch,y_hat)#+torch.abs(score-self.glu_percentage)*loss/5.0 ##TODO investigating
-    
-    def validation_step(self, batch, batch_idx):
-        """
-        pythotrch lightening stuff
-        
-        :meta private:
-        """
-        y_hat,score = self(batch)
-        return self.compute_loss(batch,y_hat)#+torch.abs(score-self.glu_percentage)*loss/5.0 ##TODO investigating
-
     def forward(self, batch):
         """It is mandatory to implement this method
 
@@ -332,11 +315,11 @@ class DilatedConv(Base):
         res = res.reshape(B,self.future_steps,-1,self.mul)
         if self.remove_last:
             res+=x_start.unsqueeze(1)
-        
+
       
         return res, score
 
     def inference(self, batch:dict)->torch.tensor:
-        
+
         res, score = self(batch)
         return res

{dsipts-1.1.6 → dsipts-1.1.7}/src/dsipts/models/base.py

@@ -154,7 +154,7 @@ class Base(pl.LightningModule):
             assert self.out_channels==1, "Classification require only one channel"
 
         self.future_steps = future_steps
-        
+        self.return_additional_loss = False
         beauty_string(self.description,'info',True)
     @abstractmethod
     def forward(self, batch:dict)-> torch.tensor:
@@ -247,14 +247,22 @@ class Base(pl.LightningModule):
             opt = self.optimizers()
             def closure():
                 opt.zero_grad()
-                y_hat = self(batch)
-                loss = self.compute_loss(batch,y_hat)
+                if self.return_additional_loss:
+                    y_hat,score = self(batch)
+                    loss = self.compute_loss(batch,y_hat) + score
+                else:
+                    y_hat = self(batch)
+                    loss = self.compute_loss(batch,y_hat)
                 self.manual_backward(loss)
                 return loss
 
             opt.step(closure)
-            y_hat = self(batch)
-            loss = self.compute_loss(batch,y_hat)
+            if self.return_additional_loss:
+                y_hat,score = self(batch)
+                loss = self.compute_loss(batch,y_hat)+score
+            else:
+                y_hat = self(batch)
+                loss = self.compute_loss(batch,y_hat)
             
             #opt.first_step(zero_grad=True)
 
@@ -269,8 +277,14 @@ class Base(pl.LightningModule):
    
             #self.trainer.fit_loop.epoch_loop.manual_optimization.optim_step_progress.increment("optimizer")
         else:
-            y_hat = self(batch)
-            loss = self.compute_loss(batch,y_hat)
+            if self.return_additional_loss:
+                y_hat,score = self(batch)
+                loss = self.compute_loss(batch,y_hat)+score
+            else:
+                y_hat = self(batch)
+                loss = self.compute_loss(batch,y_hat)
+            
+        self.train_epoch_metrics.append(loss.item())
         return loss
 
     
@@ -280,7 +294,11 @@ class Base(pl.LightningModule):
         
         :meta private:
         """
-        y_hat = self(batch)
+        if self.return_additional_loss:
+            y_hat,score = self(batch)
+        else:
+            y_hat = self(batch)
+            score = 0
         if batch_idx==0:
             if self.use_quantiles:
                 idx = 1
@@ -301,7 +319,7 @@ class Base(pl.LightningModule):
                     self.logger.experiment.track(Image(fig), name='cm_training_end')
                     #self.log(f"example_{i}", np.stack([real, pred]).T,sync_dist=True)
 
-        return self.compute_loss(batch,y_hat)
+        return self.compute_loss(batch,y_hat)+score
 
 
     def validation_epoch_end(self, outs):
@@ -310,8 +328,12 @@ class Base(pl.LightningModule):
         
         :meta private:
         """
-    
-        loss = torch.stack(outs).mean()
+        if len(outs)==0:
+            loss = 10000
+            beauty_string(f'THIS IS A BUG, It should be polulated','info',self.verbose)
+        else:
+            loss = torch.stack(outs).mean()
+        
         self.log("val_loss", loss.item(),sync_dist=True)
         beauty_string(f'Epoch: {self.count_epoch} train error: {self.train_loss_epoch:.4f} validation loss: {loss.item():.4f}','info',self.verbose)
 

{dsipts-1.1.6 → dsipts-1.1.7}/src/dsipts/models/base_v2.py

@@ -157,7 +157,7 @@ class Base(pl.LightningModule):
 
 
         self.future_steps = future_steps
-        
+        self.return_additional_loss = False
         beauty_string(self.description,'info',True)
     @abstractmethod
     def forward(self, batch:dict)-> torch.tensor:
@@ -250,14 +250,22 @@ class Base(pl.LightningModule):
             opt = self.optimizers()
             def closure():
                 opt.zero_grad()
-                y_hat = self(batch)
-                loss = self.compute_loss(batch,y_hat)
+                if self.return_additional_loss:
+                    y_hat,score = self(batch)
+                    loss = self.compute_loss(batch,y_hat) + score
+                else:
+                    y_hat = self(batch)
+                    loss = self.compute_loss(batch,y_hat)
                 self.manual_backward(loss)
                 return loss
 
             opt.step(closure)
-            y_hat = self(batch)
-            loss = self.compute_loss(batch,y_hat)
+            if self.return_additional_loss:
+                y_hat,score = self(batch)
+                loss = self.compute_loss(batch,y_hat)+score
+            else:
+                y_hat = self(batch)
+                loss = self.compute_loss(batch,y_hat)
             
             #opt.first_step(zero_grad=True)
 
@@ -272,8 +280,12 @@ class Base(pl.LightningModule):
    
             #self.trainer.fit_loop.epoch_loop.manual_optimization.optim_step_progress.increment("optimizer")
         else:
-            y_hat = self(batch)
-            loss = self.compute_loss(batch,y_hat)
+            if self.return_additional_loss:
+                y_hat,score = self(batch)
+                loss = self.compute_loss(batch,y_hat)+score
+            else:
+                y_hat = self(batch)
+                loss = self.compute_loss(batch,y_hat)
             
         self.train_epoch_metrics.append(loss.item())
         return loss
@@ -285,7 +297,12 @@ class Base(pl.LightningModule):
         
         :meta private:
         """
-        y_hat = self(batch)
+
+        if self.return_additional_loss:
+            y_hat,score = self(batch)
+        else:
+            y_hat = self(batch)
+            score = 0
         if batch_idx==0:
             if self.use_quantiles:
                 idx = 1
@@ -305,7 +322,7 @@ class Base(pl.LightningModule):
                     ax.set_title(f'Channel {i} first element first batch validation {int(100*self.count_epoch/self.trainer.max_epochs)}%')
                     self.logger.experiment.track(Image(fig), name='cm_training_end')
                     #self.log(f"example_{i}", np.stack([real, pred]).T,sync_dist=True)
-        self.validation_epoch_metrics.append(self.compute_loss(batch,y_hat))
+        self.validation_epoch_metrics.append(self.compute_loss(batch,y_hat)+score)
         return 
 
 
@@ -315,7 +332,12 @@ class Base(pl.LightningModule):
         
         :meta private:
         """
-        avg = torch.stack(self.validation_epoch_metrics).mean()
+
+        if len(self.validation_epoch_metrics)==0:
+            avg = 10000
+            beauty_string(f'THIS IS A BUG, It should be polulated','info',self.verbose)
+        else:
+            avg = torch.stack(self.validation_epoch_metrics).mean()
         self.validation_epoch_metrics = []
         self.log("val_loss", avg,sync_dist=True)
         beauty_string(f'Epoch: {self.count_epoch} train error: {self.train_loss_epoch:.4f} validation loss: {avg:.4f}','info',self.verbose)
@@ -327,7 +349,11 @@ class Base(pl.LightningModule):
         
         :meta private:
         """
-        avg = np.stack(self.train_epoch_metrics).mean()
+        if len(self.train_epoch_metrics)==0:
+            avg = 0
+            beauty_string(f'THIS IS A BUG, It should be polulated','info',self.verbose)
+        else:
+            avg = np.stack(self.train_epoch_metrics).mean()
         self.log("train_loss", avg,sync_dist=True)
         self.count_epoch+=1    
         self.train_epoch_metrics = []

{dsipts-1.1.6 → dsipts-1.1.7}/src/dsipts.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dsipts
-Version: 1.1.6
+Version: 1.1.7
 Summary: Unified library for timeseries modelling
 Author-email: Andrea Gobbi <agobbi@fbk.eu>
 Project-URL: Homepage, https://github.com/DSIP-FBK/DSIPTS
@@ -128,10 +128,14 @@ or attention based models:
 ## Install
 Clone the repo (gitlab or github)
 The library is structured to work with [uv](https://github.com/astral-sh/uv). After installing `uv` just run  
-```
+```bash
 uv pip install .
 ```
-The pip package wi
+You can install also the package from pip (be sure that the python version is less than 3.12, still sperimental):
+```bash
+uv venv --python 3.11
+uv pip install dsipts
+```
 
 
 ## For developers