web_tool/ModelSessionPyTorchExample.py [100:126]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        tile = tile.astype(np.float32)

        output, output_features = self.run_model_on_tile(tile)
        self._last_tile = output_features

        return output

    def retrain(self, **kwargs):
        x_train = np.array(self.augment_x_train)
        y_train = np.array(self.augment_y_train)

        if x_train.shape[0] == 0:
            return {
                "message": "Need to add training samples in order to train",
                "success": False
            }


        try:
            self.augment_model.fit(x_train, y_train)
            score = self.augment_model.score(x_train, y_train)
            LOGGER.debug("Fine-tuning accuracy: %0.4f" % (score))

            new_weights = torch.from_numpy(self.augment_model.coefs_[0].T.copy().astype(np.float32)[:,:,np.newaxis,np.newaxis])
            new_biases = torch.from_numpy(self.augment_model.intercepts_[0].astype(np.float32))
            new_weights = new_weights.to(self.device)
            new_biases = new_biases.to(self.device)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



web_tool/ModelSessionPyTorchSegmentationModel.py [97:123]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        tile = tile.astype(np.float32)

        output, output_features = self.run_model_on_tile(tile)
        self._last_tile = output_features

        return output

    def retrain(self, **kwargs):
        x_train = np.array(self.augment_x_train)
        y_train = np.array(self.augment_y_train)
        
        if x_train.shape[0] == 0:
            return {
                "message": "Need to add training samples in order to train",
                "success": False
            }

        
        try:
            self.augment_model.fit(x_train, y_train)
            score = self.augment_model.score(x_train, y_train)
            LOGGER.debug("Fine-tuning accuracy: %0.4f" % (score))

            new_weights = torch.from_numpy(self.augment_model.coefs_[0].T.copy().astype(np.float32)[:,:,np.newaxis,np.newaxis])
            new_biases = torch.from_numpy(self.augment_model.intercepts_[0].astype(np.float32))
            new_weights = new_weights.to(self.device)
            new_biases = new_biases.to(self.device)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -