def evaluate_images(self): par_obj.feat_arr = {} par_obj.pred_arr = {} par_obj.sum_pred = {} count = -1 for b in par_obj.left_2_calc: frames = par_obj.frames_2_load[b] for i in frames: v2.im_pred_inline_fn(par_obj, self, inline=True, outer_loop=b, inner_loop=i, count=count) v2.evaluate_forest(par_obj, self, False, 0, inline=True, outer_loop=b, inner_loop=i, count=count) count = count + 1 v2.apply_correction(par_obj) self.save_output_data_btn.setEnabled(True) self.image_status_text.showMessage('Status: evaluation finished.') par_obj.eval_load_im_win_eval = True v2.eval_pred_show_fn(par_obj.curr_img, par_obj, self)
def train_model_btn_fn(self): self.image_status_text.showMessage('Training Ensemble of Decision Trees. ') v2.update_training_samples_fn(par_obj,0) self.image_status_text.showMessage('Evaluating Images with the Trained Model. ') app.processEvents() v2.evaluate_forest(par_obj,self, False,0) v2.make_correction(par_obj, 0) self.image_status_text.showMessage('Model Trained. Continue adding samples, or click \'Save Training Model\'. ') par_obj.eval_load_im_win_eval = True self.goto_img_fn(par_obj.curr_img) self.save_model_btn.setEnabled(True)
def evaluate_images(self): par_obj.feat_arr = {} par_obj.pred_arr = {} par_obj.sum_pred = {} count = -1 for b in par_obj.left_2_calc: frames =par_obj.frames_2_load[b] for i in frames: v2.im_pred_inline_fn(par_obj, self,inline=True,outer_loop=b,inner_loop=i,count=count) v2.evaluate_forest(par_obj,self, False, 0,inline=True,outer_loop=b,inner_loop=i,count=count) count = count+1 v2.apply_correction(par_obj) self.save_output_data_btn.setEnabled(True) self.image_status_text.showMessage('Status: evaluation finished.') par_obj.eval_load_im_win_eval = True v2.eval_pred_show_fn(par_obj.curr_img, par_obj,self)