型。預(yù)測(cè)給出所有相同的輸出驗(yàn)證和測(cè)試精度< 60%我嘗試將最后一個(gè)隱藏層更改為softmax，但它仍然沒(méi)有解決這個(gè)問(wèn)題。任何反饋將不勝感激。我也嘗試過(guò)使用超參數(shù)，但我仍然找不到任何修復(fù)程序。raw_cvs_data = np.loadtxt('data_to_train.csv',delimiter=',') raw_cvs_data_to_compute = np.loadtxt('data_to_compute.csv',delimiter=',') unscaled_inputs_all = raw_cvs_data[:,1:] targets_all = raw_cvs_data[:,0] inputs_to_compute = raw_cvs_data_to_compute[:] predicted_target=[] # balancing the dataset num_one_targets = int(np.sum(targets_all)) # count how many targets are 1 zero_targets_counter = 0 # counter for target 0 indices_to_remove = [] # remove extra input/target pairs for balance  # count the number of targets 0, when get same amount of target 1 and 0, make entries where target is zero for i in range(targets_all.shape[0]):         if targets_all[i] == 0:             zero_targets_counter +=1             if zero_targets_counter > num_one_targets:                 indices_to_remove.append(i) unscaled_inputs_equal_priors = np.delete(unscaled_inputs_all,indices_to_remove, axis = 0) targets_equal_priors = np.delete(targets_all, indices_to_remove, axis = 0) #Shuffle the data  shuffled_indices = np.arange(scaled_inputs.shape[0]) np.random.shuffle(shuffled_indices) #shuffle pairs shuffled_inputs = scaled_inputs[shuffled_indices] shuffled_targets = targets_equal_priors[shuffled_indices] # splitting data samples_count = shuffled_inputs.shape[0] # |training|validation|testing| 80-10-10 train_samples_count = int(0.8 * samples_count) validation_samples_count = int(0.1 *samples_count) test_samples_count = samples_count - train_samples_count - validation_samples_count train_inputs = shuffled_inputs[:train_samples_count] train_targets = shuffled_targets[:train_samples_count]