| 74 | else: return self.epoch_accuracy[:self.current_epoch, 1].max() |
| 75 | |
| 76 | def plot_curve(self, save_path): |
| 77 | title = 'the accuracy/loss curve of train/val' |
| 78 | dpi = 80 |
| 79 | width, height = 1200, 800 |
| 80 | legend_fontsize = 10 |
| 81 | scale_distance = 48.8 |
| 82 | figsize = width / float(dpi), height / float(dpi) |
| 83 | |
| 84 | fig = plt.figure(figsize=figsize) |
| 85 | x_axis = np.array([i for i in range(self.total_epoch)]) # epochs |
| 86 | y_axis = np.zeros(self.total_epoch) |
| 87 | |
| 88 | plt.xlim(0, self.total_epoch) |
| 89 | plt.ylim(0, 1) |
| 90 | interval_y = 0.05 |
| 91 | interval_x = 5 |
| 92 | plt.xticks(np.arange(0, self.total_epoch + interval_x, interval_x)) |
| 93 | plt.yticks(np.arange(0, 1 + interval_y, interval_y)) |
| 94 | plt.grid() |
| 95 | plt.title(title, fontsize=20) |
| 96 | plt.xlabel('the training epoch', fontsize=16) |
| 97 | plt.ylabel('accuracy', fontsize=16) |
| 98 | |
| 99 | y_axis[:] = self.epoch_accuracy[:, 0] |
| 100 | plt.plot(x_axis, |
| 101 | y_axis, |
| 102 | color='g', |
| 103 | linestyle='-', |
| 104 | label='train-accuracy', |
| 105 | lw=2) |
| 106 | plt.legend(loc=4, fontsize=legend_fontsize) |
| 107 | |
| 108 | y_axis[:] = self.epoch_accuracy[:, 1] |
| 109 | plt.plot(x_axis, |
| 110 | y_axis, |
| 111 | color='y', |
| 112 | linestyle='-', |
| 113 | label='valid-accuracy', |
| 114 | lw=2) |
| 115 | plt.legend(loc=4, fontsize=legend_fontsize) |
| 116 | |
| 117 | y_axis[:] = self.epoch_losses[:, 0] |
| 118 | plt.plot(x_axis, |
| 119 | y_axis * 50, |
| 120 | color='g', |
| 121 | linestyle=':', |
| 122 | label='train-loss-x50', |
| 123 | lw=2) |
| 124 | plt.legend(loc=4, fontsize=legend_fontsize) |
| 125 | |
| 126 | y_axis[:] = self.epoch_losses[:, 1] |
| 127 | plt.plot(x_axis, |
| 128 | y_axis * 50, |
| 129 | color='y', |
| 130 | linestyle=':', |
| 131 | label='valid-loss-x50', |
| 132 | lw=2) |
| 133 | plt.legend(loc=4, fontsize=legend_fontsize) |