yolo_anchors.txt超参数值设置

keras-yolov3在训练自定义图片集之前设置合理的yolo_anchors.txt值有利于模型训练的收敛一般都带有默认的参数如下在实际项目中yolo_anchors的值可以根据kmeans.py计算获取通过聚类得到最佳anchors数据kmeans.py执行后即可得到合适的yolo_anchors参数值代码如下import numpy as np class YOLO_Kmeans: def __init__(self, cluster_number, filename): self.cluster_number cluster_number self.filename 2007_train.txt def iou(self, boxes, clusters): # 1 box - k clusters n boxes.shape[0] k self.cluster_number box_area boxes[:, 0] * boxes[:, 1] box_area box_area.repeat(k) box_area np.reshape(box_area, (n, k)) cluster_area clusters[:, 0] * clusters[:, 1] cluster_area np.tile(cluster_area, [1, n]) cluster_area np.reshape(cluster_area, (n, k)) box_w_matrix np.reshape(boxes[:, 0].repeat(k), (n, k)) cluster_w_matrix np.reshape(np.tile(clusters[:, 0], (1, n)), (n, k)) min_w_matrix np.minimum(cluster_w_matrix, box_w_matrix) box_h_matrix np.reshape(boxes[:, 1].repeat(k), (n, k)) cluster_h_matrix np.reshape(np.tile(clusters[:, 1], (1, n)), (n, k)) min_h_matrix np.minimum(cluster_h_matrix, box_h_matrix) inter_area np.multiply(min_w_matrix, min_h_matrix) result inter_area / (box_area cluster_area - inter_area) return result def avg_iou(self, boxes, clusters): accuracy np.mean([np.max(self.iou(boxes, clusters), axis1)]) return accuracy def kmeans(self, boxes, k, distnp.median): box_number boxes.shape[0] distances np.empty((box_number, k)) last_nearest np.zeros((box_number,)) np.random.seed() clusters boxes[np.random.choice( box_number, k, replaceFalse)] # init k clusters while True: distances 1 - self.iou(boxes, clusters) current_nearest np.argmin(distances, axis1) if (last_nearest current_nearest).all(): break # clusters wont change for cluster in range(k): clusters[cluster] dist( # update clusters boxes[current_nearest cluster], axis0) last_nearest current_nearest return clusters def result2txt(self, data): f open(yolo_anchors.txt, w) row np.shape(data)[0] for i in range(row): if i 0: x_y %d,%d % (data[i][0], data[i][1]) else: x_y , %d,%d % (data[i][0], data[i][1]) f.write(x_y) f.close() def txt2boxes(self): f open(self.filename, r) dataSet [] for line in f: infos line.split( ) length len(infos) for i in range(1, length): width int(infos[i].split(,)[2]) - \ int(infos[i].split(,)[0]) height int(infos[i].split(,)[3]) - \ int(infos[i].split(,)[1]) dataSet.append([width, height]) result np.array(dataSet) f.close() return result def txt2clusters(self): all_boxes self.txt2boxes() result self.kmeans(all_boxes, kself.cluster_number) result result[np.lexsort(result.T[0, None])] self.result2txt(result) print(K anchors:\n {}.format(result)) print(Accuracy: {:.2f}%.format( self.avg_iou(all_boxes, result) * 100)) if __name__ __main__: cluster_number 16 # 类别数量 filename 2007_train.txt kmeans YOLO_Kmeans(cluster_number, filename) kmeans.txt2clusters()替换原有默认的yolo_anchors.txt文件再进行模型训练。注意执行kmeans.py的时机需要在模型训练之前模型训练之前需要先写入新的anchors的值后续博客再做yolov3全流程开发补充。