tensorflow, image segmentation convnet InvalidArgumentError: Input to reshape is a tensor with 28800000 values, but the requested shape has 57600

Question

我正在尝试从 BRATS 挑战中分割图像。我在这两个存储库的组合中使用 U-net：

https://github.com/zsdonghao/u-net-brain-tumor

当我尝试输出预测统计数据时出现形状不匹配错误：

InvalidArgumentError: Input to reshape is a tensor with 28800000 values, but the requested shape has 57600 [[Node: Reshape_2 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_Cast_0_0, Reshape_2/shape)]]

我正在使用 240x240 的图像切片，batch_verification_size = 500

然后，

这是形状 test_x: (500, 240, 240, 1)
这是形状 test_y: (500, 240, 240, 1)
这是形状测试 x: (500, 240, 240, 1)
这是形状测试 y: (500, 240, 240, 1)
这是形状批次 x：(500, 240, 240, 1)
这是形状批次 y：(500, 240, 240, 1)
这是形状预测：(500, 240, 240, 1)
这是成本：Tensor("add_88:0", shape=(), dtype=float32)
这是成本：Tensor("Mean_2:0",shape=(), dtype=float32)
这是形状预测：(?, ?, ?, 1)
这是形状批次 x：(500, 240, 240, 1)
这是形状批次 y：(500, 240, 240, 1)

240 x 240 x 500 = 28800000 我不知道为什么要求 57600

看起来错误来自 output_minibatch_stats 函数：

summary_str, loss, acc, predictions = sess.run([self.summary_op, 
                                                self.net.cost, self.net.accuracy, 
self.net.predicter], 
feed_dict={self.net.x: batch_x,
self.net.y: batch_y,
self.net.keep_prob: 1.})

因此 sess.run tf 函数有问题。下面是出现错误的一些代码。有人知道会发生什么吗？

def store_prediction(self, sess, batch_x, batch_y, name):
    print('track 1')
            prediction = sess.run(self.net.predicter, feed_dict={self.net.x: batch_x, 
                                                                 self.net.y: batch_y, 
                                                                 self.net.keep_prob: 1.})
            print('track 2')
            pred_shape = prediction.shape



loss = sess.run(self.net.cost, feed_dict={self.net.x: batch_x, 
                                                       self.net.y: batch_y, `
                                                       self.net.keep_prob: 1.})
        print('track 3')
        logging.info("Verification error= {:.1f}%, loss= {:.4f}".format(error_rate(prediction,
                                                                          util.crop_to_shape(batch_y,
                                                                                             prediction.shape)),
                                                                          loss))
        print('track 4')
        print('this is shape batch x: ' + str(batch_x.shape))
        print('this is shape batch y: ' + str(batch_y.shape))
        print('this is shape prediction: ' + str(prediction.shape))
        #img = util.combine_img_prediction(batch_x, batch_y, prediction)
        print('track 5')
        #util.save_image(img, "%s/%s.jpg"%(self.prediction_path, name))

        return pred_shape

    def output_epoch_stats(self, epoch, total_loss, training_iters, lr):
        logging.info("Epoch {:}, Average loss: {:.4f}, learning rate: {:.4f}".format(epoch, (total_loss / training_iters), lr))

    def output_minibatch_stats(self, sess, summary_writer, step, batch_x, batch_y):
        print('this is shape cost : ' + str(self.net.cost.shape))
        print('this is cost : ' + str(self.net.cost))
        print('this is  acc : ' + str(self.net.accuracy.shape))
        print('this is cost : ' + str(self.net.accuracy))
        print('this is shape prediction: ' + str(self.net.predicter.shape))
        print('this is shape batch x: ' + str(batch_x.shape))
        print('this is shape batch y: ' + str(batch_y.shape))


        # Calculate batch loss and accuracy
        summary_str, loss, acc, predictions = sess.run([self.summary_op, 
                                                            self.net.cost, 
                                                            self.net.accuracy, 
                                                            self.net.predicter], 
                                                           feed_dict={self.net.x: batch_x,
                                                                      self.net.y: batch_y,
                                                                      self.net.keep_prob: 1.})
        print('track 6')
        summary_writer.add_summary(summary_str, step)
        print('track 7')
        summary_writer.flush()
        logging.info("Iter {:}, Minibatch Loss= {:.4f}, Training Accuracy= {:.4f}, Minibatch error= {:.1f}%".format(step,
                                                                                                            loss,
                                                                                                            acc,
                                                                                                            error_rate(predictions, batch_y)))
        print('track 8')

Answer 1

您在训练期间在 tensorflow 管道中将批量大小设置为 1，但在测试数据中输入了 500 批量大小。这就是为什么网络只请求形状为 57600 的张量。您可以将训练批量大小设置为 500 或将测试批量大小设置为 1。

tensorflow, image segmentation convnet InvalidArgumentError: Input to reshape is a tensor with 28800000 values, but the requested shape has 57600

tensorflow, image segmentation convnet InvalidArgumentError: Input to reshape is a tensor with 28800000 values, but the requested shape has 57600

python

image-processing

image-segmentation

conv-neural-network

tensorflow