Python U-Net分段Keras的Hausdorff损失
我想使用我在这里找到的hausdorff（）作为我的U-Net中的损失，但是当我尝试这样做时，我得到了以下错误：Python U-Net分段Keras的Hausdorff损失,python,tensorflow,keras,loss-function,Python,Tensorflow,Keras,Loss Function,我想使用我在这里找到的hausdorff（）作为我的U-Net中的损失，但是当我尝试这样做时，我得到了以下错误： ValueError: Dimensions must be equal, but are 3 and 2 for 'loss/conv2d_19_loss/MatMul' (op: 'MatMul') with input shapes: [?,3], [2,16384]. 我并不真正理解hausdorff距离的代码，但我在循环中使用了与网络相同的批量大小。我还尝试使用另一个损失
ValueError: Dimensions must be equal, but are 3 and 2 for 'loss/conv2d_19_loss/MatMul' (op: 'MatMul') with input shapes: [?,3], [2,16384].
Tensor（“损失/conv2d_19_损失/stripped_切片：0”，shape=（？，？，？），dtype=float32） Traceback (most recent call last):
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 686, in _call_cpp_shape_fn_impl
input_tensors_as_shapes, status)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 3 and 2 for 'loss/conv2d_19_loss/MatMul' (op: 'MatMul') with input shapes: [?,3], [2,16384].
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/etudiant_master/Documents/Marouane/Scripts/Test_parameters.py", line 367, in <module>
test_hyperparam_list('Loss', LOSS)
File "/home/etudiant_master/Documents/Marouane/Scripts/Test_parameters.py", line 339, in test_hyperparam_list
test_ligne = leave_one_out_model_test(batch_size, nb_epoch, validation_split, kernels, kernel_size, dropout_rate, pooling_size, block_number, path_test = path_test, iteration = var, metrics = metrics, optimizer = optimizer, loss = loss, activation = activation, activation2 = activation2)
File "/home/etudiant_master/Documents/Marouane/Scripts/Test_parameters.py", line 123, in leave_one_out_model_test
model = train_model.CNNs_layers(kernels = kernels, kernel_size = kernel_size, dropout_rate = dropout_rate, pooling_size = pooling_size, block_number = block_number, activation = activation, activation2 = activation2, metrics = metrics, optimizer = optimizer, loss = loss)
File "/home/etudiant_master/Documents/Marouane/Scripts/train_model.py", line 120, in CNNs_layers
model.compile(optimizer= optimizer, loss=loss, metrics=[metrics])
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/keras/_impl/keras/engine/training.py", line 849, in compile
output_loss = weighted_loss(y_true, y_pred, sample_weight, mask)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/keras/_impl/keras/engine/training.py", line 454, in weighted
score_array = fn(y_true, y_pred)
File "/home/etudiant_master/Documents/Marouane/Scripts/Metrics.py", line 73, in Weighted_Hausdorff_loss
d_matrix = tf.sqrt(tf.maximum(tf.reshape(tf.reduce_sum(gt_b*gt_b, axis=1), (-1, 1)) + tf.reduce_sum(all_img_locations*all_img_locations, axis=1)-2*(tf.matmul(gt_b, tf.transpose(all_img_locations))), 0.0))
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 2022, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 2516, in _mat_mul
name=name)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3162, in create_op
compute_device=compute_device)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3208, in _create_op_helper
set_shapes_for_outputs(op)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2427, in set_shapes_for_outputs
return _set_shapes_for_outputs(op)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2400, in _set_shapes_for_outputs
shapes = shape_func(op)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2330, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 627, in call_cpp_shape_fn
require_shape_fn)
File "/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 691, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Dimensions must be equal, but are 3 and 2 for 'loss/conv2d_19_loss/MatMul' (op: 'MatMul') with input shapes: [?,3], [2,16384].
回溯（最近一次呼叫最后一次）：
文件“/home/etudiant\u master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/common\u shapes.py”，第686行，在调用cpp\u shape\u fn\u impl中
输入\张量\作为\形状、状态）
文件“/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/errors_impl.py”，第473行，在退出中__
c_api.TF_GetCode（self.status.status））
tensorflow.python.framework.errors\u impl.InvalidArgumentError:维度必须相等，但对于输入形状为：[？、3]、[216384]的“loss/conv2d\u 19\u loss/MatMul”（op:'MatMul'），维度为3和2。
在处理上述异常期间，发生了另一个异常：
回溯（最近一次呼叫最后一次）：
文件“/home/etudiant_master/Documents/Marouane/Scripts/Test_parameters.py”，第367行，在
测试超参数列表（“丢失”，丢失）
文件“/home/etudiant\u master/Documents/Marouane/Scripts/Test\u parameters.py”，第339行，在测试超参数列表中
test\u ligne=leave\u one\u out\u model\u test（批大小、nb\u epoch、验证\u分割、内核、内核大小、退出率、池大小、块数、路径测试=路径测试、迭代=var、度量=度量、优化器=优化器、丢失=丢失、激活=激活、激活2=激活2）
文件“/home/etudiant\u master/Documents/Marouane/Scripts/Test\u parameters.py”，第123行，左侧为模型测试
模型=训练模型.CNNs\u层（内核=内核，内核大小=内核大小，辍学率=辍学率，池大小=池大小，块数=块数，激活=激活，激活2=激活2，度量=度量，优化器=优化器，损失=损失）
文件“/home/etudiant\u master/Documents/Marouane/Scripts/train\u model.py”，第120行，CNNs\u层
compile（优化器=优化器，损耗=损耗，度量=[度量]）
文件“/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/keras/_impl/keras/engine/training.py”，第849行，编译
输出损耗=加权损耗（y_真、y_pred、样本重量、掩码）
文件“/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/keras/_impl/keras/engine/training.py”，第454行，以加权形式显示
分数数组=fn（y_真，y_pred）
文件“/home/etudiant\u master/Documents/Marouane/Scripts/Metrics.py”，第73行，在加权Hausdorff\u损失中
d_矩阵=tf.sqrt（tf.maximum（tf.reformation（tf.reduce_sum（gt_b*gt_b，axis=1），（-1，1））+tf.reduce_sum（all_img_位置*all_img_位置，axis=1）-2*（tf.matmul（gt_b，tf.transpose（all_img_位置）），0.0）
文件“/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/ops/math_ops.py”，第2022行，matmul格式
a、 b，转置a=转置a，转置b=转置b，名称=名称）
文件“/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/ops/gen_math_ops.py”，第2516行，在
名称=名称）
文件“/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/op_def_library.py”，第787行，位于“应用”op_helper中
op_def=op_def）
文件“/home/etudiant_master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第3162行，在create_op中
计算设备=计算设备）
文件“/home/etudiant\u master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第3208行，位于“创建”和“操作”助手中
为输出设置形状（op）
文件“/home/etudiant\u master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第2427行，用于输出的集合形状
返回_设置_形状_输出（op）
文件“/home/etudiant\u master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第2400行，用于输出
形状=形状函数（op）
文件“/home/etudiant\u master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/ops.py”，第2330行，与
回传呼叫\u cpp\u shape\u fn（op，require\u shape\u fn=True）
文件“/home/etudiant\u master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/common\u shapes.py”，第627行，在call\u cpp\u shape\u fn中
需要（形状）
文件“/home/etudiant\u master/anaconda3/envs/tensorflow/lib/python3.6/site packages/tensorflow/python/framework/common\u shapes.py”，第691行，在调用cpp\u shape\u fn\u impl中
提升值错误（错误消息）
ValueError：维度必须相等，但对于输入形状为：[？、3]、[216384]的“loss/conv2d_19_loss/MatMul”（op:“MatMul”）而言，维度为3和2。
非常感谢
ValueError:对于输入形状为：[？、3]、[216384]的'loss/conv2d_19_loss/MatMul'（op:'MatMul'），维度必须相等，但为3和2。