Fix a bug in CUDA pool op

Author: snnn

onnxruntime/core/providers/cuda/nn/pool.cc

@@ -182,16 +182,20 @@ Status Pool<T, PoolType, NHWC>::ComputeInternal(OpKernelContext* context) const
     if (NHWC) {
       x_dims_cudnn.insert(x_dims_cudnn.begin() + 1, 1);
       y_dims_cudnn.insert(y_dims_cudnn.begin() + 1, 1);
+      ORT_ENFORCE(pads.size() >= kernel_shape.size());
+      pads.insert(pads.begin() + kernel_shape.size(), 0);
+      pads.insert(pads.end(), 0);
       kernel_shape.insert(kernel_shape.begin() + 1, 1);
       strides.insert(strides.begin() + 1, 1);
     } else {
       x_dims_cudnn.push_back(1);
       y_dims_cudnn.push_back(1);
+      ORT_ENFORCE(pads.size() >= kernel_shape.size());
+      pads.insert(pads.begin() + kernel_shape.size(), 0);
+      pads.insert(pads.end(), 0);
       kernel_shape.push_back(1);
       strides.push_back(1);
     }
-    pads.insert(pads.begin() + kernel_shape.size(), 0);
-    pads.insert(pads.end(), 0);
   }
 
   cudnnPoolingMode_t mode = CUDNN_POOLING_MAX;