|
@@ -266,9 +266,8 @@ static __global__ void softmax(float *predict, int length)
|
|
|
}
|
|
|
}
|
|
|
|
|
|
-static void classfier_softmax(float *predict,int length, cudaStream_t stream) {
|
|
|
+static void classfier_softmax(float *predict, int length, cudaStream_t stream) {
|
|
|
int block_size = 256;
|
|
|
-
|
|
|
checkKernel(softmax<<<1, block_size, block_size * sizeof(float), stream>>>(predict, length));
|
|
|
}
|
|
|
|
|
@@ -393,7 +392,7 @@ class InferImpl : public Infer {
|
|
|
|
|
|
for (int ib = 0; ib < num_image; ++ib) {
|
|
|
float *output_array_device = output_array_.gpu() + ib * num_classes_;
|
|
|
- checkRuntime(classfier_softmax(output_array_device, num_classes_, stream_));
|
|
|
+ classfier_softmax(output_array_device, num_classes_, stream_);
|
|
|
}
|
|
|
|
|
|
|