i conducted additional experiments.
When using Conv 1.2 layer of VGG-16 network, according to the [paper](https://arxiv.org/abs/1509.09308), performance should be better than direct conv2d. But the result is that direct conv2d is better. input_img shape = (1,64,224,224) ## NCHW Format weight shape = (64,64,3,3) bias shape = (64,) Conv with Direct algo -> 0.563ms Conv with Winograd Strassen algo -> 22.261ms The winograd performance is too low than direct conv2d. is it normal? --- [Visit Topic](https://discuss.tvm.ai/t/topi-winograd-convolution-performance-is-too-slow/6161/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/e2c8bfe327c571f155bda42ea36c21d35450594923f8c65bee3b318c22f9dd8d).
