world2025
world2025
@Ir1d 你理解那个attention模块吗？
@Ir1d 我用demo的时候显示cuda内存不够，很尴尬
@Rayn-Wu 好的，谢谢
Hi,thanks for your code,do you use the multi_scale image inputs in your experiment?
Ok,thank you.I want to use like this network to realize the image retrieval ,but I don't know how to build my own network ,can you help me ? Thank you...
Ok, thank you
Hello， h_strd =math.floor(float(previous_conv_size[0]) / out_pool_size[i]) w_strd = math.floor(float(previous_conv_size[1]) / out_pool_size[i]) the stride size should be math.floor not math.ceil acoording to the Spatial Pyramid Pooling in Deep Convolutional Networks for Visual...
@sMyron hello, did you train success? i met a question, did you use the parser.add_argument("--checkpoint_model", type=str, help="Optional path to checkpoint model") and did you find the train datasets? thank you
@JNUChenYiHong hello, did you train success? did you use the params: parser.add_argument("--checkpoint_model", type=str, help="Optional path to checkpoint model") thank you
i met the problem too, did you solve it? thank you