FunnelAct
FunnelAct copied to clipboard
megvii-model
感谢您为我的问题挤出时间来帮我解决，我表示由衷的感谢！ 在tensorflow框架下，我将您的代码放入到resnet vgg-16 NIN模型中来对cifar-10数据集进行分类，发现训练的时候损失为nan以及验证集准确率一直为0.1。请问您知道是什么原因吗？下面这是我的tensorflow代码 `channels = inputs.get_shape().as_list()[-1] scales1 = Conv2D(channels,kernel_size=3, strides=1, padding="same")(inputs) scales1 = BatchNormalization()(scales1) return tf.maximum(inputs,scales1)`
Hi, The depthwise convolution you're using in your implementation of FRelu is this the regular depthwise convolution or a depthwise separable convolution ? (a regular depthwise conv + 1x1 pointwise...
I reimplemented FReLU in PyTorch, and apply it on MobileNetV3 by replacing all the hswish with frelu. The ImageNet accuracy is as follow: |model|top1| |-|-| |mobilenetv3+hswish|75.2%| |mobilenetv3+frelu|74.8%| My code: ```python...
Thank you for your great contributions! In YOLOv5 we skipped over using Swish or Mish due to their expensive nature, especially during training, and retained the same LeakyReLU(0.1) as YOLOv3....
Hi，when I use FunnelAct in ResNet50 as the backbone of PSPNet with my own datasets，the mIoU is lower than the case of not use FunnelAct with the same epochs of...
