TensorFlow-Advanced-Segmentation-Models

TensorFlow-Advanced-Segmentation-Models copied to clipboard

I was testing the UNet model along with a mobilenetv2 and saw that there are a lot non-trainable params, which I could not explain. I quick lookup in the model...

TillBeemelmanns

support to save model in .h5 format, this commit only support UNet model, but other model just in the same way

jianfengzhai

Is there exist performance issue when training or forward model pass? take UNet for example， ··· def call(self, inputs, training=None, mask=None): ···  when training or prediction， self.backbone(inputs) is calculated...

jianfengzhai

Hi there! I have been using your repository quite extensively and I must say, I really like it so far! So thank you very much! I do have one question...

laurenzheidrich

Hi, My dataset is made of 1 channel images, how can I use the models in this library with such a configuration ? thank you !

YahyaZefri

It seems that the lines with BS, C, H, W =x.shape are good only for channels_first and there is no code for BS, H, W, C. Also, what are the...

tabmoo

Errow while save and load the model

3

I had uncommented the checkpoint and tried to save the model. It generated `saved_model.pb` file. Below are the warning messages when the model was saved. ``` callbacks = [ tf.keras.callbacks.ModelCheckpoint("DeepLabV3plus1.ckpt",...

sachinkmohan

Swin Transformer

1

Awesome project! If I could make a feature request, Microsoft's recent Swin Transformer seems to be a sota model in many tasks including semantic segmentation, and it would be great...

anklebreaker

Change Logo

2

 I was reading the README and noticed that there is a spelling error in the project logo, where instead of segmentation it says "segmeNAtion". I believe that to improve...

Lucs1590

Hi! Would you consider adding HRNet trained on imagenet dataset to your backbone networks? I am really looking forward to that

Essha123