Remote-sensing-image-semantic-segmentation icon indicating copy to clipboard operation
Remote-sensing-image-semantic-segmentation copied to clipboard

The project uses Unet-based improved networks to study Remote sensing image semantic segmentation, which is based on keras.

Results 10 Remote-sensing-image-semantic-segmentation issues
Sort by recently updated
recently updated
newest added

你好,我再使用您模型训练的时候,遇到总是卡在model.fit()那一步,训练开始后不打印任何信息,让我感觉像是卡了一样,请问这正常吗?

请问基于U-Net模型的改进点在哪里呢

发现了数据集好像不太对,是做过什么处理吗? 数据中有(0,0,0)值,并且地物颜色与真实的也不一致。

dadaset 的百度验证码 不是1d4x呀 显示错误

@TachibanaYoshino In ValImggenerator function, there is no data augmenting while TrainImggenerator used. if the validating data are small, the val_acc will be very low.

```python out1 = Activation('softmax',name='l1')(Reshape((400 * 400, n_label))(R_out4)) out2 = Activation('softmax',name='l2')(Reshape((200 * 200, n_label))(R_out3)) out3 = Activation('softmax',name='l3')(Reshape((100 * 100, n_label))(R_out2)) out4 = Activation('softmax',name='l4')(Reshape((50 * 50, n_label))(R_out1)) ``` 请问网络层为什么要使用多个尺寸的label呢? 另外,您在推理预测的时候,好像并没有使用到多尺寸的pred ```python pred...

实现: def get_label_from_palette(label_img, palette_file='Palette.json'): with open(palette_file, 'r') as fp: text = json.load(fp) palette_values = np.array(list(text.values())) palette_keys = np.array(list(text.keys())) # 将三维RGB图像展平为二维形状 flat_label_img = label_img.reshape((-1, 3)) mask = np.all(np.equal(palette_values, flat_label_img[:, None]), axis=2)...

![image](https://user-images.githubusercontent.com/58057507/204123805-76600a1c-8ad4-4ac8-ab06-eb59a21d75a7.png) ![image](https://user-images.githubusercontent.com/58057507/204123825-e2726fce-9d26-4e73-940f-0ccd26a858b2.png) 您好,请问这里val_l0_acc的keyreeor是什么问题呢