-
请问有unet系列预训练模型吗，在文档中没有找到
-
I have tried all the methods in the project.
In the readme doc,the example lile `loss:
types:
- type: MixedLoss
losses:
- type: CrossEntropyLoss
- type: LovaszSoftmax…
-
I try to train my dataset using oxford-iiit.ipynb; but I get this warning and it doesnt calculate validation performance
Initial loss = 0.0
WARNING:tensorflow:Gradients do not ex…
nzplt updated
3 years ago
-
Does this example supports imagenet backbones?
```
name = 'unet3plus'
activation = 'ReLU'
filter_num_down = [32, 64, 128, 256, 512]
filter_num_skip = [32, 32, 32, 32]
filter_num_aggregate = 1…
-
BML_CodeLab使用UNet3Plus模型训练自定义数据集，in_channels=3，num_classes=2，batch_size=4， 报错如下,
```
Traceback (most recent call last):
File "test.py", line 65, in
use_vdl=True
File "/opt/conda/envs/pyt…
-
I am a beginner. Help me solve the error I got for Unet 3+.
InvalidArgumentError Traceback (most recent call last)
in ()
14 temp_out = unet3plus.predict([valid_…
-
paddle版本：2.1
PaddleSeg：release/2.1
cuda: 10.2
报错信息如下, 省略一部分重复。
```
2021-06-16 01:43:01 [INFO]
------------Environment Information-------------
platform: Windows-10-10.0.19041-SP0
Python: 3.7…
-
Hi,
First of all - thank you for this great model collection.
Maybe this is intended by design but:
`base_model = models.unet_3plus_2d(input_shape, n_labels=19, filter_num_down=[64, 128, 256, 512, …
-
File **_model_unet_3plus_2d.py** line 128
current
` X = UNET_left(X, filter_num[i_real], stack_num=stack_num_down, activation=activation, pool=pool,
ba…
-
I get this error when I try to run the unet3plus with 512,512,3 as the input.
`ValueError: Dimensions must be equal, but are 512 and 64 for '{{node binary_crossentropy_2/mul}} = Mul[T=DT_FLOAT](re…