ICNet-tensorflow

ICNet-tensorflow copied to clipboard

How to generate information like color150.mat?

1

Hi, I want generate all names of 150 classes, object names of each class, and number of pictures which contain this class. How can I do that? or how to...

changlinzhang

How to reduce number of class in this model?

1

@hellochick Thank you very much for very interesting code. Can you give me some advice about how to reduce number of class in this model?

huyphongdo

zhouzhou33

lrxiao

Hi~Could you please send the pretrained model with email? [email protected]~ Many thanks!

5

ClaireTun

The update stops and the loss does not drop

4

hello，Today I trained ade20k, but the loss stops at about 2 and I can’t go down

AishuaiYao

README instructions not working for training on my own dataset

46

Hi, I tried to follow README instructions for training on my own dataset but it didn't work. Here is what I did: - Update `DATA_DIR` to point to dataset dir...

ogail

您好，您上一个项目的File "C:\ProgramFilesMyself\Anaconda3\envs\garbage2\lib\site-packages\tensorflow\python\client\session.py", line 1095, in _run 'Cannot interpret feed_dict key as Tensor: ' + e.args[0]) TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is...

jingrunzhou

I have change restore_var = tf.global_variables() to restore_var = [v for v in tf.global_variables() if 'conv6_cls' not in v.name] Update INPUT_SIZE to '512, 512' Update NUM_CLASSES to 13 filter_scale=2. model_type...

shakey-cuimiao

Why is it suddenly 'killed' run train.py?

1

> step 246 total loss = 0.767, sub4 = 1.042, sub24 = 0.553, sub124 = 0.238, val_loss: 0.706 (1.229 sec/step) step 247 total loss = 0.775, sub4 = 0.978, sub24...

INJNainggolan