automl icon indicating copy to clipboard operation
automl copied to clipboard

KeyError: 'trainable_weights'

Open fanchunpeng opened this issue 4 years ago • 1 comments

Traceback (most recent call last): File "train_RGB_softmax.py", line 351, in tf.app.run() File "C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\platform\app.py", line 125, in run _sys.exit(main(argv)) File "train_RGB_softmax.py", line 194, in main logits = build_model(images_batch) File "train_RGB_softmax.py", line 126, in build_model model = effnetv2_model.EffNetV2Model(model_Dict["model_name"], model_Dict) File "D:\TF_EfficientNet\EfficientNetV2\EfficientNetV2_fancp\effnetv2_model.py", line 534, in init self.cfg = cfg File "C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\network.py", line 335, in setattr or checkpointable_layer_utils.has_weights(value)): File "C:\Users\Administrator\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\training\checkpointable\layer_utils.py", line 36, in has_weights return (hasattr(obj, "trainable_weights") File "D:\TF_EfficientNet\EfficientNetV2\EfficientNetV2_fancp\hparams.py", line 56, in getattr return self.dict[k] KeyError: 'trainable_weights'

fanchunpeng avatar Jun 01 '21 09:06 fanchunpeng

Could you paste the full command line? I don't understand your question.

mingxingtan avatar Jun 04 '21 21:06 mingxingtan