shiyongde comments

Results 20 comments of


                                            shiyongde

Meet some problems when training on my own data. See below.

I have the same question

Loss Curve

i got loss_pixpro: -2.7215 , it's confuse

Train model with data of no labels?

same problem

_batch_inputs = data['inputs'] KeyError: 'inputs' error while training

same problem

[Task]: How to inference fastflow model by using pt file? (anomalib 0.3.3)

how to speedup？？

ValueError: Incompatible shapes between op input and calculated input gradient.

the same bug whith Tensorflow 1.8 cuda9.1 Build train graph Tensor("child/layer_0/case/cond/Merge:0", shape=(?, 36, 32, 32), dtype=float32) Tensor("child/layer_1/skip/bn/Identity:0", shape=(?, 36, 32, 32), dtype=float32) Tensor("child/layer_2/skip/bn/Identity:0", shape=(?, 36, 32, 32), dtype=float32) Tensor("child/layer_3/pool_at_3/from_4/bn/Identity:0", shape=(?,...

Tutorial for Zero-shot Testing or Fine-tuning GLEE on New Datasets

Waiting for this

shiyongde

Meet some problems when training on my own data. See below.

the pre-training loss

Loss Curve

Loss Curve

🐛 [Bug] export and save

Train model with data of no labels?

_batch_inputs = data['inputs'] KeyError: 'inputs' error while training

[Task]: How to inference fastflow model by using pt file? (anomalib 0.3.3)

ValueError: Incompatible shapes between op input and calculated input gradient.

Tutorial for Zero-shot Testing or Fine-tuning GLEE on New Datasets