vinson2233 comments

Results 24 comments of


                                            vinson2233

Error: Input contains NaN, infinity or a value too large for dtype('float64'): pmdarima.predict()

so the solution is not to use autoarima if the series is difficult to forecast?

@sanjaygunda13 I never tried the processing in Base64, maybe you need to try to decode the Byte64 into PIL format first.

pytorch is really memory sensitive. make sure your CUDA memory is not occupied. use `nvidia-smi` command in the terminal to see GPU memory usage

How to evaluate the CLIP model results?

what limit you from doing so? you can simply calculate it using scikit learn, just put it inside the training loop. but i wonder what you mean by precision recall...

CLIP Training Code

@vkmavani sure. The `preprocess` object from CLIP takes care of all of the preprocessing steps for the image part, so you don't need to worry about image_size or transform(see https://github.com/openai/CLIP/blob/main/clip/clip.py...

CLIP Training Code

@lonngxiang For more information, read https://github.com/openai/CLIP/issues/57, clip.model.convert_weights basically convert the CLIP model weight into float16. This will help accelerate and reduce memory usage during training. The definition of clip.model.convert_weight can...

CLIP Training Code

@lonngxiang oh you are correct. pardon me, I have edited my code above. The dataset should return something that can be put on PyTorch tensor.

CLIP Training Code

Yeah, if already using preprocess inside the class. The result from the batch can be used directly to the CLIP. So that line can be change into this : `images...

CLIP Training Code

Hmmmm, that error is new for me. Is the error occurred when calculating the loss?

CLIP Training Code

Are you using CPU by any chance? The mixed precision training usually don't work on CPU

CLIP Training Code

@lonngxiang I have updated the code again. Basically, remove all code related to mixed-precision training when using CPU instead of GPU