Akash L P

Integration with captum for explainability

2

Since mmclassification is also built with Pytorch I found it would be interesting if we could get explainable AI to be included too along GradCam since, Captum can give better...

Hi, i am trying to train craft detection model, but ended in the below mentioned error, after completion of 1000 ittertations any suggestions would help a lot, thanks. ``` c:\users\user\pycharmprojects\easy_ocr_new\easyocr\trainer\craft\data\pseudo_label\make_charbox.py(36)crop_image_by_bbox()...

Usage of Shapash for Deep Learning models

1

**Description of Problem**: Can Shapash be used for image classification and object detection problems...? like Lime and Shap libraries?

Error while loading datasets in True inference with LayoutLMv2ForTokenClassification + Gradio demo.ipynb

5

OSError: Cannot find data file. Original error: cannot identify image file '/root/.cache/huggingface/datasets/downloads/extracted/e5bbbc543f8cc95554da124f3e80a57ed24d67d06ae1467da5810703f851e3f9/dataset/training_data/images/0000971160.png' while loading dataset from ``` from datasets import load_dataset datasets = load_dataset("nielsr/funsd") ```

How can i compute Integrated Gradients for object detection(Yolov5) ?

3

Hey, how can I compute IG for object detection models such as yolov5 wherein the model's output will usually be (class, bboxes, score), where as certain classification models give prediction...

Error while generating integrated_gradients for custom object detection model

3

Attached is the full logs, ``` C:\Users\user\PycharmProjects\yolor_my\yolor_env\Scripts\python.exe C:/Users/user/PycharmProjects/yolor_my/yolor/my_test.py To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor). Person 0.65 [tensor(0.21673, device='cuda:0', requires_grad=True),...

Error while running segmentation tutorial

1

While running the segmentation tutorial I am getting this error attached is the full traceback: `Traceback (most recent call last): File "C:/Users/user/PycharmProjects/Captum_test/segmentation_example.py", line 99, in viz.visualize_image_attr(gc_attr[0].cpu().permute(1, 2, 0).detach().numpy(), sign="all") File...

Does it only do lowercase predictions?

1

Hey, thanks for the work, is there any parameter that I can change in order to get the predictions for capital letters....?, is it case sensitive or only lowercase ?

Issue while training with custom decoder and tokenizer

2

hey, i was trying to train a model of parsing arabic data, As mentioned by @VictorAtPL , I have trained Mbart tokenizer using arabic corpus, and also trained the Mbart...

Hey all, I was trying to train donut model for parsing, which contains Arabic(only) information, in order to achieve this i had collected `Arabic corpus` from various sources and then...