Dhruv Karan

No model .t7 file being created while training on own data

4

I'm running the train.lua file as, `$ th train.lua -input_h5 test_h5.h5 -input_json test_json.json -gpuid -1 -max_iters 5` I'm getting output as, `DataLoader loading json file: test_json.json vocab size is 13...

Adds CLIP to models exportable with ONNX

19

This isn't currently working, getting an error while validating the model - ``` onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Unexpected input data type. Actual: (tensor(float)) , expected: (tensor(int64)) ```...

Can I define the batch size inside the code? How would be the input format be changed then?

[WIP] Adds image-guided object detection support to OWL-ViT

10

For https://github.com/huggingface/transformers/issues/18748 @alaradirik

While training on own images, getting a Invalid operation is performed in: LinearFunction (Forward) error

5

While training on my own images, I'm getting this error, chainer.utils.type_check.InvalidType: Invalid operation is performed in: LinearFunction (Forward) Expect: prod(in_types[0].shape[1:]) == in_types[1].shape[1] Actual: 259656 != 27648