ZhaoyangLi

some strange problem with file not found error

2

File "/home/pytorchVersion/tsn-pytorch/dataset.py", line 108, in get seg_imgs = self._load_image(record.path, p) File "/home/pytorchVersion/tsn-pytorch/dataset.py", line 50, in _load_image return [Image.open(os.path.join(directory, self.image_tmpl.format(idx))).convert('RGB')] File "/home/anaconda3/envs/py36/lib/python3.6/site-packages/PIL/Image.py", line 2477, in open fp = builtins.open(filename, "rb") FileNotFoundError:...

Can I finetune my own dataset with different resolution

3

 when I use different resolution image try to fine-tune Clip.visual. Looking forward to your reply

when I execute**make**a problem appear with: [ 0%] Building CXX object CMakeFiles/CVD.dir/cvd_src/bayer.cxx.o In file included from /home/lzy/scene_lib/libcvd/cvd/image_ref.h:185:0, from /home/lzy/scene_lib/libcvd/cvd/image.h:17, from /home/lzy/scene_lib/libcvd/cvd/image_convert_fwd.h:4, from /home/lzy/scene_lib/libcvd/cvd/colourspace_convert.h:3, from /home/lzy/scene_lib/libcvd/cvd_src/bayer.cxx:3: /home/lzy/scene_lib/libcvd/cvd/internal/image_ref_implementation.hh: In member function ‘constexpr...

I would like to know whether training single image version of llava-ov needs to read the training data in the order in single_image.yaml, or whether it is random.