shenglih comments

Results 6 comments of


                                            shenglih

Train Custom Data Tutorial ⭐

I used a my_training.txt file that includes a list of training images instead of a path to the folder of images and annotations, but it always returns AssertionError: No images...

test batchsize=1 RuntimeError: CUDA out of memory.

same... warnings.warn("nn.Upsampling is deprecated. Use nn.functional.interpolate instead.") locating kps: 6%|█▌ | 167/2708 [01:30

TFLite, ONNX, CoreML, TensorRT Export

Would CoreML failure as shown below affect the successfully converted onnx model? Thank you. ONNX export success, saved as weights/yolov5s.onnx WARNING:root:TensorFlow version 2.2.0 detected. Last version known to be fully...

RuntimeError: The expanded size of the tensor (3) must match the existing size (864) at non-singleton dimension 3. Target sizes: [32, 3, 3, 3]. Tensor sizes: [864]

torch==0.3.1, python2.7, torchvision==0.2.0 work

out of memory for fine tuning

> torch.cuda.empty_cache() hi @quanvuong would you mind elaborating where to add these, much appreciated!

Errors when running run.sh

i had the exact same three errors with python 3.10. for 2, i changed to `matplotlib.use('Agg')`. 1 was resolved by using a conda env with python 3.10. hitting 3 now...