SkylerJulyApril

cannot train locally with the error "AttributeError: type object 'NCCL' has no attribute 'new_uid'"

10

File "./tools/train_net_multi_gpu.py", line 109, in max_iter=args.max_iters, gpus=gpus) File "/home/jzheng/PycharmProjects/bottom-up-attention/tools/../lib/fast_rcnn/train_multi_gpu.py", line 233, in train_net_multi_gpu uid = caffe.NCCL.new_uid() AttributeError: type object 'NCCL' has no attribute 'new_uid' What should I do with this...

model written with tf2.6.0 (not using keras) cannot find instructions to do quantization aware training, only keras model based quantization example can be found

1

I wrote my code with tensorflow 2.0, some of my code used tf.compat.v1, I'm trying to do quantization aware training for my model, however, I cannot find any functions except...

TFLite quantization, the int tflite model is much slower than the float tflite model

5

I converted Pytorch model to onnx model, and then to tensorflow model, I convert tensorflow model to float tflite model and int tflite model(with post training quantization). Currently, my int...

is it hard to reimplement UNITER for reffering expression task?

1

Hi, thank you very much for your great work. I'm wondering if I need to reimplement it for referring expression task, is it doable? How long will it take?

error when train by myself with "./experiments/scripts/train_faster_rcnn.sh 0 pascal_voc res101"

10

4952 validation roidb entries Filtered 0 roidb entries: 10022 -> 10022 Filtered 0 roidb entries: 4952 -> 4952 Solving... Loading initial model weights from data/imagenet_weights/res101.pth Loaded. Traceback (most recent call...

how to change it back to pytorch 0.3

1

how to change the code back to pytorch 0.3?

Can it be used in any of the diffusion models for upscaling purpose? Like text to image or text to video models, based on latent diffusion?

Hi, have you tested on stable diffusion 2.1?

how to adapt to non square image model training and inference?

52

can you share how to adapt to non square image model training and inference? is it possible to use stable diffusion pipeline to generate non-square images?