-
**Describe the bug and context**
I'm trying to quantize an optimized Stable Diffusion model.
I got to know that `IncDynamicQuantization` has less reduction in inference speed than `OnnxDynamicQuanti…
-
Thanks for your working.
I noticed that you mentioned pre trained model weights in Section 4.1 of the article, I have some interest in this. How should I do this part of pre training? What should I…
-
I use the pretrained weight from "https://github.com/SwinTransformer/storage/releases/download/v1.0.2/cascade_mask_rcnn_swin_base_patch4_window7.pth". When I try to pretrain on it (I set 'convert_weig…
-
`name: "SSD_DTLD"
layer {
name: "data"
type: "AnnotatedData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
crop_h:512
…
-
尝试用DistributedDataParallel做分布式训练，会出问题，有时在total_loss.backward()的时候hang住，有时在
preds = model(imgs)这句报错：
RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one…
-
### 🚀 The feature, motivation and pitch
Currently, the `reflection_pad2d_backward_cuda` operation used in neural network training cannot be computed deterministically on the GPU. This causes issues f…
-
`LayerNorm` is understood as normalization the activations by reducing across all non-batch axes. Curren…
-
I try like this:
python yolov3_darknet2caffe.py mobilenet_v1_yolov3.cfg mobilenet_v1_yolov3_final.weights mobilenet_yolov3.prototxt mobilenet_yolov3.caffemodel
and get an error:
F0627 23…
-
Adding concepts from the [extension of AIRO for AI bias](https://github.com/drd00/msc-dissertation-files/blob/master/main.ttl) developed by @drd00
-
Please add more grace when trying to handle a bias/flat/image list with uneven image sizes. Numpy doesn't care to concatenate differently sized images and fails on line 189 in biascombine:
ERROR: Val…
kweis updated
5 years ago