-
I tried to train vision encoder images only can you share code compression where my code gives accuracy 50 percent any help please code or experiments details please (training in eye gaze cxr )
-
In order to reduce the memory usage, I use optimize.quanto to quantize transformer, controlnet, and t5encoder in fp8, but I encounter an error
```
File "/home/yongfang/miniconda3/envs/diffusers/l…
-
My code:
`pipe.load_ip_adapter("h94/IP-Adapter-FaceID", subfolder="", weight_name="ip-adapter-faceid-plusv2_sdxl.bin")`
It gives error:
ip-adapter-faceid-plusv2_sdxl.bin: 100%|███████████████████…
-
Hello all! I have a question regarding the comparison of SAM vs SAM2. In the paper in Table 6, there is a comparison provided between both models across 37 datasets.
Does this comparison compar…
-
### Expected Behavior
for it to be loaded
### Actual Behavior
not loaded
### Steps to Reproduce
trained a model with the text encoder on 2 h100 gpus
sample images look fine, but it says lora …
-
When I try to use centerpose to start the node ros2 launch isaac_ros_centerpose isaac_ros_centerpose_tensor_rt.launch.py model_file_path:=/home/nvidia/Chen/centerpose/bottle_DLA34.onnx engine_file_p…
-
### Model description
Contrastive Audio-Visual Masked Autoencoder (CAV-MAE) combines two major self-supervised learning frameworks: contrastive learning and masked data modeling, to learn a joint and…
-
### feature
_No response_
-
In et_gen.py file,the follwing
clip_cls_feature, clip_visual = clip_model.encode_image(clip_src)
AttributeError: 'CLIP' object has no attribute 'encoder_image'
-
image encoder image size is too big ,can reduce 1024 to 640/480 for acceleration?