RunningLeon
RunningLeon
## Motivation add global rewriting for `adaptive_avg_pool` and ease the exporting to onnx for models such as pspnet, litehrnet. ## Modification - Add `adaptive_avg_pool2d__default` rewriting in `mmdeploy/pytorch/functions/adaptive_pool.py` - Remove some...
## Motivation Support `batch_size > 1` for `tools/profile.py`, requested in issue #861 . ## Modification - update `create_input` for batch images in mmcls, mmdet, mmpose, mmseg, mmocr, mmrotate. - update...
## Motivation Support mmseg:dev-1.x ## Modification - [x] update task and End2EndModel in `mmdeploy.codebase.mmseg.deploy` - [x] update rewritings in `mmdeploy.codebase.mmseg.models` - [x] update tests for mmseg ## BC-breaking (Optional) ##...
## Purpose This issue is pinned to collect any question that is related to model inference latency. You could follow the template to post your issue here. ## Pre-info mmdeploy...
Hi, @natanielruiz Sorry to bother you, but here's a problem. Could pls. take a look at it? It won't match when parse the ypr for [BIWI dataset](https://data.vision.ee.ethz.ch/cvl/gfanelli/head_pose/head_forest.html#db). Take following sample...
## Motivation support mmpose2.0 for sdk ## Modification Please briefly describe what modification is made in this PR. ## BC-breaking (Optional) None ## Use cases (Optional) If this PR introduces...
Hi, Have you evaluated the pretrained model on any other dataset? Can you post it? Thanks a lot.
## Motivation Support [cogvlm-chat-hf](https://huggingface.co/THUDM/cogvlm-chat-hf) for pytorch engine Usage: > [!WARNING] > CogVLM-Chat-hf uses `'lmsys/vicuna-7b-v1.5'` as tokenizer, you need to copy the tokenizer model and configs into CogVLM model directory. ```...
This PR supports the conversion of [internlm2](https://huggingface.co/internlm) from hf to trt-llm checkpoints with : - fp16/bf16 - tp
## Motivation Support llava for pytorch engine, including original models like [liuhaotian/llava-v1.5-7b](https://huggingface.co/liuhaotian/llava-v1.5-7b) and llava-hf models like [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) TODO - [ ] Resovle conflicts after PR like #1502 #1553 #1591 ##...