Open VVsssssk opened 2 years ago
E.g: Swin-Transformer mmcls tensorrt
second mmdet3d tensorrt
htc mmdetection tensorrt
segmenter mmsegmentation tensorrt
swin-transformer mmdet tensorrt
I haven't tried the conversion yet and I just used your example fater-rcnn. Maybe now, need to try.
segmenter mmsegmentation tensorrt
@haofanwang Have you tried segmenter with mmdeploy?
segmenter mmsegmentation tensorrt
@haofanwang Have you tried segmenter with mmdeploy?
@RunningLeon , Yes, but I receive error messages as below
TypeError: upsample_bicubic2d() received an invalid combination of arguments - got (Tensor, NoneType, bool, list), but expected one of:
* (Tensor input, tuple of ints output_size, bool align_corners, tuple of floats scale_factors)
didn't match because some of the arguments have invalid types: (Tensor, NoneType, bool, list)
* (Tensor input, tuple of ints output_size, bool align_corners, float scales_h, float scales_w, *, Tensor out)
And my command is
python ./tools/deploy.py \
./configs/mmseg/segmentation_tensorrt-fp16_dynamic-512x1024-2048x2048.py \
./mmsegmentation/configs/segmenter/segmenter_vit-l_mask_8x1_512x512_160k_ade20k.py \
./mmsegmentation/checkpoints/segmenter_vit-l_mask_8x1_512x512_160k_ade20k_20220105_162750-7ef345be.pth \
./mmsegmentation/demo/demo.png \
--work-dir work_dir\
--device cuda\
--dump-in
512x512 @haofanwang Try with static config with 512x512. You can change in config file.
maskformer mmdet tensorrt
swin-transformer mmdet onnx
Swin-Transformer mmcls tensorrt
SATRN mmocr tensorrt
SATRN for ocr, to onnx and tensorrt pls!
SATRN for ocr, to onnx and tensorrt pls!
SATRN MMOCR tensorrt
dynamic_voxelization mmdet3d onnxruntime and tensorrt
Swin-Transformer Second Segmenter
Oriented R-CNN,S2A-Net for mmrotate tensorrt, please!
mask2former mmdet tensorrt
monoflex tensorrt
mmtracking
AssociativeEmbedding pose detection in mmpose
mmocr
yolact mmdetection onnx
K-Net
htc
Smoke, mmdetection3d , tensorrt
Swin-Transformer mmdetection tensorrt
yolact mmdetection onnx
@VVsssssk do you know when swin-transformers can release
a vote to TOOD
MMaction2/Pyskl for (skeleton based action recognition)
deformable detr!,detr!,transformer系列
segmenter mmsegmentation tensorrt
Done. It's been supported in v0.6.0
Swin-Transformer mmdetection tensorrt
Done. It's been supported in v0.6.0
solov2 onnx tensorrt
TSM/TSN... mmaction2 tensorrt
mmdetection3d SMOKE
TSM、Video swin-transformer mmaction2 tensorrt :heart_eyes: :pray:
mmdetection solov2
solov2 tensorrt
fcos3d in mmdetection3d
solov2 tensorrt
@VVsssssk : Given that both MaskFormer and Mask2Former got lots of votes, is there any plan to support them? They are not even on the table on top, any specific reason? Thank you!
solov2 onnx tensorrt
SAR model
ConvNeXt
ConvNext mmdet tensorrt
HTC segmentation object detection, onnx tensorrt
Reference: