J L

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] orig_width=640 orig_height =640 renderer...

can you supply a pre-trained model

1

can you supply a pre-trained model

AttributeError: 'Parameter' object has no attribute '_trt'

1

tensorrt 8.2.2.1 CUDA 10.2 UBUNTU 18.04 convert Efficientnet in Adabins to TRT https://github.com/shariqfarooq123/AdaBins/blob/2fb686a66a304f0a719bc53d77412460af97fd61/models/layers.py (trt8.2py39) delight-gpu@LIGHT-24B:~/project/torch2trt$ python 2trt.py init.py BB: CustomQKVToContextPluginDynamic init.py BB: CustomQKVToContextPluginDynamic init.py BB: CustomQKVToContextPluginDynamic init.py BB: CustomEmbLayerNormPluginDynamic init.py...

pyglet.gl.ContextException: Could not create GL context

1

I installed as guide https://pyrender.readthedocs.io/en/latest/install/index.html#python-installation but error occur detasets.py video 1/1 (1/343) /home/azuryl/data2/video/4p-c1_20212281641.mp4: orig_height, orig_width: 288 360 Traceback (most recent call last): File "track.py", line 663, in detect(args) File "track.py",...

orig_width=640 orig_height =640 renderer = Renderer(resolution=(orig_width, orig_height), orig_img=True,wireframe=False) def show_render(vibe_results,renderer, img_vibe): mesh_color = {k: colorsys.hsv_to_rgb(np.random.rand(), 0.5, 1.0) for k in vibe_results.keys()} for key, vibe_result in vibe_results.items(): #print("\n key,vibe_result:\n",key,vibe_result) frame_verts =...

MASKRCNN trt_model has Zero output

6

@grimoire >>>>>>>>>>>>>TRT infer.................. !!!!!!!!!!!!mmdet2trt/apis create_wrap_detector isinstance(trt_model, str) ##############torch2trt_dynamic.py inital TRTModule input_names,output_names: None None #####mmdet2trt init_trt_model....... [01/28/2022-16:45:39] [TRT] [W] TensorRT was linked against cuBLAS/cuBLAS LT 10.2.3 but loaded cuBLAS/cuBLAS LT 10.2.2...

MASKRCNN Encountered known unsupported method torch.Tensor.new_tensor

7

**Describe the bug** A clear and concise description of what the bug is. **Encountered known unsupported method torch.Tensor.new_tensor** **To Reproduce** Code snippet about how to reproduce the bug. https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn pretrained...

Can not load dataset from config. Use default CLASSES instead.

3

where can get MSKRCNN config file if I use mmdet config file then mmdet2trt init_trt_model....... [01/27/2022-14:52:30] [TRT] [W] TensorRT was linked against cuBLAS/cuBLAS LT 10.2.3 but loaded cuBLAS/cuBLAS LT 10.2.2...

why need norm = np.ones((pred.shape[0], 2)) * np.array([h, w]) / 10 in accuracy

1

in UDP-Pose/deep-high-resolution-net.pytorch/lib/core/evaluate.py Line 55 in d742edd norm = np.ones((pred.shape[0], 2)) * np.array([h, w]) / 10 norm = np.ones((pred.shape[0], 2)) * np.array([h, w]) / 10 I did know why use norm...

input(256, 256, 1) conv(254, 254, 16) relu(254, 254, 16) conv(252, 252, 16) relu(252, 252, 16) pool(126, 126, 16) #dropout(126, 126, 16) conv(124, 124, 32) relu(124, 124, 32) conv(122, 122, 32)...