fisakhan

My be your training dataset is too small.

I think the only problem is dependency on Tensorflow 1.12. Its a petty that someone is still using TensorFlow==1.12 when we have TensorFlow==2.25.

The placeholder error can be solved by replacing import tensorflow as tf with import tensorflow.compat.v1 as tf tf.disable_v2_behavior() in all files. However, ./renderer/rasterize_triangles_kernel.so will still make a problem with newer...

I get the same error. @Iswarya05 how did you solve this problem? Do we need to built the tensorflow from source?

I solved this problem by installing TensorFlow C API from `https://www.tensorflow.org/install/lang_c` because tf.load_op_library requires libtensorflow_framework.so but now I get the following error: `NotFoundError: ./renderer/rasterize_triangles_kernel.so: undefined symbol: _ZN10tensorflow15TensorShapeBaseINS_11TensorShapeEEC1EN4absl4SpanIKxEE`

@rakaar what version of the cuda and cudnn did you use for TensorFlow==1.12? Can we run it on CPU only without having need for cuda? I use TensorFlow==2.4 and CUDA==11...

Can someone provide pre-compiled binary file rasterize_triangles_kernel.so that can work with TensorFlow >= 2.0 ?

When I solve the above problem then I get the following problem: > ----------------- Options --------------- > batchsize: 2 > cfg_file: lib/configs/resnext101_32x4d_nyudv2_class [default: lib/configs/resnext_32x4d_nyudv2_c1] > dataroot: ./datasets/NYUDV2 [default: None] >...

I found that the following versions are compatible but then it is in conflict with google-auth ``` google-colab==1.0.0 tensorflow==2.5.0 tensorflow-cloud==0.1.16 ``` After installing latest version of google-auth as suggested by...

I receive the following error `ImportError: cannot import name 'build_model_from_cfg'` Even though I can run the following example from mmdetection successfully ``` from mmdet.apis import init_detector, inference_detector, show_result_pyplot config_file =...