Dahai

training own data problems

1

running model trained from own datasets where there are 7321 classes (chinese character) gets output as below: 1072 text boxes before nms ./demo_images/BizLicenseOCR2.jpg : net 410630ms, restore 1ms, nms 10ms...

get InvalidArgumentError (see above for traceback): Not enough time for target transition sequence (required: 17, available: 11)14You can turn this error into a warning by using the flag ignore_longer_outputs_than_inputs in tf.nn.ctc_loss

9

get InvalidArgumentError (see above for traceback): Not enough time for target transition sequence (required: 17, available: 11)14You can turn this error into a warning by using the flag ignore_longer_outputs_than_inputs in...

I always get angle

Compile nearest neighbors in utils folder in windows platform successfully，but the output From test.py in nearest_neighbors does not make sense

6

test code： batch_size = 16 num_points = 81920 K = 16 pc = np.random.rand(batch_size, num_points, 3).astype(np.float32) start = time.time() neigh_idx = nearest_neighbors.knn_batch(pc, pc, K, omp=True) print(neigh_idx) print(time.time() - start) output：...

模型训练的acc一直停留在85%， densenet网络的input的filters可以改成128来提高模型的拟合能力吗？

4

@

Android studio4.2.1 ncnn-20210525-android-vulkan opencv-mobile-4.5.1-android

trainning mobilenet_v2 failed

1

I got an error because the format of mobilenet_v2.mobilenetv2_base return values is not compatible with the format of resnet.resnet_base or resnet_gluoncv.resnet_base return values. the trainning was stoped in for level_name,...