Hi,
I am doing one experiment with object detection model similar to SSD model given caffe-jacinto-models.
Experiment 1:
1. Trained the model with 2 classes
- caffe-jacinto training is successful
- importing is also done without any issue
- While host emulation inference, Pooling layer failed is coming.
Infer Log-
14, TIDL_ConcatLayer , 1, 2 , 1 , 12 , 13 , x , x , x , x , x , x , 14 , 1 , 128 , 73 , 73 , 1 , 256 , 73 , 73 ,
15, TIDL_PoolingLayer , 1, 1 , 1 , 14 , x , x , x , x , x , x , x , 15 , 1 , 256 , 73 , 73 , 1 , 256 , 37 , 37 ,
16, TIDL_ConvolutionLayer , 1, 1 , 1 , 15 , x , x , x , x , x , x , x , 16 , 1 , 256 , 37 , 37 , 1 , 32 , 37 , 37 ,
Layer 14 : Max PASS : 64770 : 64770 Out Q : 7669 , 65024, TIDL_ConcatLayer, PASSED #MMACs = 0.00, 0.00, 0.00, Sparsity : -1.#J, -1.#J
Layer 15 :[0][5][36] - outData - 0 outputRef - 3 TIDL_PoolingLayer, FAILED!!!!!! #MMACs = 0.35, 0.00, 0.35, Sparsity : 0.00, 100.00
Layer 16 : Max PASS : 111919 : 111919 Out Q : 14302 , 112358, TIDL_ConvolutionLayer, PASSED #MMACs = 11.21, 10.97, 12.79, Sparsity : -14.06, 2.16
Let me know , what should be the reason is?
Can we ignore this Failed Warning?
