Sanjay Saini

Hello @yosinski, Thanks for providing us excellent visualization toolbox, I would like to know whether deep-visualization-toolbox support video file as a input??? i tried to give video file as input...

Loss saturate after 80 Epoch

1

Hi @github-luffy, I trained AuxiliaryNet on WFLW data set using WingLoss and loss and failure rate: L1 staturate after 80 Epoch. Does this mean model is converged/generalised? What was your...

Output Node names

4

I am trying to convert your model into .dlc format which is Qualcomm Snapdragon (SNPE) format. I gave the output node names "`pred_sbbox/concat_2, pred_mbbox/concat_2, pred_lbbox/concat_2"` However its says that `ERROR_TF_NODE_NOT_FOUND_IN_GRAPH:...

Can someone help me to understand `self.fc = nn.Linear(176, 196) `how 176 input feature has been choose in PFLDInference network. I am trying to train 192x192 image size model but...

Can someone help me to understand "self.fc = nn.Linear(176, 196)" how 176 input feature has been choose

2

Can someone help me to understand `self.fc = nn.Linear(176, 196)` how 176 input feature has been choose in PFLDInference network.

Can anybody explain this code to me??

1

``` with tf.variable_scope('MiddleAndRPN_' + name): # convolutinal middle layers temp_conv = ConvMD(3, 64, 64, 3, (2, 1, 1), (1, 1, 1), temp_conv, name='conv3') temp_conv = tf.transpose(temp_conv, perm=[0, 2, 3, 4,...

OS: Ubuntu 18.04 LTS TensorRT: 8.0 Cuda: 10.2 GCC: 7.5 ``` jetsonhack@jetsonhack-desktop:~/tensorRT/TensorRT-Yolov3$ cd build && cmake .. && make && make install -- The C compiler identification is GNU 7.5.0...

Exception: RNN : Input dimension should be rank 3 : [batch_size, n_steps, n_features]

12

I am trying to test your model with my dataset but i am getting error in RNN: > ........... > ........... > ........... > [TL] RNNLayer Conv3D_ConvLSTM/clstm_layer_1: n_hidden:256 n_steps:16 in_dim:5...

TypeError: Input 'split_dim' of 'Split' Op has type float32 that does not match expected type of int32.

1

Dear @GuangmingZhu , I have modified the ...tensorlayer/layers/recurrent.py layer as per tensorlayer-rnnlayer.py. However, I am getting following errors, do you have any idea how to solve???? ``` Traceback (most recent...