-
Hi I need to change the first convolution of the model from rgb/resnet_v1_50/conv1/weights:0 (float32_ref 7x7x3x64) to rgb/resnet_v1_50/conv1/weights:0 (float32_ref 7x7x4x64), so basicaly augmenting …
-
## ❓ Questions and Help
Hi, I recently met an issue that my gradient becomes nan. I checked the codes and I found becomes some of my inputs contain infinity. On the one hand, I think in theory this…
-
## 🐛 Bug
I'm going to train a Resnet on ImageNet with DDP (A single node with multiple GPUs). I find that the data load time works fine in the first a few batches, but will increase a lot then if…
-
**Just a thought.**
I noticed that in there is no documentation neither in the doc or the repo readMe on building from source or cloning, this might seem synonymous to python developers, but arguably…
-
## 🐛 Bug
When trying to run a multi-process training with mpi backend the program fails at communication. Otherwise runs perfectly fine.
## To Reproduce
Steps to reproduce the behavior:
1.…
-
https://clarifai.com/models/celebrity-image-recognition-model-e466caa0619f444ab97497640cefc4dc
人脸识别
-
**It should reach 77.5* mAP at 80k iterations.**
Why I can't get this map?I just clone the code, and follow the readme.
-
@jpuigcerver Thanks for your answer. Actually, I build your model using pytorch and I try to extract the weights form your lua pretrained model and transfer them to my pytorch model. I do the convolut…
-
In the paper it is mentioned that the **softmax function** is being applied to the outputs after computing scores for each candidate item (_**equation 9**_), however, the PyTroch Implemention ([comput…
-
I meet OOM problem both train and valid, I decrease the batch size but it still happen, the problems seems happen when load pretrained models. the log of valid mpii dataset with resnet50 model is be…