-
## TL; DR
- ViT feature representations are *less hierarchical*.
- Early tr blocks learn both local and global dependencies provided with large enough dataset.
- Skip connections play much more i…
-
Hi, @yangxy
GPEN is great job, thank you very much for all you shared.
Now we are trying to train the GPEN-BFR-256 model with 8 x Nvidia A100 GPU with your latest training code that was updated yes…
-
**Describe the bug**
I tried to use the two pre-trained models `Mink16UNet34C` provided [here](https://github.com/chrischoy/SpatioTemporalSegmentation#model-zoo) with [main.py](https://github.com/chr…
-
#### Hello again,
thanks to your help, I was able to run the whole program on large scale data successfully.
However, the result doesn't always look that accurate. Some categorization are hard to…
-
UPD:
The standing items:
- add pseudocode. I think pseudocode / compact python implementations would be very useful for understanding what is normalized over and what learned affine weights corres…
-
@jeffreyhanson - hoping you can confirm my understanding of the spatial clustering code and answer my questions below.
If spatial clustering is turned on, the following happens when running fct_m…
-
The [Allan et al (2019) paper, "Hotspots of human impact on threatened terrestrial vertebrates"](https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3000158), looked at terrestrial s…
-
I read in your Readme that you're having issues with getting NaNs as result.
I've had similar issues and found that after the first iteration, sometimes my activations would be negative. This causes …
-
There are some tests (e.g., `TestDepartures`) that use `np.ones` or `np.zeros`, so the output of these operations won't produce outputs the discern correctness of behavior.
Instead, we should have …
-
While using scGCO, encountered the following error
code is running in Python 3.9
```
gmmDict=scGCO.gmm_model(data_norm)
result_df= identify_spatial_genes(locs, data_norm, cellGraph ,gmmDict)
``…