BoHuangLab commited on
Commit
4037949
·
verified ·
1 Parent(s): c7cfa07

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -18,6 +18,7 @@ Checkpoints behind the [CELL-FM CondenSeq demo](https://huggingface.co/spaces/Bo
18
  | `condenseq/cellfm_seq2img.bin` | CELL-FM CS sequence-to-image generator (includes the ESM-C 600M encoder) | `pretrain_condenseq/cellfm_seq2img/checkpoint-50000` |
19
  | `condenseq/vae.bin` | Image VAE, 160x160, 3 down blocks, 4 latent channels | `pretrain_condenseq/vae/checkpoint-50000` |
20
  | `condenseq/vit_cls.bin` | ViT condensed/diffuse classifier, 2-channel 160x160 input | `PT_CondenSeq_img_ViT_cls_R1/checkpoint-10000` |
 
21
  | `hpa/cellfm_seq2img.bin` | CELL-FM virtual-staining generator for HPA, 256x256, 3-channel conditioning (includes the ESM-C 600M encoder) | `pretrain_hpa/cellfm_seq2img/checkpoint-50000` |
22
  | `hpa/vae.bin` | Image VAE at 256x256, the one `hpa/cellfm_seq2img.bin` was trained against | `pretrain_hpa/vae/checkpoint-50000` |
23
  | `hpa/vit.bin` | Image-embedding ViT for HPA: 12 layers, 512 hidden, 2048 MLP, 8 heads, patch 4, 256x256 input. Trained to identify the protein in an image over 13,908 classes; the embedding is the representation, not the prediction. Four input channels — protein, nucleus, ER, microtubules | `pretrain_hpa/vit/checkpoint-16000` |
 
18
  | `condenseq/cellfm_seq2img.bin` | CELL-FM CS sequence-to-image generator (includes the ESM-C 600M encoder) | `pretrain_condenseq/cellfm_seq2img/checkpoint-50000` |
19
  | `condenseq/vae.bin` | Image VAE, 160x160, 3 down blocks, 4 latent channels | `pretrain_condenseq/vae/checkpoint-50000` |
20
  | `condenseq/vit_cls.bin` | ViT condensed/diffuse classifier, 2-channel 160x160 input | `PT_CondenSeq_img_ViT_cls_R1/checkpoint-10000` |
21
+ | `condenseq/reference_nucleus.npy` | The DAPI channel every CondenSeq generation is conditioned on: `(1, 160, 160)` float32 in [-1, 1]. CondenSeq protein index 12626, image 0 — the same one the offline seq2img runs used | built |
22
  | `hpa/cellfm_seq2img.bin` | CELL-FM virtual-staining generator for HPA, 256x256, 3-channel conditioning (includes the ESM-C 600M encoder) | `pretrain_hpa/cellfm_seq2img/checkpoint-50000` |
23
  | `hpa/vae.bin` | Image VAE at 256x256, the one `hpa/cellfm_seq2img.bin` was trained against | `pretrain_hpa/vae/checkpoint-50000` |
24
  | `hpa/vit.bin` | Image-embedding ViT for HPA: 12 layers, 512 hidden, 2048 MLP, 8 heads, patch 4, 256x256 input. Trained to identify the protein in an image over 13,908 classes; the embedding is the representation, not the prediction. Four input channels — protein, nucleus, ER, microtubules | `pretrain_hpa/vit/checkpoint-16000` |