salesforce/BLIP
1
0
Fork 0
mirror of https://github.com/salesforce/BLIP.git synced 2026-01-26 15:19:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

update demo

Browse Source
This commit is contained in:
root
2022-01-28 12:59:36 +00:00
parent 48e4eba7a9
commit f68d24cf16
6 changed files with 18 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
demo.ipynb
View File

@@ -1,5 +1,13 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "bb2e6f60",
"metadata": {},
"source": [
"# BLIP: Inference Demo"
]
},
{
"cell_type": "code",
"execution_count": null,
@@ -53,7 +61,8 @@
"id": "f72f4406",
"metadata": {},
"source": [
"# Image Captioning"
"# Image Captioning\n",
"Perform image captioning using finetuned BLIP model"
]
},
{
@@ -98,7 +107,8 @@
"id": "fac320a2",
"metadata": {},
"source": [
"# VQA"
"# VQA\n",
"Perform visual question answering using finetuned BLIP model"
]
},
{

4
models/blip.py
View File

@@ -20,7 +20,7 @@ from timm.models.hub import download_cached_file
class BLIP_Base(nn.Module):
def __init__(self,
med_config = './configs/med_config.json',
med_config = 'configs/med_config.json',
image_size = 384,
vit = 'base',
vit_grad_ckpt = False,
@@ -75,7 +75,7 @@ class BLIP_Base(nn.Module):
class BLIP_Decoder(nn.Module):
def __init__(self,
med_config = './configs/med_config.json',
med_config = 'configs/med_config.json',
image_size = 384,
vit = 'base',
vit_grad_ckpt = False,

2
models/blip_nlvr.py
View File

@@ -13,7 +13,7 @@ import numpy as np
class BLIP_NLVR(nn.Module):
def __init__(self,
med_config = './configs/med_config.json',
med_config = 'configs/med_config.json',
image_size = 480,
vit = 'base',
vit_grad_ckpt = False,

2
models/blip_pretrain.py
View File

@@ -18,7 +18,7 @@ from models.blip import create_vit, init_tokenizer, load_checkpoint
class BLIP_Pretrain(nn.Module):
def __init__(self,
med_config = './configs/bert_config.json',
med_config = 'configs/bert_config.json',
image_size = 224,
vit = 'base',
vit_grad_ckpt = False,

2
models/blip_retrieval.py
View File

@@ -9,7 +9,7 @@ from models.blip import create_vit, init_tokenizer, load_checkpoint
class BLIP_Retrieval(nn.Module):
def __init__(self,
med_config = './configs/med_config.json',
med_config = 'configs/med_config.json',
image_size = 384,
vit = 'base',
vit_grad_ckpt = False,

2
models/blip_vqa.py
View File

@@ -9,7 +9,7 @@ import numpy as np
class BLIP_VQA(nn.Module):
def __init__(self,
med_config = './configs/med_config.json',
med_config = 'configs/med_config.json',
image_size = 480,
vit = 'base',
vit_grad_ckpt = False,