-
Notifications
You must be signed in to change notification settings - Fork 16
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
66da5e2
commit 94b5736
Showing
2 changed files
with
245 additions
and
0 deletions.
There are no files selected for viewing
210 changes: 210 additions & 0 deletions
210
Generative AI/ImageToTextGenerator/ImageToTextGenerator.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,210 @@ | ||
| { | ||
| "nbformat": 4, | ||
| "nbformat_minor": 0, | ||
| "metadata": { | ||
| "colab": { | ||
| "provenance": [], | ||
| "gpuType": "T4" | ||
| }, | ||
| "kernelspec": { | ||
| "name": "python3", | ||
| "display_name": "Python 3" | ||
| }, | ||
| "language_info": { | ||
| "name": "python" | ||
| }, | ||
| "accelerator": "GPU", | ||
| "gpuClass": "standard" | ||
| }, | ||
| "cells": [ | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 16, | ||
| "metadata": { | ||
| "id": "SeT-a9Byby1n" | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "\n", | ||
| "from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer\n", | ||
| "import torch\n", | ||
| "from PIL import Image" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "source": [ | ||
| "\n", | ||
| "model = VisionEncoderDecoderModel.from_pretrained(\"nlpconnect/vit-gpt2-image-captioning\")\n", | ||
| "feature_extractor = ViTImageProcessor.from_pretrained(\"nlpconnect/vit-gpt2-image-captioning\")\n", | ||
| "tokenizer = AutoTokenizer.from_pretrained(\"nlpconnect/vit-gpt2-image-captioning\")\n", | ||
| "\n", | ||
| "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n", | ||
| "model.to(device)" | ||
| ], | ||
| "metadata": { | ||
| "colab": { | ||
| "base_uri": "https://localhost:8080/" | ||
| }, | ||
| "id": "Gh2jscQnot8g", | ||
| "outputId": "fe64ca40-7f91-4cd4-8967-5c00bb0ce857" | ||
| }, | ||
| "execution_count": 17, | ||
| "outputs": [ | ||
| { | ||
| "output_type": "execute_result", | ||
| "data": { | ||
| "text/plain": [ | ||
| "VisionEncoderDecoderModel(\n", | ||
| " (encoder): ViTModel(\n", | ||
| " (embeddings): ViTEmbeddings(\n", | ||
| " (patch_embeddings): ViTPatchEmbeddings(\n", | ||
| " (projection): Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16))\n", | ||
| " )\n", | ||
| " (dropout): Dropout(p=0.0, inplace=False)\n", | ||
| " )\n", | ||
| " (encoder): ViTEncoder(\n", | ||
| " (layer): ModuleList(\n", | ||
| " (0-11): 12 x ViTLayer(\n", | ||
| " (attention): ViTAttention(\n", | ||
| " (attention): ViTSelfAttention(\n", | ||
| " (query): Linear(in_features=768, out_features=768, bias=True)\n", | ||
| " (key): Linear(in_features=768, out_features=768, bias=True)\n", | ||
| " (value): Linear(in_features=768, out_features=768, bias=True)\n", | ||
| " (dropout): Dropout(p=0.0, inplace=False)\n", | ||
| " )\n", | ||
| " (output): ViTSelfOutput(\n", | ||
| " (dense): Linear(in_features=768, out_features=768, bias=True)\n", | ||
| " (dropout): Dropout(p=0.0, inplace=False)\n", | ||
| " )\n", | ||
| " )\n", | ||
| " (intermediate): ViTIntermediate(\n", | ||
| " (dense): Linear(in_features=768, out_features=3072, bias=True)\n", | ||
| " (intermediate_act_fn): GELUActivation()\n", | ||
| " )\n", | ||
| " (output): ViTOutput(\n", | ||
| " (dense): Linear(in_features=3072, out_features=768, bias=True)\n", | ||
| " (dropout): Dropout(p=0.0, inplace=False)\n", | ||
| " )\n", | ||
| " (layernorm_before): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n", | ||
| " (layernorm_after): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n", | ||
| " )\n", | ||
| " )\n", | ||
| " )\n", | ||
| " (layernorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n", | ||
| " (pooler): ViTPooler(\n", | ||
| " (dense): Linear(in_features=768, out_features=768, bias=True)\n", | ||
| " (activation): Tanh()\n", | ||
| " )\n", | ||
| " )\n", | ||
| " (decoder): GPT2LMHeadModel(\n", | ||
| " (transformer): GPT2Model(\n", | ||
| " (wte): Embedding(50257, 768)\n", | ||
| " (wpe): Embedding(1024, 768)\n", | ||
| " (drop): Dropout(p=0.1, inplace=False)\n", | ||
| " (h): ModuleList(\n", | ||
| " (0-11): 12 x GPT2Block(\n", | ||
| " (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n", | ||
| " (attn): GPT2Attention(\n", | ||
| " (c_attn): Conv1D()\n", | ||
| " (c_proj): Conv1D()\n", | ||
| " (attn_dropout): Dropout(p=0.1, inplace=False)\n", | ||
| " (resid_dropout): Dropout(p=0.1, inplace=False)\n", | ||
| " )\n", | ||
| " (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n", | ||
| " (crossattention): GPT2Attention(\n", | ||
| " (c_attn): Conv1D()\n", | ||
| " (q_attn): Conv1D()\n", | ||
| " (c_proj): Conv1D()\n", | ||
| " (attn_dropout): Dropout(p=0.1, inplace=False)\n", | ||
| " (resid_dropout): Dropout(p=0.1, inplace=False)\n", | ||
| " )\n", | ||
| " (ln_cross_attn): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n", | ||
| " (mlp): GPT2MLP(\n", | ||
| " (c_fc): Conv1D()\n", | ||
| " (c_proj): Conv1D()\n", | ||
| " (act): NewGELUActivation()\n", | ||
| " (dropout): Dropout(p=0.1, inplace=False)\n", | ||
| " )\n", | ||
| " )\n", | ||
| " )\n", | ||
| " (ln_f): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n", | ||
| " )\n", | ||
| " (lm_head): Linear(in_features=768, out_features=50257, bias=False)\n", | ||
| " )\n", | ||
| ")" | ||
| ] | ||
| }, | ||
| "metadata": {}, | ||
| "execution_count": 17 | ||
| } | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "source": [ | ||
| "max_length = 16\n", | ||
| "num_beams = 4\n", | ||
| "gen_kwargs = {\"max_length\": max_length, \"num_beams\": num_beams}" | ||
| ], | ||
| "metadata": { | ||
| "id": "hm6EtiPoot27" | ||
| }, | ||
| "execution_count": 18, | ||
| "outputs": [] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "source": [ | ||
| "def predict_step(image_paths):\n", | ||
| " images = []\n", | ||
| " for image_path in image_paths:\n", | ||
| " i_image = Image.open(image_path)\n", | ||
| " if i_image.mode != \"RGB\":\n", | ||
| " i_image = i_image.convert(mode=\"RGB\")\n", | ||
| "\n", | ||
| " images.append(i_image)\n", | ||
| "\n", | ||
| " pixel_values = feature_extractor(images=images, return_tensors=\"pt\").pixel_values\n", | ||
| " pixel_values = pixel_values.to(device)\n", | ||
| "\n", | ||
| " output_ids = model.generate(pixel_values, **gen_kwargs)\n", | ||
| "\n", | ||
| " preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)\n", | ||
| " preds = [pred.strip() for pred in preds]\n", | ||
| " return preds" | ||
| ], | ||
| "metadata": { | ||
| "id": "FQ298E4gotu-" | ||
| }, | ||
| "execution_count": 19, | ||
| "outputs": [] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "source": [ | ||
| "predict_step(['/content/drive/MyDrive/images/Plane-flying-on-earth-atmosphere.jpg']) " | ||
| ], | ||
| "metadata": { | ||
| "colab": { | ||
| "base_uri": "https://localhost:8080/" | ||
| }, | ||
| "id": "u5ajgeTho6G_", | ||
| "outputId": "e6f62aa7-b0b7-4eff-947f-85a3a84e87ce" | ||
| }, | ||
| "execution_count": 22, | ||
| "outputs": [ | ||
| { | ||
| "output_type": "execute_result", | ||
| "data": { | ||
| "text/plain": [ | ||
| "['a large jetliner flying through a blue sky']" | ||
| ] | ||
| }, | ||
| "metadata": {}, | ||
| "execution_count": 22 | ||
| } | ||
| ] | ||
| } | ||
| ] | ||
| } |
35 changes: 35 additions & 0 deletions
35
Generative AI/ImageToTextGenerator/imagetotextgenerator.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,35 @@ | ||
| from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer | ||
| import torch | ||
| from PIL import Image | ||
|
|
||
| model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning") | ||
| feature_extractor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning") | ||
| tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning") | ||
|
|
||
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | ||
| model.to(device) | ||
|
|
||
| max_length = 16 | ||
| num_beams = 4 | ||
| gen_kwargs = {"max_length": max_length, "num_beams": num_beams} | ||
|
|
||
| def predict_step(image_paths): | ||
| images = [] | ||
| for image_path in image_paths: | ||
| i_image = Image.open(image_path) | ||
| if i_image.mode != "RGB": | ||
| i_image = i_image.convert(mode="RGB") | ||
|
|
||
| images.append(i_image) | ||
|
|
||
| pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values | ||
| pixel_values = pixel_values.to(device) | ||
|
|
||
| output_ids = model.generate(pixel_values, **gen_kwargs) | ||
|
|
||
| preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True) | ||
| preds = [pred.strip() for pred in preds] | ||
| return preds | ||
|
|
||
| predict_step(['/content/alexandr-podvalny-TciuHvwoK0k-unsplash.jpg']) | ||
|
|