Add tiny processor fixture for testing

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+output.png filter=lfs diff=lfs merge=lfs -text
+receipt_00008.png filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,152 @@
+{
+  "architectures": [
+    "Kosmos2_5ForConditionalGeneration"
+  ],
+  "latent_query_num": 2048,
+  "model_type": "kosmos-2.5",
+  "text_config": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "attention_heads": 16,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dropout": 0,
+    "early_stopping": false,
+    "embed_dim": 1536,
+    "pad_token_id": 1,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 6144,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "layerdrop": 0.0,
+    "layers": 24,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "kosmos_2_5_text_model",
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": true,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torch_dtype": null,
+    "torchscript": false,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 108481
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "intermediate_size": 3968,
+    "head_dim": 64,
+    "decoder_start_token_id": null,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1536,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 1e-10,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 4096,
+    "min_length": 0,
+    "model_type": "kosmos_2_5_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 24,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 18,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_embed_hidden_size": 768,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "max_num_patches": 4096,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vocab_size": 8704
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": false,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.0.dev0",
+  "num_beam" : 1,
+  "do_sample": false
+}

md.py

@@ -0,0 +1,33 @@
+import re
+import torch
+import requests
+from PIL import Image, ImageDraw
+from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration
+
+repo = "microsoft/kosmos-2.5"
+device = "cuda:0"
+dtype = torch.bfloat16
+model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=device, torch_dtype=dtype)
+processor = AutoProcessor.from_pretrained(repo)
+
+# sample image
+url = "https://huggingface.co/microsoft/kosmos-2.5/resolve/main/receipt_00008.png"
+image = Image.open(requests.get(url, stream=True).raw)
+
+prompt = "<md>"
+inputs = processor(text=prompt, images=image, return_tensors="pt")
+
+height, width = inputs.pop("height"), inputs.pop("width")
+raw_width, raw_height = image.size
+scale_height = raw_height / height
+scale_width = raw_width / width
+
+inputs = {k: v.to(device) if v is not None else None for k, v in inputs.items()}
+inputs["flattened_patches"] = inputs["flattened_patches"].to(dtype)
+generated_ids = model.generate(
+    **inputs,
+    max_new_tokens=1024,
+)
+
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
+print(generated_text[0])

ocr.py

@@ -0,0 +1,73 @@
+import re
+import torch
+import requests
+from PIL import Image, ImageDraw
+from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration
+
+repo = "microsoft/kosmos-2.5"
+device = "cuda:0"
+dtype = torch.bfloat16
+model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=device, torch_dtype=dtype)
+processor = AutoProcessor.from_pretrained(repo)
+
+# sample image
+url = "https://huggingface.co/microsoft/kosmos-2.5/resolve/main/receipt_00008.png"
+image = Image.open(requests.get(url, stream=True).raw)
+
+# bs = 1
+prompt = "<ocr>"
+inputs = processor(text=prompt, images=image, return_tensors="pt")
+height, width = inputs.pop("height"), inputs.pop("width")
+raw_width, raw_height = image.size
+scale_height = raw_height / height
+scale_width = raw_width / width
+
+# bs > 1, batch generation
+# inputs = processor(text=[prompt, prompt], images=[image,image], return_tensors="pt")
+# height, width = inputs.pop("height"), inputs.pop("width")
+# raw_width, raw_height = image.size
+# scale_height = raw_height / height[0]
+# scale_width = raw_width / width[0]
+
+inputs = {k: v.to(device) if v is not None else None for k, v in inputs.items()}
+inputs["flattened_patches"] = inputs["flattened_patches"].to(dtype)
+generated_ids = model.generate(
+    **inputs,
+    max_new_tokens=1024,
+)
+
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
+def post_process(y, scale_height, scale_width):
+    y = y.replace(prompt, "")
+    if "<md>" in prompt:
+        return y
+    pattern = r"<bbox><x_\d+><y_\d+><x_\d+><y_\d+></bbox>"
+    bboxs_raw = re.findall(pattern, y)
+    lines = re.split(pattern, y)[1:]
+    bboxs = [re.findall(r"\d+", i) for i in bboxs_raw]
+    bboxs = [[int(j) for j in i] for i in bboxs]
+    info = ""
+    for i in range(len(lines)):
+        box = bboxs[i]
+        x0, y0, x1, y1 = box
+        if not (x0 >= x1 or y0 >= y1):
+            x0 = int(x0 * scale_width)
+            y0 = int(y0 * scale_height)
+            x1 = int(x1 * scale_width)
+            y1 = int(y1 * scale_height)
+            info += f"{x0},{y0},{x1},{y0},{x1},{y1},{x0},{y1},{lines[i]}"
+    return info
+
+output_text = post_process(generated_text[0], scale_height, scale_width)
+print(output_text)
+
+draw = ImageDraw.Draw(image)
+lines = output_text.split("\n")
+for line in lines:
+    # draw the bounding box
+    line = list(line.split(","))
+    if len(line) < 8:
+        continue
+    line = list(map(int, line[:8]))
+    draw.polygon(line, outline="red")
+image.save("output.png")

preprocessor_config.json

@@ -0,0 +1,5 @@
+{
+    "image_processor_type": "Kosmos2_5ImageProcessor",
+    "processor_class": "Kosmos2_5Processor"
+  }
+